{"id":"8745925f-e8d0-49b1-b0a5-d7738907ce32","entityType":"agent","slug":"clawhub-heldinhow-freeride-opencode","name":"Freeride Opencode","canonicalUrl":"https://www.xpersona.co/agent/clawhub-heldinhow-freeride-opencode","canonicalPath":"/agent/clawhub-heldinhow-freeride-opencode","generatedAt":"2026-10-09T18:05:24.605Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"Configure and optimize OpenCode Zen free models with smart fallbacks for subtasks, heartbeat, and cron jobs. Use when setting up cost-effective AI model routing with automatic failover between free models.","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 815 downloads reported by the source. Last updated 4/15/2026.","installCommand":"clawhub skill install kn74nrx32v4n0423jptzg1v5kx80ssnf:freeride-opencode","sourceUrl":"https://clawhub.ai/Heldinhow/freeride-opencode","homepage":"https://clawhub.ai/Heldinhow/freeride-opencode","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/Heldinhow/freeride-opencode","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":58,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Freeride Opencode technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"stars":null,"forks":null,"downloads":815,"packageName":null,"latestVersion":"1.2.0","tractionLabel":"815 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-03-01T02:13:02.120Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-03-01T02:13:02.120Z","lastIndexedAt":null,"nextCrawlAt":"2026-03-02T02:13:02.120Z","lastVerifiedAt":null,"highlights":[{"version":"1.2.0","createdAt":"2026-02-10T12:55:22.855Z","changelog":"Provider diversification strategy: Trinity Large via OpenRouter as first fallback to maximize resilience against rate limits.","fileCount":9,"zipByteSize":11378},{"version":"0.1.0","createdAt":"2026-02-08T14:32:56.003Z","changelog":"Initial release: configure OpenCode Zen free models with automatic, intelligent fallback and per-task selection. - Enables primary/fallback routing among free AI models to optimize cost and reliability. - Provides guided recommendations for selecting models by task type (primary, subtask, heartbeat, cron). - Includes structured example configurations and best practices for robust setup. - Documents supported free models with task suitability and fallback strategies. - Adds troubleshooting and links to further configuration references and templates.","fileCount":5,"zipByteSize":6158}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install kn74nrx32v4n0423jptzg1v5kx80ssnf:freeride-opencode","setupComplexity":"low","setupSteps":["Install using `clawhub skill install kn74nrx32v4n0423jptzg1v5kx80ssnf:freeride-opencode` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/Heldinhow/freeride-opencode before using production credentials."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-freeride-opencode/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-freeride-opencode/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-freeride-opencode/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-freeride-opencode/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-freeride-opencode/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-freeride-opencode/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T18:05:24.605Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-freeride-opencode/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-freeride-opencode/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-freeride-opencode/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-freeride-opencode/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"Skill: Freeride Opencode\n\nOwner: Heldinhow\n\nSummary: Configure and optimize OpenCode Zen free models with smart fallbacks for subtasks, heartbeat, and cron jobs. Use when setting up cost-effective AI model routing with automatic failover between free models.\n\nTags: latest:1.2.0\n\nVersion history:\n\nv1.2.0 | 2026-02-10T12:55:22.855Z | user\n\nProvider diversification strategy: Trinity Large via OpenRouter as first fallback to maximize resilience against rate limits.\n\nv0.1.0 | 2026-02-08T14:32:56.003Z | auto\n\nInitial release: configure OpenCode Zen free models with automatic, intelligent fallback and per-task selection.\n\n- Enables primary/fallback routing among free AI models to optimize cost and reliability.\n- Provides guided recommendations for selecting models by task type (primary, subtask, heartbeat, cron).\n- Includes structured example configurations and best practices for robust setup.\n- Documents supported free models with task suitability and fallback strategies.\n- Adds troubleshooting and links to further configuration references and templates.\n\nArchive index:\n\nArchive v1.2.0: 9 files, 11378 bytes\n\nFiles: examples/usage.md (5909b), PLAN.md (2075b), README.md (1111b), references/models.md (5649b), references/templates.md (3804b), SKILL.md (7835b), SPECIFICATION.md (2227b), TASKS.md (1925b), _meta.json (136b)\n\nFile v1.2.0:SKILL.md\n\n---\nname: freeride-opencode\ndescription: Configure and optimize OpenCode Zen free models with smart fallbacks for subtasks, heartbeat, and cron jobs. Use when setting up cost-effective AI model routing with automatic failover between free models.\nversion: 1.2.0\n---\n\n# Freeride OpenCode\n\nConfigure OpenCode Zen free models with intelligent fallbacks to optimize costs while maintaining reliability.\n\n> **⚠️ Important:** To use this skill, you need **two API keys**:\n> 1. **OpenCode Zen API key** - For OpenCode free models (MiniMax M2.1, Kimi K2.5, GLM 4.7, GPT 5 Nano)\n> 2. **OpenRouter API key** - For OpenRouter free models (Trinity Large and other OpenRouter providers)\n>\n> Configure both keys in your OpenCode/Zen settings before applying these configurations.\n\n## Quick Start\n\nApply optimal free model configuration with provider diversification:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      },\n      \"heartbeat\": {\n        \"model\": \"opencode/glm-4.7-free\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## 🔑 API Keys Required\n\nThis skill uses models from **two different providers**, so you need both API keys configured:\n\n### 1. OpenCode Zen API Key\n**Required for:**\n- `opencode/minimax-m2.1-free`\n- `opencode/kimi-k2.5-free`\n- `opencode/glm-4.7-free`\n- `opencode/gpt-5-nano`\n\n**Where to get:** Sign up at [OpenCode Zen](https://opencode.ai) and generate an API key.\n\n### 2. OpenRouter API Key\n**Required for:**\n- `openrouter/arcee-ai/trinity-large-preview:free`\n- Any other OpenRouter free models you add\n\n**Where to get:** Sign up at [OpenRouter.ai](https://openrouter.ai) and generate an API key.\n\n### Configuration\n\nAdd both keys to your OpenCode configuration:\n\n```json\n{\n  \"providers\": {\n    \"opencode\": {\n      \"api_key\": \"YOUR_OPENCODE_ZEN_API_KEY\"\n    },\n    \"openrouter\": {\n      \"api_key\": \"YOUR_OPENROUTER_API_KEY\"\n    }\n  }\n}\n```\n\n### Fallback Behavior by Provider\n\n- If **OpenCode models** fail → tries next OpenCode fallback or OpenRouter model\n- If **OpenRouter models** fail → tries next OpenRouter or OpenCode fallback\n- Configure both providers for maximum reliability\n\n## Model Selection Guide\n\nSee [models.md](models.md) for detailed model comparisons, capabilities, and provider information.\n\n| Task Type | Recommended Model | Rationale |\n|-----------|------------------|-----------|\n| **Primary/General** | MiniMax M2.1 Free | Best free model capability |\n| **Fallback 1** | Trinity Large Free | Different provider (OpenRouter) for rate limit resilience |\n| **Fallback 2** | Kimi K2.5 Free | General purpose, balance |\n| **Heartbeat** | GLM 4.7 Free | Multilingual, cost-effective for frequent checks |\n| **Subtasks/Subagents** | Kimi K2.5 Free | Balanced capability for secondary tasks |\n\n### Free Models Available\n\n| Model | ID | Best For |\n|-------|-----|----------|\n| **MiniMax M2.1 Free** | `opencode/minimax-m2.1-free` | Complex reasoning, coding (Primary) |\n| **Trinity Large Free** | `openrouter/arcee-ai/trinity-large-preview:free` | High-quality OpenRouter option (Fallback 1) |\n| **Kimi K2.5 Free** | `opencode/kimi-k2.5-free` | General purpose, balance (Fallback 2) |\n\n## Fallback Strategy\n\n### Provider Diversification (v1.2.0)\n\nThis version implements **provider diversification** to maximize resilience against rate limits and service disruptions:\n\n```json\n\"fallbacks\": [\n  \"openrouter/arcee-ai/trinity-large-preview:free\",  // Different provider (OpenRouter)\n  \"opencode/kimi-k2.5-free\"                           // Same provider as primary (OpenCode)\n]\n```\n\n**Why Provider Diversification Matters:**\n- **Rate limit isolation:** If OpenCode experiences rate limits, OpenRouter models remain available (and vice versa)\n- **First fallback from different provider:** Trinity Large on OpenRouter ensures continuity even if all OpenCode models are rate-limited\n- **Maximum resilience:** By spreading across providers, you avoid a single point of failure\n\n**Fallback triggers:**\n- Rate limits exceeded\n- Auth failures\n- Timeouts\n- Provider unavailability\n\n### Fallback Behavior by Provider\n\n- If **OpenCode models** fail → tries OpenRouter fallback first (Trinity Large), then back to OpenCode (Kimi)\n- If **OpenRouter model** fails → tries OpenCode fallback (Kimi)\n- This cross-provider approach ensures at least one model is usually available\n\n## Per-Task Configuration\n\n### Heartbeat (Every 30 min)\n\n```json\n\"heartbeat\": {\n  \"every\": \"30m\",\n  \"model\": \"opencode/gpt-5-nano\"\n}\n```\n\nUse the cheapest model for frequent, lightweight checks.\n\n### Subtasks/Subagents\n\n```json\n\"subagents\": {\n  \"model\": \"opencode/kimi-k2.5-free\"\n}\n```\n\nGood balance for secondary tasks that need reasonable capability.\n\n### Complete Example\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      },\n      \"models\": {\n        \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax M2.1\" },\n        \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi K2.5\" },\n        \"openrouter/arcee-ai/trinity-large-preview:free\": { \"alias\": \"Trinity Large\" }\n      },\n      \"heartbeat\": {\n        \"every\": \"30m\",\n        \"model\": \"opencode/glm-4.7-free\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Applying Configuration\n\nUse OpenClaw CLI:\n\n```bash\nopenclaw config.patch --raw '{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\"openrouter/arcee-ai/trinity-large-preview:free\", \"opencode/kimi-k2.5-free\"]\n      },\n      \"heartbeat\": { \"model\": \"opencode/glm-4.7-free\" },\n      \"subagents\": { \"model\": \"opencode/kimi-k2.5-free\" }\n    }\n  }\n}'\n```\n\n## Best Practices\n\n1. **Provider diversification** - Always have your first fallback from a different provider (e.g., OpenRouter) to avoid rate limits affecting all models\n2. **Keep fallbacks minimal** - 2-3 well-chosen fallbacks are better than many\n3. **Match model to task** - Don't use MiniMax for simple checks\n4. **Test fallback order** - Put more capable models first, with provider diversification\n5. **Monitor usage** - Track which models get used most\n\n## Troubleshooting\n\n**Authentication errors (401/403)?**\n- Check that you have **both** API keys configured:\n  - OpenCode Zen API key for OpenCode models\n  - OpenRouter API key for Trinity Large and OpenRouter models\n- Verify keys are valid and have not expired\n\n**Rate limits still occurring?**\n- Add provider diversification (ensure first fallback is from different provider)\n- Consider reducing heartbeat frequency\n\n**Responses too slow?**\n- Move GPT 5 Nano higher in fallback chain\n- Use simpler model for subtasks\n\n**Model not available?**\n- Check model ID format: `opencode/model-id-free` or `openrouter/provider/model:free`\n- Verify model is still free (check [models.md](models.md))\n- Ensure you have the correct API key for the provider\n\n**OpenRouter models not working?**\n- Verify OpenRouter API key is configured\n- Check OpenRouter account has credits/access\n- Some models may have additional access requirements\n\n## References\n\n### [models.md](models.md)\nComplete reference of all free models with capabilities, providers, performance comparisons, and error handling.\n\n### [templates.md](templates.md)\nReady-to-use configuration templates for different use cases (minimal, complete, cost-optimized, performance-optimized).\n\n### [examples/usage.md](examples/usage.md)\nPractical examples showing how to use this skill in real scenarios.\n\nFile v1.2.0:README.md\n\n# Freeride OpenCode Skill\n\n> ⚠️ **Para funcionar, são necessárias duas API keys:**\n> - **OpenCode Zen API key** - Para modelos OpenCode (MiniMax M2.1, Kimi K2.5, GLM 4.7, GPT 5 Nano)\n> - **OpenRouter API key** - Para modelos OpenRouter (Trinity Large e outros)\n\n## Descrição\n\nConfigure modelos free do OpenCode Zen com fallbacks inteligentes para otimizar custos mantendo confiabilidade.\n\n## Quick Start\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      }\n    }\n  }\n}\n```\n\n## Documentação Completa\n\nVeja [SKILL.md](SKILL.md) para documentação detalhada.\n\n## Modelos Disponíveis\n\n| Modelo | Provider | ID | Posição |\n|--------|----------|-----|---------|\n| MiniMax M2.1 | OpenCode | `opencode/minimax-m2.1-free` | Primary |\n| Trinity Large | OpenRouter | `openrouter/arcee-ai/trinity-large-preview:free` | Fallback 1 |\n| Kimi K2.5 | OpenCode | `opencode/kimi-k2.5-free` | Fallback 2 |\n\n## Versão\n\n1.2.0\n\nFile v1.2.0:_meta.json\n\n{\n  \"ownerId\": \"kn74nrx32v4n0423jptzg1v5kx80ssnf\",\n  \"slug\": \"freeride-opencode\",\n  \"version\": \"1.2.0\",\n  \"publishedAt\": 1770728122855\n}\n\nFile v1.2.0:references/models.md\n\n# OpenCode Zen Free Models Reference\n\n> **⚠️ API Keys Required:**\n> - **OpenCode models:** Requires OpenCode Zen API key\n> - **OpenRouter models:** Requires OpenRouter API key\n>\n> Configure both keys in your OpenCode settings for full fallback coverage.\n\n## Complete Model List\n\n### MiniMax M2.1 Free (Primary)\n- **ID:** `opencode/minimax-m2.1-free`\n- **Provider:** MiniMax (via OpenCode)\n- **Best for:** Complex coding tasks, reasoning, multi-step workflows\n- **Context:** Large context window\n- **Strengths:** Strong coding capability, good reasoning\n\n### Trinity Large Free (Fallback 1 - Different Provider)\n- **ID:** `openrouter/arcee-ai/trinity-large-preview:free`\n- **Provider:** Arcee AI (via OpenRouter)\n- **Best for:** Complex reasoning, coding, multi-step workflows\n- **Context:** Large context window\n- **Strengths:** High-quality model, **different provider** for rate limit resilience\n- **Why Fallback 1:** Being on OpenRouter, this model remains available when OpenCode models are rate-limited\n\n### Kimi K2.5 Free (Fallback 2)\n- **ID:** `opencode/kimi-k2.5-free`\n- **Provider:** Moonshot AI (Kimi) (via OpenCode)\n- **Best for:** General purpose, balanced performance\n- **Context:** Large context window\n- **Strengths:** Good all-around model, reliable responses\n\n### GLM 4.7 Free\n- **ID:** `opencode/glm-4.7-free`\n- **Provider:** Zhipu AI (GLM)\n- **Best for:** Multilingual tasks, alternative provider fallback\n- **Context:** Medium-large context\n- **Strengths:** Multilingual support, different provider ecosystem\n\n### GPT 5 Nano\n- **ID:** `opencode/gpt-5-nano`\n- **Provider:** OpenAI\n- **Best for:** Simple tasks, high-frequency operations, quick checks\n- **Context:** Smaller context window\n- **Strengths:** Fastest responses, lowest cost\n\n## Provider Information\n\n### OpenCode (MiniMax, Moonshot AI/Kimi)\n- Primary provider for free models\n- Requires OpenCode Zen API key\n- Models: MiniMax M2.1, Kimi K2.5\n\n### OpenRouter (Arcee AI/Trinity Large)\n- **Different provider** from OpenCode\n- Aggregation platform with multiple model providers\n- Trinity Large: Arcee AI's large language model\n- Focus: High-quality reasoning and coding\n- **Requires OpenRouter API key** (separate from OpenCode Zen)\n- **Key benefit:** Rate limits on OpenCode do NOT affect OpenRouter models\n\n## Rate Limits by Model\n\n| Model | Typical Rate Limits | Notes |\n|-------|--------------------|-------|\n| MiniMax M2.1 Free | Medium | Most popular free model |\n| Trinity Large Free | Medium | **Different provider** - available when OpenCode is rate-limited |\n| Kimi K2.5 Free | Medium-High | Good availability within OpenCode |\n\n## Performance Comparison\n\n| Model | Speed | Capability | Provider Diversification |\n|-------|-------|------------|-------------------------|\n| MiniMax M2.1 Free | Medium | Highest | Primary (OpenCode) |\n| Trinity Large Free | Medium | High | Fallback 1 (OpenRouter) ✅ |\n| Kimi K2.5 Free | Medium-High | High | Fallback 2 (OpenCode) |\n\n## Configuration Tips\n\n### For High-Volume Tasks\n```\nPrimary: MiniMax M2.1 Free (OpenCode)\nFallback 1: Trinity Large Free (OpenRouter) ✅ Provider Diversification\nFallback 2: Kimi K2.5 Free (OpenCode)\n```\n\n### For Critical Tasks\n```\nPrimary: MiniMax M2.1 Free (OpenCode)\nFallback 1: Trinity Large Free (OpenRouter) ✅ Provider Diversification\nFallback 2: Kimi K2.5 Free (OpenCode)\n(Ensure at least one fallback is from different provider)\n```\n\n### For Cost-Sensitive Setups\n```\nPrimary: GPT 5 Nano\nFallbacks: Kimi K2.5 Free → Trinity Large Free → MiniMax M2.1 Free\n(Use cheapest first, upgrade only if needed)\n```\n\n## Error Handling\n\n### Common Errors and Responses\n\n1. **Rate Limit (429)**\n   - Action: Try next fallback immediately\n   - Prevention: More fallbacks configured\n\n2. **Auth Error (401/403)**\n   - **OpenCode models:** Check OpenCode Zen API key\n   - **OpenRouter models:** Check OpenRouter API key\n   - Action: Try next fallback (may be from different provider)\n\n3. **Timeout (408/504)**\n   - Action: Try next fallback\n   - Prevention: Check network, reduce request size\n\n4. **Model Not Found (404)**\n   - Action: Remove from fallback chain\n   - Check: Model ID and availability\n   - OpenRouter models may require additional access/credits\n\n5. **Provider-Specific Errors**\n   - OpenCode errors: Verify OpenCode Zen API key and subscription\n   - OpenRouter errors: Verify OpenRouter API key has credits\n\n### Health Check Commands\n\n```bash\n# Check OpenCode models available\nopencode models\n\n# Check current configuration\nopenclaw config.get\n\n# Verify gateway health\nopenclaw health\n```\n\n## Model Aliases\n\nSet friendly names in configuration:\n\n```json\n\"models\": {\n  \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax\" },\n  \"openrouter/arcee-ai/trinity-large-preview:free\": { \"alias\": \"Trinity Large\" },\n  \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi\" }\n}\n```\n\n## Migration from OpenRouter FreeRide\n\nIf migrating from the OpenRouter FreeRide skill:\n\n**Before:**\n```json\n\"model\": {\n  \"primary\": \"openrouter/qwen/qwen3-coder:free\",\n  \"fallbacks\": [\"openrouter/free:free\"]\n}\n```\n\n**After (OpenCode Zen with OpenRouter fallback - v1.2.0):**\n```json\n\"model\": {\n  \"primary\": \"opencode/minimax-m2.1-free\",\n  \"fallbacks\": [\"openrouter/arcee-ai/trinity-large-preview:free\", \"opencode/kimi-k2.5-free\"]\n}\n```\n\n**Key differences:**\n- Uses OpenCode Zen credentials (plus optional OpenRouter API key)\n- **Provider diversification:** First fallback is on OpenRouter (different provider)\n- High-quality free options with cross-provider resilience\n- Simplified 2-fallback chain\n\n**API Keys Needed:**\n- OpenCode Zen API key (primary)\n- OpenRouter API key (required for Trinity Large fallback)\n\nFile v1.2.0:references/templates.md\n\n# Configuration Templates\n\n## Minimal Template (Just Fallbacks)\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      }\n    }\n  }\n}\n```\n\n## Complete Template (All Optimizations)\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      },\n      \"models\": {\n        \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax M2.1\" },\n        \"openrouter/arcee-ai/trinity-large-preview:free\": { \"alias\": \"Trinity Large\" },\n        \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi K2.5\" },\n        \"opencode/glm-4.7-free\": { \"alias\": \"GLM 4.7\" }\n      },\n      \"heartbeat\": {\n        \"every\": \"30m\",\n        \"model\": \"opencode/glm-4.7-free\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Cost-Optimized Template (Cheapest First)\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/glm-4.7-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      },\n      \"heartbeat\": {\n        \"model\": \"opencode/glm-4.7-free\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Performance-Optimized Template (Best First)\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\"\n        ]\n      },\n      \"heartbeat\": {\n        \"model\": \"opencode/glm-4.7-free\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Subagent-Only Template\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Cron-Specific Template\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/glm-4.7-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\"\n        ]\n      }\n    }\n  }\n}\n```\n\n## Applying Templates\n\n> **⚠️ Prerequisites:** Ensure you have both API keys configured before applying templates:\n> - OpenCode Zen API key (for `opencode/*` models)\n> - OpenRouter API key (for `openrouter/*` models - Trinity Large)\n>\n> Without both keys, fallbacks will fail when switching providers.\n\n### Via CLI\n\n```bash\nopenclaw config.patch --raw '{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\"openrouter/arcee-ai/trinity-large-preview:free\", \"opencode/kimi-k2.5-free\"]\n      }\n    }\n  }\n}'\n```\n\n### Via Gateway API\n\n```bash\nopenclaw gateway call config.patch --params '{\n  \"raw\": \"{\\\"agents\\\":{\\\"defaults\\\":{\\\"model\\\":{\\\"primary\\\":\\\"opencode/minimax-m2.1-free\\\",\\\"fallbacks\\\":[\\\"openrouter/arcee-ai/trinity-large-preview:free\\\",\\\"opencode/kimi-k2.5-free\\\"]}}}}\"\n}'\n```\n\n### Manual Edit\n\nEdit `~/.openclaw/openclaw.json` directly, then run:\n\n```bash\nopenclaw gateway restart\n```\n\n## Verifying Configuration\n\nAfter applying:\n\n```bash\n# Check model configuration\nopenclaw config.get | jq '.agents.defaults.model'\n\n# List available models\nopencode models | grep -E \"opencode/.*-free\"\n\n# Test fallback\nopencode run \"Hello\" --model opencode/minimax-m2.1-free\n```\n\n## Resetting to Defaults\n\nTo remove FreeRide configuration and return to defaults:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"anthropic/claude-sonnet-4-5\"\n      }\n    }\n  }\n}\n```\n\nFile v1.2.0:examples/usage.md\n\n# Usage Examples\n\n## Example 1: Initial Setup\n\n**User Request:**\n> \"I want to configure my OpenClaw to use free models from OpenCode Zen\"\n\n**Response:**\nI'll configure optimal free model fallbacks for you:\n\n```bash\n# Apply the configuration\nopenclaw config.patch --raw '{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\"\n        ]\n      },\n      \"models\": {\n        \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax M2.1\" },\n        \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi K2.5\" },\n        \"opencode/glm-4.7-free\": {},\n        \"opencode/gpt-5-nano\": {}\n      }\n    }\n  }\n}'\n```\n\n## Example 2: Optimizing for Subtasks\n\n**User Request:**\n> \"My subtasks are slow and expensive. How can I use a cheaper model?\"\n\n**Response:**\nLet's switch subtasks to GPT 5 Nano for faster, cheaper processing:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"subagents\": {\n        \"model\": \"opencode/gpt-5-nano\"\n      }\n    }\n  }\n}\n```\n\n**Apply:**\n```bash\nopenclaw config.patch --raw '{\"agents\":{\"defaults\":{\"subagents\":{\"model\":\"opencode/gpt-5-nano\"}}}}'\n```\n\n## Example 3: Reducing Heartbeat Costs\n\n**User Request:**\n> \"I have heartbeat running every 5 minutes and it's costing too much\"\n\n**Response:**\nLet's use GPT 5 Nano for heartbeat and increase interval to 30 minutes:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"heartbeat\": {\n        \"every\": \"30m\",\n        \"model\": \"opencode/gpt-5-nano\"\n      }\n    }\n  }\n}\n```\n\n## Example 4: Custom Fallback Chain\n\n**User Request:**\n> \"I want to prioritize Kimi over MiniMax as my primary\"\n\n**Response:**\nHere's the configuration with Kimi as primary:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/kimi-k2.5-free\",\n        \"fallbacks\": [\n          \"opencode/minimax-m2.1-free\",\n          \"opencode/glm-4.7-free\"\n        ]\n      }\n    }\n  }\n}\n```\n\n## Example 5: Adding a New Fallback\n\n**User Request:**\n> \"How do I add another model to my fallback chain?\"\n\n**Response:**\nJust add it to the fallbacks array:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\",\n          \"opencode/new-model-free\"  // New fallback\n        ]\n      }\n    }\n  }\n}\n```\n\n## Example 6: Checking Current Configuration\n\n**User Request:**\n> \"What models am I currently using?\"\n\n**Response:**\nLet me check your configuration:\n\n```bash\nopenclaw config.get | jq '.agents.defaults.model'\n```\n\n**Output:**\n```json\n{\n  \"primary\": \"opencode/minimax-m2.1-free\",\n  \"fallbacks\": [\n    \"opencode/kimi-k2.5-free\",\n    \"opencode/glm-4.7-free\",\n    \"opencode/gpt-5-nano\"\n  ]\n}\n```\n\n## Example 7: Switching from OpenRouter FreeRide\n\n**User Request:**\n> \"I'm coming from the OpenRouter FreeRide skill. How do I switch?\"\n\n**Response:**\nYour OpenRouter config:\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"openrouter/qwen/qwen3-coder:free\",\n        \"fallbacks\": [\"openrouter/free:free\"]\n      }\n    }\n  }\n}\n```\n\nSwitch to OpenCode Zen:\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\"\n        ]\n      }\n    }\n  }\n}\n```\n\n**Benefits:**\n- No separate API key needed\n- More free model options\n- Direct provider access\n- Better fallbacks\n\n## Example 8: Troubleshooting Rate Limits\n\n**User Request:**\n> \"I'm hitting rate limits on all my fallbacks\"\n\n**Response:**\nLet's add more fallbacks and check availability:\n\n```bash\n# Check available free models\nopencode models | grep -E \"opencode/.*-free\"\n```\n\n**Expand fallback chain:**\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\",\n          \"openrouter/free:free\"  // Fallback to OpenRouter\n        ]\n      }\n    }\n  }\n}\n```\n\n## Example 9: Performance Testing\n\n**User Request:**\n> \"I want to test which free model is fastest for simple tasks\"\n\n**Response:**\nLet's benchmark the models:\n\n```bash\n# Test each model\necho \"Testing MiniMax M2.1...\"\ntime opencode run \"What is 2+2?\" --model opencode/minimax-m2.1-free\n\necho \"Testing Kimi K2.5...\"\ntime opencode run \"What is 2+2?\" --model opencode/kimi-k2.5-free\n\necho \"Testing GPT 5 Nano...\"\ntime opencode run \"What is 2+2?\" --model opencode/gpt-5-nano\n```\n\n## Example 10: Complete Production Configuration\n\n**User Request:**\n> \"Give me a production-ready configuration\"\n\n**Response:**\nHere's a complete, optimized configuration:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\"\n        ]\n      },\n      \"models\": {\n        \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax M2.1\" },\n        \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi K2.5\" },\n        \"opencode/glm-4.7-free\": { \"alias\": \"GLM 4.7\" },\n        \"opencode/gpt-5-nano\": { \"alias\": \"GPT Nano\" }\n      },\n      \"heartbeat\": {\n        \"every\": \"30m\",\n        \"model\": \"opencode/gpt-5-nano\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      },\n      \"maxConcurrent\": 4,\n      \"compaction\": {\n        \"mode\": \"safeguard\"\n      }\n    }\n  }\n}\n```\n\n**Features:**\n- Best free model as primary\n- Three fallback options\n- Cheap heartbeat (30 min interval)\n- Balanced subtasks model\n- Aliases for all models\n- Concurrency limits\n- Context compaction enabled\n\nFile v1.2.0:PLAN.md\n\n# Plan: Add arcee-ai/trinity-large-preview:free Fallback\n\n## Objective\nUpdate freeride-opencode skill (v1.0.0 → v1.1.0) to include arcee-ai/trinity-large-preview:free via OpenRouter as an additional fallback option.\n\n## Steps\n\n### Step 1: Update SKILL.md\n- [ ] Bump version from 1.0.0 to 1.1.0\n- [ ] Add Trinity Large to Quick Start JSON example\n- [ ] Add Trinity Large to Model Selection Guide table\n- [ ] Add Trinity Large to Free Models Available table\n- [ ] Update Fallback Strategy section with new fallback order\n- [ ] Update Complete Example JSON\n- [ ] Update Best Practices section if needed\n\n### Step 2: Update references/models.md\n- [ ] Add new \"Trinity Large Free\" section with model details\n- [ ] Update Provider Information section (add OpenRouter)\n- [ ] Update Rate Limits by Model table\n- [ ] Update Performance Comparison table\n- [ ] Update Configuration Tips examples\n- [ ] Update Model Aliases section\n- [ ] Update Migration section (add Trinity mention)\n\n### Step 3: Update references/templates.md\n- [ ] Update Minimal Template fallback chain\n- [ ] Update Complete Template fallback chain\n- [ ] Add new template variant (Trinity-Focused) - optional\n- [ ] Update Verifying Configuration section\n- [ ] Update Resetting to Defaults section if needed\n\n### Step 4: Version Bump & Publish\n- [ ] Update version in SKILL.md header (already done in Step 1)\n- [ ] Validate all JSON examples are syntactically correct\n- [ ] Update any internal version references\n- [ ] Document changes in memory/today's file\n\n## Validation\n- All JSON examples parse correctly\n- Model IDs follow existing pattern (`openrouter/provider/model:free`)\n- Documentation is consistent with existing style\n- Backward compatibility maintained\n\n## Estimated Time\n- Step 1: 10 minutes\n- Step 2: 15 minutes\n- Step 3: 10 minutes\n- Step 4: 5 minutes\n- **Total: ~40 minutes**\n\n## Rollback Plan\nIf issues arise:\n1. Revert SKILL.md to v1.0.0\n2. Revert models.md to remove Trinity Large entry\n3. Revert templates.md fallback chains\n4. No configuration files need changes (skill is documentation-only)\n\nFile v1.2.0:SPECIFICATION.md\n\n# Specification: Add arcee-ai/trinity-large-preview:free Fallback\n\n## Overview\nUpdate the freeride-opencode skill to add `arcee-ai/trinity-large-preview:free` via OpenRouter as an additional fallback option.\n\n## Changes Summary\n- **New Model**: arcee-ai/trinity-large-preview:free (via OpenRouter)\n- **Model ID**: `openrouter/arcee-ai/trinity-large-preview:free`\n- **Position**: Added as second fallback option (after Kimi K2.5 Free, before GLM 4.7 Free)\n- **Version**: Bump from 1.0.0 to 1.1.0\n\n## Model Details\n- **Provider**: OpenRouter\n- **Model**: arcee-ai/trinity-large-preview\n- **Tier**: Free\n- **Best for**: Complex reasoning, coding tasks, multi-step workflows\n- **Strengths**: Additional high-quality option from different provider (OpenRouter)\n\n## Configuration Changes\n\n### Updated Fallback Chain\n```json\n\"fallbacks\": [\n  \"opencode/kimi-k2.5-free\",                                    // 2nd priority (high capability)\n  \"openrouter/arcee-ai/trinity-large-preview:free\",             // NEW: 3rd priority\n  \"opencode/glm-4.7-free\",                                       // 4th priority (multilingual)\n  \"opencode/gpt-5-nano\"                                          // 5th priority (fastest/cheapest)\n]\n```\n\n### Updated Model Aliases\n```json\n\"models\": {\n  \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax M2.1\" },\n  \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi K2.5\" },\n  \"openrouter/arcee-ai/trinity-large-preview:free\": { \"alias\": \"Trinity Large\" },\n  \"opencode/glm-4.7-free\": {},\n  \"opencode/gpt-5-nano\": {}\n}\n```\n\n## Files to Update\n1. **SKILL.md**: Update version, documentation, examples, and model table\n2. **references/models.md**: Add new model entry with details\n3. **references/templates.md**: Update fallback chains in all templates\n\n## Priority Rationale\n1. MiniMax M2.1 Free - Best overall free model\n2. Kimi K2.5 Free - Strong alternative\n3. **Trinity Large (NEW)** - New high-quality OpenRouter option\n4. GLM 4.7 Free - Multilingual/alternative provider\n5. GPT 5 Nano - Fastest, cheapest fallback\n\n## Backward Compatibility\n- Existing configurations without the new model will continue to work\n- New installations get enhanced fallback coverage\n- No breaking changes to API or configuration structure\n\nFile v1.2.0:TASKS.md\n\n# Tasks: Implement arcee-ai/trinity-large-preview:free Fallback\n\n## Task Checklist\n\n### Phase 1: Update SKILL.md\n- [ ] **T1.1**: Update version header: `version: 1.1.0`\n- [ ] **T1.2**: Update Quick Start JSON example with new fallback\n- [ ] **T1.3**: Add Trinity Large to Model Selection Guide table\n- [ ] **T1.4**: Add Trinity Large to Free Models Available table\n- [ ] **T1.5**: Update Fallback Strategy section with new order\n- [ ] **T1.6**: Update Complete Example JSON with Trinity Large\n\n### Phase 2: Update references/models.md\n- [ ] **T2.1**: Add \"### Trinity Large Free\" section with full details\n- [ ] **T2.2**: Add OpenRouter to Provider Information section\n- [ ] **T2.3**: Update Rate Limits by Model table (add Trinity row)\n- [ ] **T2.4**: Update Performance Comparison table (add Trinity row)\n- [ ] **T2.5**: Update Configuration Tips examples with Trinity\n- [ ] **T2.6**: Update Model Aliases section with Trinity entry\n\n### Phase 3: Update references/templates.md\n- [ ] **T3.1**: Update Minimal Template fallback chain\n- [ ] **T3.2**: Update Complete Template fallback chain\n- [ ] **T3.3**: Update Verifying Configuration section\n\n### Phase 4: Finalize\n- [ ] **T4.1**: Validate all JSON examples\n- [ ] **T4.2**: Update memory file with changes summary\n- [ ] **T4.3**: Final review of all modifications\n\n---\n\n## Implementation Details\n\n### Model ID Format\n```\nopenrouter/arcee-ai/trinity-large-preview:free\n```\n\n### Alias\n```\nTrinity Large\n```\n\n### Updated Fallback Order (by priority)\n1. opencode/minimax-m2.1-free (Primary)\n2. opencode/kimi-k2.5-free (Fallback 1)\n3. openrouter/arcee-ai/trinity-large-preview:free ← NEW\n4. opencode/glm-4.7-free\n5. opencode/gpt-5-nano\n\n### Files Modified\n- `/root/.openclaw/workspace/skills/freeride-opencode/SKILL.md`\n- `/root/.openclaw/workspace/skills/freeride-opencode/references/models.md`\n- `/root/.openclaw/workspace/skills/freeride-opencode/references/templates.md`\n\nArchive v0.1.0: 5 files, 6158 bytes\n\nFiles: examples/usage.md (5909b), references/models.md (3963b), references/templates.md (3438b), SKILL.md (4635b), _meta.json (136b)\n\nFile v0.1.0:SKILL.md\n\n---\nname: freeride-opencode\ndescription: Configure and optimize OpenCode Zen free models with smart fallbacks for subtasks, heartbeat, and cron jobs. Use when setting up cost-effective AI model routing with automatic failover between free models.\nversion: 1.0.0\n---\n\n# Freeride OpenCode\n\nConfigure OpenCode Zen free models with intelligent fallbacks to optimize costs while maintaining reliability.\n\n## Quick Start\n\nApply optimal free model configuration:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\"\n        ]\n      },\n      \"heartbeat\": {\n        \"model\": \"opencode/gpt-5-nano\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Model Selection Guide\n\nSee [models.md](models.md) for detailed model comparisons, capabilities, and provider information.\n\n| Task Type | Recommended Model | Rationale |\n|-----------|------------------|-----------|\n| **Primary/General** | MiniMax M2.1 Free | Best free model capability |\n| **Subtasks** | Kimi K2.5 Free | Balanced cost/performance |\n| **Heartbeat** | GPT 5 Nano | Fastest and cheapest |\n| **Cron Jobs** | Depends on complexity |\n\n### Free Models Available\n\n| Model | ID | Best For |\n|-------|-----|----------|\n| **MiniMax M2.1 Free** | `opencode/minimax-m2.1-free` | Complex reasoning, coding |\n| **Kimi K2.5 Free** | `opencode/kimi-k2.5-free` | General purpose, balance |\n| **GLM 4.7 Free** | `opencode/glm-4.7-free` | Multilingual, fallback |\n| **GPT 5 Nano** | `opencode/gpt-5-nano` | Simple tasks, high frequency |\n\n## Fallback Strategy\n\nConfigure fallbacks in priority order:\n\n```json\n\"fallbacks\": [\n  \"opencode/kimi-k2.5-free\",    // Second best capability\n  \"opencode/glm-4.7-free\",       // Alternative provider\n  \"opencode/gpt-5-nano\"          // Fallback of last resort\n]\n```\n\n**Fallback triggers:**\n- Rate limits exceeded\n- Auth failures\n- Timeouts\n- Provider unavailability\n\n## Per-Task Configuration\n\n### Heartbeat (Every 30 min)\n\n```json\n\"heartbeat\": {\n  \"every\": \"30m\",\n  \"model\": \"opencode/gpt-5-nano\"\n}\n```\n\nUse the cheapest model for frequent, lightweight checks.\n\n### Subtasks/Subagents\n\n```json\n\"subagents\": {\n  \"model\": \"opencode/kimi-k2.5-free\"\n}\n```\n\nGood balance for secondary tasks that need reasonable capability.\n\n### Complete Example\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\"\n        ]\n      },\n      \"models\": {\n        \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax M2.1\" },\n        \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi K2.5\" },\n        \"opencode/glm-4.7-free\": {},\n        \"opencode/gpt-5-nano\": {}\n      },\n      \"heartbeat\": {\n        \"every\": \"30m\",\n        \"model\": \"opencode/gpt-5-nano\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Applying Configuration\n\nUse OpenClaw CLI:\n\n```bash\nopenclaw config.patch --raw '{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\"opencode/kimi-k2.5-free\", \"opencode/glm-4.7-free\", \"opencode/gpt-5-nano\"]\n      },\n      \"heartbeat\": { \"model\": \"opencode/gpt-5-nano\" },\n      \"subagents\": { \"model\": \"opencode/kimi-k2.5-free\" }\n    }\n  }\n}'\n```\n\n## Best Practices\n\n1. **Always have fallbacks** - Configure at least 2-3 fallback models\n2. **Mix providers** - Reduces single-provider risk\n3. **Match model to task** - Don't use MiniMax for simple checks\n4. **Test fallback order** - Put more capable models first\n5. **Monitor usage** - Track which models get used most\n\n## Troubleshooting\n\n**Rate limits still occurring?**\n- Add more fallback models\n- Consider reducing heartbeat frequency\n\n**Responses too slow?**\n- Move GPT 5 Nano higher in fallback chain\n- Use simpler model for subtasks\n\n**Model not available?**\n- Check model ID format: `opencode/model-id-free`\n- Verify model is still free (check [models.md](models.md))\n\n## References\n\n### [models.md](models.md)\nComplete reference of all free models with capabilities, providers, performance comparisons, and error handling.\n\n### [templates.md](templates.md)\nReady-to-use configuration templates for different use cases (minimal, complete, cost-optimized, performance-optimized).\n\n### [examples/usage.md](examples/usage.md)\nPractical examples showing how to use this skill in real scenarios.\n\nFile v0.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn74nrx32v4n0423jptzg1v5kx80ssnf\",\n  \"slug\": \"freeride-opencode\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1770561176003\n}\n\nFile v0.1.0:references/models.md\n\n# OpenCode Zen Free Models Reference\n\n## Complete Model List\n\n### MiniMax M2.1 Free\n- **ID:** `opencode/minimax-m2.1-free`\n- **Provider:** MiniMax\n- **Best for:** Complex coding tasks, reasoning, multi-step workflows\n- **Context:** Large context window\n- **Strengths:** Strong coding capability, good reasoning\n\n### Kimi K2.5 Free\n- **ID:** `opencode/kimi-k2.5-free`\n- **Provider:** Moonshot AI (Kimi)\n- **Best for:** General purpose, balanced performance\n- **Context:** Large context window\n- **Strengths:** Good all-around model, reliable responses\n\n### GLM 4.7 Free\n- **ID:** `opencode/glm-4.7-free`\n- **Provider:** Zhipu AI (GLM)\n- **Best for:** Multilingual tasks, alternative provider fallback\n- **Context:** Medium-large context\n- **Strengths:** Multilingual support, different provider ecosystem\n\n### GPT 5 Nano\n- **ID:** `opencode/gpt-5-nano`\n- **Provider:** OpenAI\n- **Best for:** Simple tasks, high-frequency operations, quick checks\n- **Context:** Smaller context window\n- **Strengths:** Fastest responses, lowest cost\n\n## Provider Information\n\n### MiniMax\n- API: `https://api.minimax.io/anthropic`\n- Documentation: OpenCode Zen docs\n\n### Moonshot AI (Kimi)\n- Known for: Kimi long-context model\n- Strong in: Document understanding, conversation\n\n### Zhipu AI (GLM)\n- Chinese AI company\n- Focus: Multilingual and Chinese language tasks\n\n### OpenAI\n- Established provider\n- GPT 5 Nano: Lightweight, fast variant\n\n## Rate Limits by Model\n\n| Model | Typical Rate Limits | Notes |\n|-------|--------------------|-------|\n| MiniMax M2.1 Free | Medium | Most popular free model |\n| Kimi K2.5 Free | Medium-High | Good availability |\n| GLM 4.7 Free | Medium | Alternative option |\n| GPT 5 Nano | High | Generous limits |\n\n## Performance Comparison\n\n| Model | Speed | Capability | Cost |\n|-------|-------|------------|------|\n| MiniMax M2.1 Free | Medium | Highest | Free |\n| Kimi K2.5 Free | Medium-High | High | Free |\n| GLM 4.7 Free | Medium | Medium-High | Free |\n| GPT 5 Nano | Fastest | Medium | Free |\n\n## Configuration Tips\n\n### For High-Volume Tasks\n```\nPrimary: MiniMax M2.1 Free\nFallbacks: Kimi K2.5 Free → GLM 4.7 Free → GPT 5 Nano\n```\n\n### For Critical Tasks\n```\nPrimary: MiniMax M2.1 Free\nFallbacks: Kimi K2.5 Free → GLM 4.7 Free\n(Remove GPT 5 Nano for higher quality)\n```\n\n### For Cost-Sensitive Setups\n```\nPrimary: GPT 5 Nano\nFallbacks: Kimi K2.5 Free → MiniMax M2.1 Free\n(Use cheapest first, upgrade only if needed)\n```\n\n## Error Handling\n\n### Common Errors and Responses\n\n1. **Rate Limit (429)**\n   - Action: Try next fallback immediately\n   - Prevention: More fallbacks configured\n\n2. **Auth Error (401/403)**\n   - Action: Try next fallback\n   - Check: API keys configured in OpenCode\n\n3. **Timeout (408/504)**\n   - Action: Try next fallback\n   - Prevention: Check network, reduce request size\n\n4. **Model Not Found (404)**\n   - Action: Remove from fallback chain\n   - Check: Model ID and availability\n\n### Health Check Commands\n\n```bash\n# Check OpenCode models available\nopencode models\n\n# Check current configuration\nopenclaw config.get\n\n# Verify gateway health\nopenclaw health\n```\n\n## Model Aliases\n\nSet friendly names in configuration:\n\n```json\n\"models\": {\n  \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax\" },\n  \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi\" },\n  \"opencode/glm-4.7-free\": { \"alias\": \"GLM\" },\n  \"opencode/gpt-5-nano\": { \"alias\": \"Nano\" }\n}\n```\n\n## Migration from OpenRouter FreeRide\n\nIf migrating from the OpenRouter FreeRide skill:\n\n**Before:**\n```json\n\"model\": {\n  \"primary\": \"openrouter/qwen/qwen3-coder:free\",\n  \"fallbacks\": [\"openrouter/free:free\"]\n}\n```\n\n**After (OpenCode Zen):**\n```json\n\"model\": {\n  \"primary\": \"opencode/minimax-m2.1-free\",\n  \"fallbacks\": [\"opencode/kimi-k2.5-free\", \"opencode/glm-4.7-free\", \"opencode/gpt-5-nano\"]\n}\n```\n\n**Key differences:**\n- No API key needed (uses OpenCode Zen credentials)\n- Multiple high-quality free options\n- Fallback to GPT 5 Nano available\n- No router overhead\n\nFile v0.1.0:references/templates.md\n\n# Configuration Templates\n\n## Minimal Template (Just Fallbacks)\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\"\n        ]\n      }\n    }\n  }\n}\n```\n\n## Complete Template (All Optimizations)\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\"\n        ]\n      },\n      \"models\": {\n        \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax M2.1\" },\n        \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi K2.5\" },\n        \"opencode/glm-4.7-free\": {},\n        \"opencode/gpt-5-nano\": {}\n      },\n      \"heartbeat\": {\n        \"every\": \"30m\",\n        \"model\": \"opencode/gpt-5-nano\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Cost-Optimized Template (Cheapest First)\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/gpt-5-nano\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/minimax-m2.1-free\",\n          \"opencode/glm-4.7-free\"\n        ]\n      },\n      \"heartbeat\": {\n        \"model\": \"opencode/gpt-5-nano\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/gpt-5-nano\"\n      }\n    }\n  }\n}\n```\n\n## Performance-Optimized Template (Best First)\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\"\n        ]\n      },\n      \"heartbeat\": {\n        \"model\": \"opencode/gpt-5-nano\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Subagent-Only Template\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Cron-Specific Template\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/gpt-5-nano\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\"\n        ]\n      }\n    }\n  }\n}\n```\n\n## Applying Templates\n\n### Via CLI\n\n```bash\nopenclaw config.patch --raw '{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\"opencode/kimi-k2.5-free\", \"opencode/glm-4.7-free\", \"opencode/gpt-5-nano\"]\n      }\n    }\n  }\n}'\n```\n\n### Via Gateway API\n\n```bash\nopenclaw gateway call config.patch --params '{\n  \"raw\": \"{\\\"agents\\\":{\\\"defaults\\\":{\\\"model\\\":{\\\"primary\\\":\\\"opencode/minimax-m2.1-free\\\",\\\"fallbacks\\\":[\\\"opencode/kimi-k2.5-free\\\",\\\"opencode/glm-4.7-free\\\",\\\"opencode/gpt-5-nano\\\"]}}}}\"\n}'\n```\n\n### Manual Edit\n\nEdit `~/.openclaw/openclaw.json` directly, then run:\n\n```bash\nopenclaw gateway restart\n```\n\n## Verifying Configuration\n\nAfter applying:\n\n```bash\n# Check model configuration\nopenclaw config.get | jq '.agents.defaults.model'\n\n# List available models\nopencode models | grep -E \"opencode/.*-free\"\n\n# Test fallback\nopencode run \"Hello\" --model opencode/minimax-m2.1-free\n```\n\n## Resetting to Defaults\n\nTo remove FreeRide configuration and return to defaults:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"anthropic/claude-sonnet-4-5\"\n      }\n    }\n  }\n}\n```\n\nFile v0.1.0:examples/usage.md\n\n# Usage Examples\n\n## Example 1: Initial Setup\n\n**User Request:**\n> \"I want to configure my OpenClaw to use free models from OpenCode Zen\"\n\n**Response:**\nI'll configure optimal free model fallbacks for you:\n\n```bash\n# Apply the configuration\nopenclaw config.patch --raw '{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\"\n        ]\n      },\n      \"models\": {\n        \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax M2.1\" },\n        \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi K2.5\" },\n        \"opencode/glm-4.7-free\": {},\n        \"opencode/gpt-5-nano\": {}\n      }\n    }\n  }\n}'\n```\n\n## Example 2: Optimizing for Subtasks\n\n**User Request:**\n> \"My subtasks are slow and expensive. How can I use a cheaper model?\"\n\n**Response:**\nLet's switch subtasks to GPT 5 Nano for faster, cheaper processing:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"subagents\": {\n        \"model\": \"opencode/gpt-5-nano\"\n      }\n    }\n  }\n}\n```\n\n**Apply:**\n```bash\nopenclaw config.patch --raw '{\"agents\":{\"defaults\":{\"subagents\":{\"model\":\"opencode/gpt-5-nano\"}}}}'\n```\n\n## Example 3: Reducing Heartbeat Costs\n\n**User Request:**\n> \"I have heartbeat running every 5 minutes and it's costing too much\"\n\n**Response:**\nLet's use GPT 5 Nano for heartbeat and increase interval to 30 minutes:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"heartbeat\": {\n        \"every\": \"30m\",\n        \"model\": \"opencode/gpt-5-nano\"\n      }\n    }\n  }\n}\n```\n\n## Example 4: Custom Fallback Chain\n\n**User Request:**\n> \"I want to prioritize Kimi over MiniMax as my primary\"\n\n**Response:**\nHere's the configuration with Kimi as primary:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/kimi-k2.5-free\",\n        \"fallbacks\": [\n          \"opencode/minimax-m2.1-free\",\n          \"opencode/glm-4.7-free\"\n        ]\n      }\n    }\n  }\n}\n```\n\n## Example 5: Adding a New Fallback\n\n**User Request:**\n> \"How do I add another model to my fallback chain?\"\n\n**Response:**\nJust add it to the fallbacks array:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\",\n          \"opencode/new-model-free\"  // New fallback\n        ]\n      }\n    }\n  }\n}\n```\n\n## Example 6: Checking Current Configuration\n\n**User Request:**\n> \"What models am I currently using?\"\n\n**Response:**\nLet me check your configuration:\n\n```bash\nopenclaw config.get | jq '.agents.defaults.model'\n```\n\n**Output:**\n```json\n{\n  \"primary\": \"opencode/minimax-m2.1-free\",\n  \"fallbacks\": [\n    \"opencode/kimi-k2.5-free\",\n    \"opencode/glm-4.7-free\",\n    \"opencode/gpt-5-nano\"\n  ]\n}\n```\n\n## Example 7: Switching from OpenRouter FreeRide\n\n**User Request:**\n> \"I'm coming from the OpenRouter FreeRide skill. How do I switch?\"\n\n**Response:**\nYour OpenRouter config:\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"openrouter/qwen/qwen3-coder:free\",\n        \"fallbacks\": [\"openrouter/free:free\"]\n      }\n    }\n  }\n}\n```\n\nSwitch to OpenCode Zen:\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\"\n        ]\n      }\n    }\n  }\n}\n```\n\n**Benefits:**\n- No separate API key needed\n- More free model options\n- Direct provider access\n- Better fallbacks\n\n## Example 8: Troubleshooting Rate Limits\n\n**User Request:**\n> \"I'm hitting rate limits on all my fallbacks\"\n\n**Response:**\nLet's add more fallbacks and check availability:\n\n```bash\n# Check available free models\nopencode models | grep -E \"opencode/.*-free\"\n```\n\n**Expand fallback chain:**\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\",\n          \"openrouter/free:free\"  // Fallback to OpenRouter\n        ]\n      }\n    }\n  }\n}\n```\n\n## Example 9: Performance Testing\n\n**User Request:**\n> \"I want to test which free model is fastest for simple tasks\"\n\n**Response:**\nLet's benchmark the models:\n\n```bash\n# Test each model\necho \"Testing MiniMax M2.1...\"\ntime opencode run \"What is 2+2?\" --model opencode/minimax-m2.1-free\n\necho \"Testing Kimi K2.5...\"\ntime opencode run \"What is 2+2?\" --model opencode/kimi-k2.5-free\n\necho \"Testing GPT 5 Nano...\"\ntime opencode run \"What is 2+2?\" --model opencode/gpt-5-nano\n```\n\n## Example 10: Complete Production Configuration\n\n**User Request:**\n> \"Give me a production-ready configuration\"\n\n**Response:**\nHere's a complete, optimized configuration:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\",\n          \"opencode/glm-4.7-free\",\n          \"opencode/gpt-5-nano\"\n        ]\n      },\n      \"models\": {\n        \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax M2.1\" },\n        \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi K2.5\" },\n        \"opencode/glm-4.7-free\": { \"alias\": \"GLM 4.7\" },\n        \"opencode/gpt-5-nano\": { \"alias\": \"GPT Nano\" }\n      },\n      \"heartbeat\": {\n        \"every\": \"30m\",\n        \"model\": \"opencode/gpt-5-nano\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      },\n      \"maxConcurrent\": 4,\n      \"compaction\": {\n        \"mode\": \"safeguard\"\n      }\n    }\n  }\n}\n```\n\n**Features:**\n- Best free model as primary\n- Three fallback options\n- Cheap heartbeat (30 min interval)\n- Balanced subtasks model\n- Aliases for all models\n- Concurrency limits\n- Context compaction enabled","readmeExcerpt":"Skill: Freeride Opencode Owner: Heldinhow Summary: Configure and optimize OpenCode Zen free models with smart fallbacks for subtasks, heartbeat, and cron jobs. Use when setting up cost-effective AI model routing with automatic failover between free models. Tags: latest:1.2.0 Version history: v1.2.0 | 2026-02-10T12:55:22.855Z | user Provider diversification strategy: Trinity Large via OpenRouter as first fallback to m","codeSnippets":[],"executableExamples":[{"language":"json","snippet":"{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      },\n      \"heartbeat\": {\n        \"model\": \"opencode/glm-4.7-free\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}"},{"language":"json","snippet":"{\n  \"providers\": {\n    \"opencode\": {\n      \"api_key\": \"YOUR_OPENCODE_ZEN_API_KEY\"\n    },\n    \"openrouter\": {\n      \"api_key\": \"YOUR_OPENROUTER_API_KEY\"\n    }\n  }\n}"},{"language":"json","snippet":"\"fallbacks\": [\n  \"openrouter/arcee-ai/trinity-large-preview:free\",  // Different provider (OpenRouter)\n  \"opencode/kimi-k2.5-free\"                           // Same provider as primary (OpenCode)\n]"},{"language":"json","snippet":"\"heartbeat\": {\n  \"every\": \"30m\",\n  \"model\": \"opencode/gpt-5-nano\"\n}"},{"language":"json","snippet":"\"subagents\": {\n  \"model\": \"opencode/kimi-k2.5-free\"\n}"},{"language":"json","snippet":"{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      },\n      \"models\": {\n        \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax M2.1\" },\n        \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi K2.5\" },\n        \"openrouter/arcee-ai/trinity-large-preview:free\": { \"alias\": \"Trinity Large\" }\n      },\n      \"heartbeat\": {\n        \"every\": \"30m\",\n        \"model\": \"opencode/glm-4.7-free\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: freeride-opencode\ndescription: Configure and optimize OpenCode Zen free models with smart fallbacks for subtasks, heartbeat, and cron jobs. Use when setting up cost-effective AI model routing with automatic failover between free models.\nversion: 1.2.0\n---\n\n# Freeride OpenCode\n\nConfigure OpenCode Zen free models with intelligent fallbacks to optimize costs while maintaining reliability.\n\n> **⚠️ Important:** To use this skill, you need **two API keys**:\n> 1. **OpenCode Zen API key** - For OpenCode free models (MiniMax M2.1, Kimi K2.5, GLM 4.7, GPT 5 Nano)\n> 2. **OpenRouter API key** - For OpenRouter free models (Trinity Large and other OpenRouter providers)\n>\n> Configure both keys in your OpenCode/Zen settings before applying these configurations.\n\n## Quick Start\n\nApply optimal free model configuration with provider diversification:\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      },\n      \"heartbeat\": {\n        \"model\": \"opencode/glm-4.7-free\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## 🔑 API Keys Required\n\nThis skill uses models from **two different providers**, so you need both API keys configured:\n\n### 1. OpenCode Zen API Key\n**Required for:**\n- `opencode/minimax-m2.1-free`\n- `opencode/kimi-k2.5-free`\n- `opencode/glm-4.7-free`\n- `opencode/gpt-5-nano`\n\n**Where to get:** Sign up at [OpenCode Zen](https://opencode.ai) and generate an API key.\n\n### 2. OpenRouter API Key\n**Required for:**\n- `openrouter/arcee-ai/trinity-large-preview:free`\n- Any other OpenRouter free models you add\n\n**Where to get:** Sign up at [OpenRouter.ai](https://openrouter.ai) and generate an API key.\n\n### Configuration\n\nAdd both keys to your OpenCode configuration:\n\n```json\n{\n  \"providers\": {\n    \"opencode\": {\n      \"api_key\": \"YOUR_OPENCODE_ZEN_API_KEY\"\n    },\n    \"openrouter\": {\n      \"api_key\": \"YOUR_OPENROUTER_API_KEY\"\n    }\n  }\n}\n```\n\n### Fallback Behavior by Provider\n\n- If **OpenCode models** fail → tries next OpenCode fallback or OpenRouter model\n- If **OpenRouter models** fail → tries next OpenRouter or OpenCode fallback\n- Configure both providers for maximum reliability\n\n## Model Selection Guide\n\nSee [models.md](models.md) for detailed model comparisons, capabilities, and provider information.\n\n| Task Type | Recommended Model | Rationale |\n|-----------|------------------|-----------|\n| **Primary/General** | MiniMax M2.1 Free | Best free model capability |\n| **Fallback 1** | Trinity Large Free | Different provider (OpenRouter) for rate limit resilience |\n| **Fallback 2** | Kimi K2.5 Free | General purpose, balance |\n| **Heartbeat** | GLM 4.7 Free | Multilingual, cost-effective for frequent checks |\n| **Subtasks/Subagents** | Kimi K2.5 Free | Balanced capability for secondary tasks |\n\n### Free Models Available\n\n"},{"path":"README.md","content":"# Freeride OpenCode Skill\n\n> ⚠️ **Para funcionar, são necessárias duas API keys:**\n> - **OpenCode Zen API key** - Para modelos OpenCode (MiniMax M2.1, Kimi K2.5, GLM 4.7, GPT 5 Nano)\n> - **OpenRouter API key** - Para modelos OpenRouter (Trinity Large e outros)\n\n## Descrição\n\nConfigure modelos free do OpenCode Zen com fallbacks inteligentes para otimizar custos mantendo confiabilidade.\n\n## Quick Start\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      }\n    }\n  }\n}\n```\n\n## Documentação Completa\n\nVeja [SKILL.md](SKILL.md) para documentação detalhada.\n\n## Modelos Disponíveis\n\n| Modelo | Provider | ID | Posição |\n|--------|----------|-----|---------|\n| MiniMax M2.1 | OpenCode | `opencode/minimax-m2.1-free` | Primary |\n| Trinity Large | OpenRouter | `openrouter/arcee-ai/trinity-large-preview:free` | Fallback 1 |\n| Kimi K2.5 | OpenCode | `opencode/kimi-k2.5-free` | Fallback 2 |\n\n## Versão\n\n1.2.0"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn74nrx32v4n0423jptzg1v5kx80ssnf\",\n  \"slug\": \"freeride-opencode\",\n  \"version\": \"1.2.0\",\n  \"publishedAt\": 1770728122855\n}"},{"path":"references/models.md","content":"# OpenCode Zen Free Models Reference\n\n> **⚠️ API Keys Required:**\n> - **OpenCode models:** Requires OpenCode Zen API key\n> - **OpenRouter models:** Requires OpenRouter API key\n>\n> Configure both keys in your OpenCode settings for full fallback coverage.\n\n## Complete Model List\n\n### MiniMax M2.1 Free (Primary)\n- **ID:** `opencode/minimax-m2.1-free`\n- **Provider:** MiniMax (via OpenCode)\n- **Best for:** Complex coding tasks, reasoning, multi-step workflows\n- **Context:** Large context window\n- **Strengths:** Strong coding capability, good reasoning\n\n### Trinity Large Free (Fallback 1 - Different Provider)\n- **ID:** `openrouter/arcee-ai/trinity-large-preview:free`\n- **Provider:** Arcee AI (via OpenRouter)\n- **Best for:** Complex reasoning, coding, multi-step workflows\n- **Context:** Large context window\n- **Strengths:** High-quality model, **different provider** for rate limit resilience\n- **Why Fallback 1:** Being on OpenRouter, this model remains available when OpenCode models are rate-limited\n\n### Kimi K2.5 Free (Fallback 2)\n- **ID:** `opencode/kimi-k2.5-free`\n- **Provider:** Moonshot AI (Kimi) (via OpenCode)\n- **Best for:** General purpose, balanced performance\n- **Context:** Large context window\n- **Strengths:** Good all-around model, reliable responses\n\n### GLM 4.7 Free\n- **ID:** `opencode/glm-4.7-free`\n- **Provider:** Zhipu AI (GLM)\n- **Best for:** Multilingual tasks, alternative provider fallback\n- **Context:** Medium-large context\n- **Strengths:** Multilingual support, different provider ecosystem\n\n### GPT 5 Nano\n- **ID:** `opencode/gpt-5-nano`\n- **Provider:** OpenAI\n- **Best for:** Simple tasks, high-frequency operations, quick checks\n- **Context:** Smaller context window\n- **Strengths:** Fastest responses, lowest cost\n\n## Provider Information\n\n### OpenCode (MiniMax, Moonshot AI/Kimi)\n- Primary provider for free models\n- Requires OpenCode Zen API key\n- Models: MiniMax M2.1, Kimi K2.5\n\n### OpenRouter (Arcee AI/Trinity Large)\n- **Different provider** from OpenCode\n- Aggregation platform with multiple model providers\n- Trinity Large: Arcee AI's large language model\n- Focus: High-quality reasoning and coding\n- **Requires OpenRouter API key** (separate from OpenCode Zen)\n- **Key benefit:** Rate limits on OpenCode do NOT affect OpenRouter models\n\n## Rate Limits by Model\n\n| Model | Typical Rate Limits | Notes |\n|-------|--------------------|-------|\n| MiniMax M2.1 Free | Medium | Most popular free model |\n| Trinity Large Free | Medium | **Different provider** - available when OpenCode is rate-limited |\n| Kimi K2.5 Free | Medium-High | Good availability within OpenCode |\n\n## Performance Comparison\n\n| Model | Speed | Capability | Provider Diversification |\n|-------|-------|------------|-------------------------|\n| MiniMax M2.1 Free | Medium | Highest | Primary (OpenCode) |\n| Trinity Large Free | Medium | High | Fallback 1 (OpenRouter) ✅ |\n| Kimi K2.5 Free | Medium-High | High | Fallback 2 (OpenCode) |\n\n## Configuration Tips\n\n### For High-Volume Tas"},{"path":"references/templates.md","content":"# Configuration Templates\n\n## Minimal Template (Just Fallbacks)\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      }\n    }\n  }\n}\n```\n\n## Complete Template (All Optimizations)\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      },\n      \"models\": {\n        \"opencode/minimax-m2.1-free\": { \"alias\": \"MiniMax M2.1\" },\n        \"openrouter/arcee-ai/trinity-large-preview:free\": { \"alias\": \"Trinity Large\" },\n        \"opencode/kimi-k2.5-free\": { \"alias\": \"Kimi K2.5\" },\n        \"opencode/glm-4.7-free\": { \"alias\": \"GLM 4.7\" }\n      },\n      \"heartbeat\": {\n        \"every\": \"30m\",\n        \"model\": \"opencode/glm-4.7-free\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Cost-Optimized Template (Cheapest First)\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/glm-4.7-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\",\n          \"opencode/kimi-k2.5-free\"\n        ]\n      },\n      \"heartbeat\": {\n        \"model\": \"opencode/glm-4.7-free\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Performance-Optimized Template (Best First)\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\n          \"openrouter/arcee-ai/trinity-large-preview:free\"\n        ]\n      },\n      \"heartbeat\": {\n        \"model\": \"opencode/glm-4.7-free\"\n      },\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Subagent-Only Template\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"subagents\": {\n        \"model\": \"opencode/kimi-k2.5-free\"\n      }\n    }\n  }\n}\n```\n\n## Cron-Specific Template\n\n```json\n{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/glm-4.7-free\",\n        \"fallbacks\": [\n          \"opencode/kimi-k2.5-free\"\n        ]\n      }\n    }\n  }\n}\n```\n\n## Applying Templates\n\n> **⚠️ Prerequisites:** Ensure you have both API keys configured before applying templates:\n> - OpenCode Zen API key (for `opencode/*` models)\n> - OpenRouter API key (for `openrouter/*` models - Trinity Large)\n>\n> Without both keys, fallbacks will fail when switching providers.\n\n### Via CLI\n\n```bash\nopenclaw config.patch --raw '{\n  \"agents\": {\n    \"defaults\": {\n      \"model\": {\n        \"primary\": \"opencode/minimax-m2.1-free\",\n        \"fallbacks\": [\"openrouter/arcee-ai/trinity-large-preview:free\", \"opencode/kimi-k2.5-free\"]\n      }\n    }\n  }\n}'\n```\n\n### Via Gateway API\n\n```bash\nopenclaw gateway call config.patch --params '{\n  \""}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1310,"uniquenessScore":39,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-09T18:05:24.605Z","emptyReason":null},"items":[{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-10T18:48:31.762Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}