{"id":"72066720-1d13-4e38-a3f2-bb38810f58ef","entityType":"agent","slug":"clawhub-clarezoe-rtk-token-saver","name":"Rtk Token Saver","canonicalUrl":"https://www.xpersona.co/agent/clawhub-clarezoe-rtk-token-saver","canonicalPath":"/agent/clawhub-clarezoe-rtk-token-saver","generatedAt":"2026-10-11T10:50:22.212Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T06:56:25.992Z","emptyReason":null},"description":"Use rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact o... Skill: Rtk Token Saver Owner: clarezoe Summary: Use rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact o... Tags: cli:1.0.2, developer-tools:1.0.2, latest:1.0.2, shell-output:1.0.2, token-savings:1.0.2 Version history: v1.0.2 | 2026-06-09T13:22:01.729Z | user Add OpenCode, Kiro, Devin, Codex, Cursor, and Windsurf skil","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s178sk484g47vwcbvvfcjpftfx8461fz:rtk-token-saver","sourceUrl":"https://clawhub.ai/clarezoe/rtk-token-saver","homepage":"https://clawhub.ai/clarezoe/skills/rtk-token-saver","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/clarezoe/rtk-token-saver","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/clarezoe/skills/rtk-token-saver","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Use rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact o..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T06:56:25.992Z","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":"2026-10-11T06:56:25.992Z","emptyReason":null},"stars":null,"forks":null,"downloads":1129,"packageName":null,"latestVersion":"1.0.2","tractionLabel":"1.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T06:56:25.933Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T06:56:25.992Z","lastCrawledAt":"2026-10-11T06:56:25.933Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T06:56:25.933Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.2","createdAt":"2026-06-09T13:22:01.729Z","changelog":"Add OpenCode, Kiro, Devin, Codex, Cursor, and Windsurf skill compatibility","fileCount":3,"zipByteSize":3570},{"version":"1.0.1","createdAt":"2026-06-09T13:10:20.779Z","changelog":"Normalize SKILL.md frontmatter for OpenClaw, Hermes, and Claude compatibility","fileCount":3,"zipByteSize":3589}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s178sk484g47vwcbvvfcjpftfx8461fz:rtk-token-saver","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"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-clarezoe-rtk-token-saver/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-rtk-token-saver/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-rtk-token-saver/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-rtk-token-saver/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-rtk-token-saver/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-rtk-token-saver/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T10:50:22.212Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-rtk-token-saver/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-rtk-token-saver/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-rtk-token-saver/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-clarezoe-rtk-token-saver/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":"high","updatedAt":"2026-10-11T06:56:25.992Z","emptyReason":null},"readme":"Skill: Rtk Token Saver\n\nOwner: clarezoe\n\nSummary: Use rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact o...\n\nTags: cli:1.0.2, developer-tools:1.0.2, latest:1.0.2, shell-output:1.0.2, token-savings:1.0.2\n\nVersion history:\n\nv1.0.2 | 2026-06-09T13:22:01.729Z | user\n\nAdd OpenCode, Kiro, Devin, Codex, Cursor, and Windsurf skill compatibility\n\nv1.0.1 | 2026-06-09T13:10:20.779Z | user\n\nNormalize SKILL.md frontmatter for OpenClaw, Hermes, and Claude compatibility\n\nArchive index:\n\nArchive v1.0.2: 3 files, 3570 bytes\n\nFiles: skill-card.md (1929b), SKILL.md (4787b), _meta.json (134b)\n\nFile v1.0.2:SKILL.md\n\n---\nname: \"rtk-token-saver\"\ndescription: \"Use rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact output is required.\"\nlicense: \"MIT\"\nmetadata: {\"version\":\"1.0.2\",\"category\":\"developer-tools\",\"triggers\":[\"rtk\",\"reduce tokens\",\"large command output\",\"compact shell output\",\"token savings\"],\"license\":\"MIT\",\"tags\":[\"developer-tools\",\"token-savings\",\"shell-output\",\"cli\"],\"hermes\":{\"tags\":[\"developer-tools\",\"token-savings\",\"shell-output\",\"cli\"]}}\n---\n\n# RTK Token Saver\n\nUse this skill when a task involves shell commands that may produce large output, especially repository inspection, git history, diffs, search, file reading, tests, linting, builds, logs, containers, or package manager output.\n\nRTK is a CLI proxy that filters and compresses command output before it enters the agent context. Prefer RTK when compact output is enough to make the next decision. Use raw commands when exact bytes, full JSON, full logs, cryptographic material, or complete unmodified output is required.\n\n## Activation Rules\n\nUse RTK by default for:\n- Directory listings and tree-like exploration.\n- Git status, diffs, logs, pull, push, and GitHub CLI summaries.\n- Search commands across large repositories.\n- Reading large files when a concise view is sufficient.\n- Test, lint, typecheck, and build commands where failures are the main signal.\n- Docker, Kubernetes, AWS, package manager, and log output that may be noisy.\n\nDo not use RTK when:\n- The user explicitly asks for raw or complete output.\n- The next step requires exact formatting, exact bytes, or complete structured data.\n- A command output will be parsed programmatically by another command.\n- Security-sensitive values may be exposed; avoid reading secrets at all.\n- RTK is not installed or the relevant RTK wrapper fails. Fall back to the native command and keep output scoped.\n\n## Install and Verify\n\nBefore relying on RTK, check whether it is available:\n\n```bash\nwhich rtk\nrtk --version\nrtk gain\n```\n\nIf RTK is missing, do not install it silently. Report that RTK is unavailable and run the native command with the narrowest safe scope.\n\n## Command Mapping\n\n### Repository and File Exploration\n\nPrefer:\n\n```bash\nrtk ls .\nrtk find \"*.ts\" .\nrtk read path/to/file.ts\nrtk read path/to/file.ts -l aggressive\nrtk smart path/to/file.ts\n```\n\nInstead of broad raw commands such as:\n\n```bash\nls -laR .\nfind . -type f\ncat path/to/large-file.ts\n```\n\n### Search\n\nPrefer:\n\n```bash\nrtk grep \"pattern\" .\nrtk grep \"functionName\" src\n```\n\nUse native grep, ripgrep, or repository search tools when exact match behavior, line ranges, or complete output is required.\n\n### Git\n\nPrefer:\n\n```bash\nrtk git status\nrtk git diff\nrtk git diff --stat\nrtk git log -n 10\nrtk gh pr list\nrtk gh pr view 42\n```\n\nUse raw git commands when applying patches, generating exact diffs for review, or feeding output into another tool.\n\n### Tests, Lint, Typecheck, and Build\n\nPrefer RTK wrappers for high-noise checks:\n\n```bash\nrtk test npm test\nrtk jest\nrtk vitest\nrtk pytest\nrtk cargo test\nrtk go test\nrtk lint\nrtk tsc\nrtk next build\nrtk cargo clippy\nrtk ruff check\n```\n\nIf a compact failure summary is not enough to fix the issue, rerun the smallest failing command natively with flags that show the exact failure.\n\n### Logs and Services\n\nPrefer:\n\n```bash\nrtk docker ps\nrtk docker logs <container>\nrtk docker compose ps\nrtk kubectl pods\nrtk kubectl logs <pod>\nrtk aws logs get-log-events\nrtk log path/to/app.log\n```\n\nUse raw output only when full logs are required for auditing, exact reproduction, or external attachment.\n\n## Workflow\n\n1. Check whether RTK is installed when the task would benefit from compact command output.\n2. Use the RTK command that corresponds to the native command.\n3. Inspect the compact output and decide the next smallest action.\n4. If RTK hides information needed for correctness, rerun the native command with the narrowest scope that exposes the missing detail.\n5. Record validation commands exactly, including whether RTK or native output was used.\n\n## Guardrails\n\n- Never use RTK as an excuse to skip validation.\n- Never claim a test, lint, typecheck, or build passed unless the command exit status succeeded.\n- Do not use RTK for commands whose output must be consumed exactly by a script or parser.\n- Do not run broad commands just because RTK compresses output; keep command scope targeted.\n- Respect project-specific tool preferences. If a project provides a preferred test or lint command, wrap that command with RTK only when compact output is appropriate.\n\n## Completion Output\n\nWhen RTK was used for important work, summarize:\n- The RTK commands run.\n- Whether any native command was rerun for exact output.\n- Final validation status.\n\nFile v1.0.2:_meta.json\n\n{\n  \"ownerId\": \"kn71ntcwxg33gv53ryabqt0vw981g9my\",\n  \"slug\": \"rtk-token-saver\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1781011321729\n}\n\nFile v1.0.2:skill-card.md\n\n## Description:\n\nUse rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact output is required.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[clarezoe](https://clawhub.ai/user/clarezoe)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill to choose compact RTK-wrapped shell commands for repository inspection, search, git operations, tests, builds, linting, logs, and related CLI workflows. It also guides when to fall back to native commands for exact output or sensitive operations.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The local rtk CLI may be untrusted or unsuitable for commands involving credentials or high-impact systems.\n\nMitigation: Verify the local rtk CLI before relying on it, and use native commands when handling secrets or when exact output is required.\n\nRisk: Compact command output may omit details needed for a correct decision.\n\nMitigation: Rerun the smallest relevant native command when RTK output is insufficient for validation or debugging.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/clarezoe/skills/rtk-token-saver)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Shell commands]\n\n**Output Format:** [Markdown with inline bash code blocks]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May recommend native-command fallbacks when exact output, complete structured data, or secret handling is required.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release evidence and skill metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.0.1: 3 files, 3589 bytes\n\nFiles: skill-card.md (2087b), SKILL.md (4787b), _meta.json (134b)\n\nFile v1.0.1:SKILL.md\n\n---\nname: \"rtk-token-saver\"\ndescription: \"Use rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact output is required.\"\nlicense: \"MIT\"\nmetadata: {\"version\":\"1.0.1\",\"category\":\"developer-tools\",\"triggers\":[\"rtk\",\"reduce tokens\",\"large command output\",\"compact shell output\",\"token savings\"],\"license\":\"MIT\",\"tags\":[\"developer-tools\",\"token-savings\",\"shell-output\",\"cli\"],\"hermes\":{\"tags\":[\"developer-tools\",\"token-savings\",\"shell-output\",\"cli\"]}}\n---\n\n# RTK Token Saver\n\nUse this skill when a task involves shell commands that may produce large output, especially repository inspection, git history, diffs, search, file reading, tests, linting, builds, logs, containers, or package manager output.\n\nRTK is a CLI proxy that filters and compresses command output before it enters the agent context. Prefer RTK when compact output is enough to make the next decision. Use raw commands when exact bytes, full JSON, full logs, cryptographic material, or complete unmodified output is required.\n\n## Activation Rules\n\nUse RTK by default for:\n- Directory listings and tree-like exploration.\n- Git status, diffs, logs, pull, push, and GitHub CLI summaries.\n- Search commands across large repositories.\n- Reading large files when a concise view is sufficient.\n- Test, lint, typecheck, and build commands where failures are the main signal.\n- Docker, Kubernetes, AWS, package manager, and log output that may be noisy.\n\nDo not use RTK when:\n- The user explicitly asks for raw or complete output.\n- The next step requires exact formatting, exact bytes, or complete structured data.\n- A command output will be parsed programmatically by another command.\n- Security-sensitive values may be exposed; avoid reading secrets at all.\n- RTK is not installed or the relevant RTK wrapper fails. Fall back to the native command and keep output scoped.\n\n## Install and Verify\n\nBefore relying on RTK, check whether it is available:\n\n```bash\nwhich rtk\nrtk --version\nrtk gain\n```\n\nIf RTK is missing, do not install it silently. Report that RTK is unavailable and run the native command with the narrowest safe scope.\n\n## Command Mapping\n\n### Repository and File Exploration\n\nPrefer:\n\n```bash\nrtk ls .\nrtk find \"*.ts\" .\nrtk read path/to/file.ts\nrtk read path/to/file.ts -l aggressive\nrtk smart path/to/file.ts\n```\n\nInstead of broad raw commands such as:\n\n```bash\nls -laR .\nfind . -type f\ncat path/to/large-file.ts\n```\n\n### Search\n\nPrefer:\n\n```bash\nrtk grep \"pattern\" .\nrtk grep \"functionName\" src\n```\n\nUse native grep, ripgrep, or repository search tools when exact match behavior, line ranges, or complete output is required.\n\n### Git\n\nPrefer:\n\n```bash\nrtk git status\nrtk git diff\nrtk git diff --stat\nrtk git log -n 10\nrtk gh pr list\nrtk gh pr view 42\n```\n\nUse raw git commands when applying patches, generating exact diffs for review, or feeding output into another tool.\n\n### Tests, Lint, Typecheck, and Build\n\nPrefer RTK wrappers for high-noise checks:\n\n```bash\nrtk test npm test\nrtk jest\nrtk vitest\nrtk pytest\nrtk cargo test\nrtk go test\nrtk lint\nrtk tsc\nrtk next build\nrtk cargo clippy\nrtk ruff check\n```\n\nIf a compact failure summary is not enough to fix the issue, rerun the smallest failing command natively with flags that show the exact failure.\n\n### Logs and Services\n\nPrefer:\n\n```bash\nrtk docker ps\nrtk docker logs <container>\nrtk docker compose ps\nrtk kubectl pods\nrtk kubectl logs <pod>\nrtk aws logs get-log-events\nrtk log path/to/app.log\n```\n\nUse raw output only when full logs are required for auditing, exact reproduction, or external attachment.\n\n## Workflow\n\n1. Check whether RTK is installed when the task would benefit from compact command output.\n2. Use the RTK command that corresponds to the native command.\n3. Inspect the compact output and decide the next smallest action.\n4. If RTK hides information needed for correctness, rerun the native command with the narrowest scope that exposes the missing detail.\n5. Record validation commands exactly, including whether RTK or native output was used.\n\n## Guardrails\n\n- Never use RTK as an excuse to skip validation.\n- Never claim a test, lint, typecheck, or build passed unless the command exit status succeeded.\n- Do not use RTK for commands whose output must be consumed exactly by a script or parser.\n- Do not run broad commands just because RTK compresses output; keep command scope targeted.\n- Respect project-specific tool preferences. If a project provides a preferred test or lint command, wrap that command with RTK only when compact output is appropriate.\n\n## Completion Output\n\nWhen RTK was used for important work, summarize:\n- The RTK commands run.\n- Whether any native command was rerun for exact output.\n- Final validation status.\n\nFile v1.0.1:_meta.json\n\n{\n  \"ownerId\": \"kn71ntcwxg33gv53ryabqt0vw981g9my\",\n  \"slug\": \"rtk-token-saver\",\n  \"version\": \"1.0.1\",\n  \"publishedAt\": 1781010620779\n}\n\nFile v1.0.1:skill-card.md\n\n## Description: <br>\nUse rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact output is required. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[clarezoe](https://clawhub.ai/user/clarezoe) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nDevelopers and engineers use this skill to guide agents toward compact RTK command wrappers for noisy repository, git, search, test, build, lint, log, and service-output workflows while retaining raw-command fallbacks when exact output is needed. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Summarized command output can hide details needed for audits, exact log review, structured parsing, or security-sensitive inspection. <br>\nMitigation: Use raw commands when complete output, exact bytes, full JSON, full logs, or security-sensitive review is required. <br>\nRisk: An agent may overuse compact wrappers and miss information needed to validate tests, builds, or repository state. <br>\nMitigation: Keep command scope targeted, check exit status, and rerun the smallest relevant native command when the compact output is insufficient. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/clarezoe/rtk-token-saver) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, shell commands, configuration] <br>\n**Output Format:** [Markdown with inline bash code blocks] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Guides command selection and asks for native command fallbacks when exact output is required.] <br>\n\n## Skill Version(s): <br>\n1.0.1 (source: server release evidence and skill metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>","readmeExcerpt":"Skill: Rtk Token Saver Owner: clarezoe Summary: Use rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact o... Tags: cli:1.0.2, developer-tools:1.0.2, latest:1.0.2, shell-output:1.0.2, token-savings:1.0.2 Version history: v1.0.2 | 2026-06-09T13:22:01.729Z | user Add OpenCode, Kiro, Devin, Codex, Cursor, and Windsurf skil","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"which rtk\nrtk --version\nrtk gain"},{"language":"bash","snippet":"rtk ls .\nrtk find \"*.ts\" .\nrtk read path/to/file.ts\nrtk read path/to/file.ts -l aggressive\nrtk smart path/to/file.ts"},{"language":"bash","snippet":"ls -laR .\nfind . -type f\ncat path/to/large-file.ts"},{"language":"bash","snippet":"rtk grep \"pattern\" .\nrtk grep \"functionName\" src"},{"language":"bash","snippet":"rtk git status\nrtk git diff\nrtk git diff --stat\nrtk git log -n 10\nrtk gh pr list\nrtk gh pr view 42"},{"language":"bash","snippet":"rtk test npm test\nrtk jest\nrtk vitest\nrtk pytest\nrtk cargo test\nrtk go test\nrtk lint\nrtk tsc\nrtk next build\nrtk cargo clippy\nrtk ruff check"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: \"rtk-token-saver\"\ndescription: \"Use rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact output is required.\"\nlicense: \"MIT\"\nmetadata: {\"version\":\"1.0.2\",\"category\":\"developer-tools\",\"triggers\":[\"rtk\",\"reduce tokens\",\"large command output\",\"compact shell output\",\"token savings\"],\"license\":\"MIT\",\"tags\":[\"developer-tools\",\"token-savings\",\"shell-output\",\"cli\"],\"hermes\":{\"tags\":[\"developer-tools\",\"token-savings\",\"shell-output\",\"cli\"]}}\n---\n\n# RTK Token Saver\n\nUse this skill when a task involves shell commands that may produce large output, especially repository inspection, git history, diffs, search, file reading, tests, linting, builds, logs, containers, or package manager output.\n\nRTK is a CLI proxy that filters and compresses command output before it enters the agent context. Prefer RTK when compact output is enough to make the next decision. Use raw commands when exact bytes, full JSON, full logs, cryptographic material, or complete unmodified output is required.\n\n## Activation Rules\n\nUse RTK by default for:\n- Directory listings and tree-like exploration.\n- Git status, diffs, logs, pull, push, and GitHub CLI summaries.\n- Search commands across large repositories.\n- Reading large files when a concise view is sufficient.\n- Test, lint, typecheck, and build commands where failures are the main signal.\n- Docker, Kubernetes, AWS, package manager, and log output that may be noisy.\n\nDo not use RTK when:\n- The user explicitly asks for raw or complete output.\n- The next step requires exact formatting, exact bytes, or complete structured data.\n- A command output will be parsed programmatically by another command.\n- Security-sensitive values may be exposed; avoid reading secrets at all.\n- RTK is not installed or the relevant RTK wrapper fails. Fall back to the native command and keep output scoped.\n\n## Install and Verify\n\nBefore relying on RTK, check whether it is available:\n\n```bash\nwhich rtk\nrtk --version\nrtk gain\n```\n\nIf RTK is missing, do not install it silently. Report that RTK is unavailable and run the native command with the narrowest safe scope.\n\n## Command Mapping\n\n### Repository and File Exploration\n\nPrefer:\n\n```bash\nrtk ls .\nrtk find \"*.ts\" .\nrtk read path/to/file.ts\nrtk read path/to/file.ts -l aggressive\nrtk smart path/to/file.ts\n```\n\nInstead of broad raw commands such as:\n\n```bash\nls -laR .\nfind . -type f\ncat path/to/large-file.ts\n```\n\n### Search\n\nPrefer:\n\n```bash\nrtk grep \"pattern\" .\nrtk grep \"functionName\" src\n```\n\nUse native grep, ripgrep, or repository search tools when exact match behavior, line ranges, or complete output is required.\n\n### Git\n\nPrefer:\n\n```bash\nrtk git status\nrtk git diff\nrtk git diff --stat\nrtk git log -n 10\nrtk gh pr list\nrtk gh pr view 42\n```\n\nUse raw git commands when applying patches, generating exact diffs for review, or feeding output into another tool.\n\n### Tests, Lint, Typecheck, and Build\n\nPrefer RTK wrapp"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn71ntcwxg33gv53ryabqt0vw981g9my\",\n  \"slug\": \"rtk-token-saver\",\n  \"version\": \"1.0.2\",\n  \"publishedAt\": 1781011321729\n}"},{"path":"skill-card.md","content":"## Description:\n\nUse rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact output is required.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[clarezoe](https://clawhub.ai/user/clarezoe)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and engineers use this skill to choose compact RTK-wrapped shell commands for repository inspection, search, git operations, tests, builds, linting, logs, and related CLI workflows. It also guides when to fall back to native commands for exact output or sensitive operations.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The local rtk CLI may be untrusted or unsuitable for commands involving credentials or high-impact systems.\n\nMitigation: Verify the local rtk CLI before relying on it, and use native commands when handling secrets or when exact output is required.\n\nRisk: Compact command output may omit details needed for a correct decision.\n\nMitigation: Rerun the smallest relevant native command when RTK output is insufficient for validation or debugging.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/clarezoe/skills/rtk-token-saver)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Shell commands]\n\n**Output Format:** [Markdown with inline bash code blocks]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May recommend native-command fallbacks when exact output, complete structured data, or secret handling is required.]\n\n## Skill Version(s):\n\n1.0.2 (source: server release evidence and skill metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Use rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact o... Skill: Rtk Token Saver Owner: clarezoe Summary: Use rtk to reduce token usage from common shell, git, search, file-reading, test, build, and lint commands while preserving raw-output fallbacks when exact o... Tags: cli:1.0.2, developer-tools:1.0.2, latest:1.0.2, shell-output:1.0.2, token-savings:1.0.2 Version history: v1.0.2 | 2026-06-09T13:22:01.729Z | user Add OpenCode, Kiro, Devin, Codex, Cursor, and Windsurf skil","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1058,"uniquenessScore":48,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T06:56:25.992Z","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":"2026-10-11T06:56:25.992Z","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":"2026-10-11T10:50:22.212Z","emptyReason":null},"items":[{"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":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"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":"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"}]}}}