{"id":"5e8251e8-c4f3-4c1a-8d58-7eb75a6ff719","entityType":"agent","slug":"clawhub-netanel-abergel-monday-for-agents","name":"Monday For Agents","canonicalUrl":"https://www.xpersona.co/agent/clawhub-netanel-abergel-monday-for-agents","canonicalPath":"/agent/clawhub-netanel-abergel-monday-for-agents","generatedAt":"2026-10-10T01:02:36.416Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T00:06:29.240Z","emptyReason":null},"description":"Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a... Skill: Monday For Agents Owner: netanel-abergel Summary: Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a... Tags: latest:1.1.1 Version history: v1.1.1 | 2026-04-02T16:25:24.438Z | user monday-for-agents 1.1.1 - Renamed documentation file from SKILL.md to skill.md for consistency. - No changes to implementatio","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.9K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s17ber573ejk857tr938jb5dqs8413hk:monday-for-agents","sourceUrl":"https://clawhub.ai/netanel-abergel/monday-for-agents","homepage":"https://clawhub.ai/netanel-abergel/skills/monday-for-agents","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/netanel-abergel/monday-for-agents","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/netanel-abergel/skills/monday-for-agents","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":40,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T00:06:29.240Z","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":"2026-10-10T00:06:29.240Z","emptyReason":null},"stars":null,"forks":null,"downloads":1854,"packageName":null,"latestVersion":"1.1.1","tractionLabel":"1.9K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T00:06:29.239Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T00:06:29.240Z","lastCrawledAt":"2026-10-10T00:06:29.239Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T00:06:29.239Z","lastVerifiedAt":null,"highlights":[{"version":"1.1.1","createdAt":"2026-04-02T16:25:24.438Z","changelog":"## monday-for-agents 1.1.1 - Renamed documentation file from `SKILL.md` to `skill.md` for consistency. - No changes to implementation or functionality.","fileCount":3,"zipByteSize":5375},{"version":"1.1.0","createdAt":"2026-04-02T16:23:05.087Z","changelog":"fix: remove plaintext token storage, align metadata with actual requirements","fileCount":2,"zipByteSize":4180},{"version":"1.0.0","createdAt":"2026-04-01T13:06:06.248Z","changelog":"monday-for-agents 1.0.0 initial release - Enables setup and management of monday.com accounts for OpenClaw agent PAs, including account creation and secure API token handling. - Provides ready-to-use bash functions for interacting with monday.com boards, items, and columns via the GraphQL API. - Documents robust troubleshooting, setup checklists, operation rules, and best practices for API and MCP server use. - Supports both direct GraphQL operations and natural language workflows through MCP, with guidance for local or hosted deployment. - Includes cost and rate-limit tips, as well as strict operational rules to ensure secure and reliable integration.","fileCount":2,"zipByteSize":3926}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17ber573ejk857tr938jb5dqs8413hk:monday-for-agents","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-netanel-abergel-monday-for-agents/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-netanel-abergel-monday-for-agents/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-netanel-abergel-monday-for-agents/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-netanel-abergel-monday-for-agents/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-netanel-abergel-monday-for-agents/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-netanel-abergel-monday-for-agents/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T01:02:36.415Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-netanel-abergel-monday-for-agents/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-netanel-abergel-monday-for-agents/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-netanel-abergel-monday-for-agents/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-netanel-abergel-monday-for-agents/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":"2026-10-10T00:06:29.240Z","emptyReason":null},"readme":"Skill: Monday For Agents\n\nOwner: netanel-abergel\n\nSummary: Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a...\n\nTags: latest:1.1.1\n\nVersion history:\n\nv1.1.1 | 2026-04-02T16:25:24.438Z | user\n\n## monday-for-agents 1.1.1\n\n- Renamed documentation file from `SKILL.md` to `skill.md` for consistency.\n- No changes to implementation or functionality.\n\nv1.1.0 | 2026-04-02T16:23:05.087Z | user\n\nfix: remove plaintext token storage, align metadata with actual requirements\n\nv1.0.0 | 2026-04-01T13:06:06.248Z | auto\n\nmonday-for-agents 1.0.0 initial release\n\n- Enables setup and management of monday.com accounts for OpenClaw agent PAs, including account creation and secure API token handling.\n- Provides ready-to-use bash functions for interacting with monday.com boards, items, and columns via the GraphQL API.\n- Documents robust troubleshooting, setup checklists, operation rules, and best practices for API and MCP server use.\n- Supports both direct GraphQL operations and natural language workflows through MCP, with guidance for local or hosted deployment.\n- Includes cost and rate-limit tips, as well as strict operational rules to ensure secure and reliable integration.\n\nArchive index:\n\nArchive v1.1.1: 3 files, 5375 bytes\n\nFiles: skill-card.md (2168b), skill.md (9092b), _meta.json (136b)\n\nFile v1.1.1:skill.md\n\n---\nname: monday-for-agents\ndescription: \"Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a monday.com workspace for a PA, connecting the PA to monday.com, querying boards and items, creating or updating items, or troubleshooting monday.com API access. Covers GraphQL cookbook, column types, and MCP configuration. Works with any LLM model.\"\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"📋\",\n        \"requires\":\n          {\n            \"env\": [\"MONDAY_API_TOKEN\"],\n          },\n      },\n  }\n---\n\n# monday.com for Agents\n\nOne skill for everything monday.com: account setup, daily operations, GraphQL API, MCP server, and troubleshooting.\n\n## Minimum Model\nAny model for routine operations. Use a medium model for debugging GraphQL errors.\n\n---\n\n## Section 1 — Setup\n\n### Option A: Manual Account Creation\n\nEach PA needs its own account — do not use the owner's.\n\n1. Go to [monday.com/agents-signup](https://monday.com/agents-signup).\n2. Use the agent email (e.g. `agent@agentdomain.com`).\n3. Owner invites the PA via Admin → Users → Invite.\n\n### Get an API Token\n\n1. Log into monday.com as the agent.\n2. Click avatar → **Developers** → **My Access Tokens** → **Copy**.\n3. Set the token as an environment variable via OpenClaw's config (preferred) or your system's secret manager.\n   ❌ Do **not** write the token to a plaintext file or add it to shell startup files.\n   ❌ Do **not** commit tokens to version control.\n\n**Recommended: OpenClaw env config**\nAdd `MONDAY_API_TOKEN` to your OpenClaw agent environment via the Ocana dashboard or `openclaw.json` `env` block — never hardcode it in scripts.\n\n**For local dev only (not production):**\n```bash\nexport MONDAY_API_TOKEN=\"TOKEN_HERE\"  # current shell only, not persisted\n```\n\n### Setup Checklist\n\n```\n[ ] PA has a monday.com account (agent email, not owner's)\n[ ] MONDAY_API_TOKEN set in OpenClaw agent environment (not a plaintext file)\n[ ] Workspace access confirmed\n[ ] Verified with: monday_query '{\"query\": \"{ me { id name } }\"}'\n[ ] If using MCP: server added to config and tested\n```\n\n---\n\n## Section 2 — Operations\n\n### API Basics\n\nMonday.com uses a single **GraphQL endpoint**:\n\n```\nhttps://api.monday.com/v2    (preferred)\nhttps://api.monday.com/graphql  (also works)\n```\n\n#### Reusable Helper\n\n```bash\nMONDAY_API_URL=\"https://api.monday.com/v2\"\n\n# MONDAY_API_TOKEN must be set in the agent's environment (not read from file)\nif [ -z \"$MONDAY_API_TOKEN\" ]; then\n  echo \"ERROR: MONDAY_API_TOKEN is not set. Configure it in your OpenClaw agent environment.\" >&2\n  exit 1\nfi\n\nmonday_query() {\n  RESPONSE=$(curl -s -X POST \"$MONDAY_API_URL\" \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: $MONDAY_API_TOKEN\" \\\n    -H \"API-Version: 2024-10\" \\\n    -d \"$1\")\n\n  if echo \"$RESPONSE\" | python3 -c \"\nimport sys, json\nd = json.load(sys.stdin)\nif d.get('errors'):\n    print('API ERROR:', d['errors'])\n    sys.exit(1)\n\" 2>/dev/null; then\n    echo \"$RESPONSE\"\n  else\n    echo \"API ERROR: $RESPONSE\" >&2\n    return 1\n  fi\n}\n```\n\n### Common Operations\n\n```bash\n# List boards\nmonday_query '{\"query\": \"{ boards(limit: 25) { id name description state } }\"}'\n\n# Get items from a board\nmonday_query '{\"query\": \"{ boards(ids: [BOARD_ID]) { items_page(limit: 50) { cursor items { id name group { id title } column_values { id title text type } } } } }\"}'\n\n# Create an item\nmonday_query '{\n  \"query\": \"mutation ($board: ID!, $name: String!) { create_item(board_id: $board, item_name: $name) { id } }\",\n  \"variables\": {\"board\": \"BOARD_ID\", \"name\": \"New Task\"}\n}'\n\n# Update a status column\nmonday_query '{\n  \"query\": \"mutation ($board: ID!, $item: ID!, $col: String!, $val: JSON!) { change_column_value(board_id: $board, item_id: $item, column_id: $col, value: $val) { id } }\",\n  \"variables\": {\n    \"board\": \"BOARD_ID\",\n    \"item\": \"ITEM_ID\",\n    \"col\": \"status\",\n    \"val\": \"{\\\"label\\\": \\\"Done\\\"}\"\n  }\n}'\n\n# Add a comment to an item\nmonday_query '{\n  \"query\": \"mutation ($item: ID!, $body: String!) { create_update(item_id: $item, body: $body) { id } }\",\n  \"variables\": {\"item\": \"ITEM_ID\", \"body\": \"Update text here\"}\n}'\n\n# List columns in a board\nmonday_query '{\"query\": \"{ boards(ids: [BOARD_ID]) { columns { id title type } } }\"}'\n\n# Query subitems\nmonday_query '{\"query\": \"{ items(ids: [ITEM_ID]) { subitems { id name column_values { id text } } } }\"}'\n\n# Get current user\nmonday_query '{\"query\": \"{ me { id name email account { id name } } }\"}'\n```\n\n### Pagination for Large Boards\n\n```bash\n# First page — also returns a cursor\nmonday_query '{\"query\": \"{ boards(ids: [BOARD_ID]) { items_page(limit: 100) { cursor items { id name } } } }\"}'\n\n# Next page — pass the cursor value from the previous response\nmonday_query '{\"query\": \"{ next_items_page(limit: 100, cursor: \\\"CURSOR_VALUE\\\") { cursor items { id name } } }\"}'\n```\n\n### Check Before Creating (Avoid Duplicates)\n\n```bash\nRESULT=$(monday_query '{\"query\": \"{ items_by_multiple_column_values(board_id: BOARD_ID, column_id: \\\"name\\\", column_values: [\\\"Item Name\\\"]) { id name } }\"}')\n\nCOUNT=$(echo \"$RESULT\" | python3 -c \"\nimport sys, json\nd = json.load(sys.stdin)\nprint(len(d.get('data', {}).get('items_by_multiple_column_values', [])))\n\")\n\nif [ \"$COUNT\" -eq 0 ]; then\n  echo \"Item not found — creating\"\nelse\n  echo \"Item already exists — skipping\"\nfi\n```\n\n### Batch Update Multiple Items\n\n```bash\nfor ITEM_ID in 123456 789012 345678; do\n  monday_query \"{\n    \\\"query\\\": \\\"mutation { change_column_value(board_id: BOARD_ID, item_id: $ITEM_ID, column_id: \\\\\\\"status\\\\\\\", value: \\\\\\\"{\\\\\\\\\\\\\\\"label\\\\\\\\\\\\\\\": \\\\\\\\\\\\\\\"In Progress\\\\\\\\\\\\\\\"}\\\\\\\") { id } }\\\"\n  }\"\n  sleep 0.2  # Respect rate limits\ndone\n```\n\n### Rate Limits\n\nMonday.com uses **complexity-based** rate limiting (not simple request counting). Response headers include `x-ratelimit-remaining-complexity`. Keep queries focused, use pagination, and add `sleep 0.2` between batch calls.\n\n---\n\n## Section 3 — MCP Server (Recommended for Daily Use)\n\nThe MCP server lets you work with boards using natural language tools — no manual GraphQL needed.\n\n### Option A: Hosted MCP\n\nAdd to `~/.openclaw/openclaw.json` under `mcpServers`:\n\n```json\n{\n  \"mcpServers\": {\n    \"monday-mcp\": {\n      \"url\": \"https://mcp.monday.com/mcp\"\n    }\n  }\n}\n```\n\nNo local install needed. Uses OAuth.\n\nTest: `mcporter call monday-mcp list_boards`\n\n### Option B: Local MCP (npx)\n\n```json\n{\n  \"mcpServers\": {\n    \"monday-api-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"@mondaydotcomorg/monday-api-mcp@latest\"],\n      \"env\": {\n        \"MONDAY_API_TOKEN\": \"your_token_here\"\n      }\n    }\n  }\n}\n```\n\nSpeed tip: `npm install -g @mondaydotcomorg/monday-api-mcp` then use `\"command\": \"monday-api-mcp\"`.\n\n---\n\n## Section 4 — Troubleshooting\n\n| Error | Cause | Fix |\n|---|---|---|\n| 401 Unauthorized | Token invalid or expired | Regenerate in Developer settings, update file |\n| 403 Forbidden | No board access | Ask owner to share the board with the PA account |\n| \"Column not found\" | Wrong column ID | Run list columns query first |\n| \"Complexity budget exhausted\" | Query too heavy | Use pagination with `limit: 50` |\n| Empty response | Network or JSON issue | `echo $RESPONSE \\| python3 -m json.tool` |\n| Rate limit (429) | Too many requests | Add `sleep 0.2` between calls in loops |\n\n---\n\n## Core Operating Rules\n\nFollow these rules every time, without exception:\n\n1. **Create → API. Operate → MCP.**\n   - New workspace / board / column: use API (curl + GraphQL)\n   - Daily read/update/create items: use MCP (mcporter)\n\n2. **Never guess IDs.**\n   - Before any mutation: run `mcporter call monday.list_workspaces` or `get_board_info` first\n   - Store all IDs in TOOLS.md immediately after creation\n\n3. **One workspace per context.**\n   - Family ≠ Work ≠ PA Network\n   - Never mix contexts in the same workspace\n\n4. **Before any mutation: verify.**\n   - Run `mcporter call monday.get_board_info boardId=X` to confirm column IDs\n   - Wrong column ID = silent failure or data corruption\n\n5. **IDs in TOOLS.md, not memory.**\n   - After creating any resource: `echo \"board-name: $ID\" >> TOOLS.md`\n   - Before using an ID: `grep \"board-name\" TOOLS.md`\n\n6. **Do NOT create or update board items without explicit instruction from owner.**\n   - Always confirm board ID before mutations\n   - Never print or log the API token\n\n---\n\n## Cost Tips\n\n- **Cheap:** MCP handles natural language → API translation. Prefer it over raw GraphQL.\n- **Expensive:** Fetching all items from large boards without pagination. Always use `limit:`.\n- **Small model OK:** Routine ops (list, create, update) work with any model.\n- **Use medium model for:** Debugging GraphQL errors or constructing complex queries.\n\n---\n\n## References\n\n- Column value JSON formats: see `references/column-types.md` in this skill directory\n- Full GraphQL cookbook: see `references/graphql-operations.md` in this skill directory\n- monday.com GraphQL API: https://developer.monday.com/api-reference\n- MCP server docs: https://mcp.monday.com\n\nFile v1.1.1:_meta.json\n\n{\n  \"ownerId\": \"kn70mvkzt5qbjzp9kdyecvn6jh840nqb\",\n  \"slug\": \"monday-for-agents\",\n  \"version\": \"1.1.1\",\n  \"publishedAt\": 1775147124438\n}\n\nFile v1.1.1:skill-card.md\n\n## Description:\n\nSet up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[netanel-abergel](https://clawhub.ai/user/netanel-abergel)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and operators use this skill to configure an OpenClaw agent for monday.com and perform board, item, update, and troubleshooting workflows through GraphQL or MCP.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: A monday.com API token may be exposed if placed directly in plaintext configuration files.\n\nMitigation: Use the platform secret or environment mechanism, avoid committing tokens, and use a least-privilege monday.com account.\n\nRisk: The local MCP setup uses an unpinned package that would receive the monday.com API token.\n\nMitigation: Prefer the hosted OAuth MCP option, or pin and review the local MCP package before use.\n\nRisk: Board IDs stored in TOOLS.md can reveal workspace-specific internal metadata.\n\nMitigation: Treat board IDs as internal data and avoid publishing or sharing TOOLS.md outside the intended workspace.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/netanel-abergel/skills/monday-for-agents)\n- [monday.com GraphQL API](https://developer.monday.com/api-reference)\n- [monday.com MCP Server Docs](https://mcp.monday.com)\n- [monday.com Agent Signup](https://monday.com/agents-signup)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with inline shell, JSON, and GraphQL examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires MONDAY_API_TOKEN for direct API usage; hosted MCP option uses OAuth.]\n\n## Skill Version(s):\n\n1.1.1 (source: server release evidence)\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 v1.1.0: 2 files, 4180 bytes\n\nFiles: SKILL.md (9093b), _meta.json (136b)\n\nFile v1.1.0:SKILL.md\n\n---\nname: monday-for-agents\ndescription: \"Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a monday.com workspace for a PA, connecting the PA to monday.com, querying boards and items, creating or updating items, or troubleshooting monday.com API access. Covers GraphQL cookbook, column types, and MCP configuration. Works with any LLM model.\"\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"📋\",\n        \"requires\":\n          {\n            \"env\": [\"MONDAY_API_TOKEN\"],\n          },\n      },\n  }\n---\n\n# monday.com for Agents\n\nOne skill for everything monday.com: account setup, daily operations, GraphQL API, MCP server, and troubleshooting.\n\n## Minimum Model\nAny model for routine operations. Use a medium model for debugging GraphQL errors.\n\n---\n\n## Section 1 — Setup\n\n### Option A: Manual Account Creation\n\nEach PA needs its own account — do not use the owner's.\n\n1. Go to [monday.com/agents-signup](https://monday.com/agents-signup).\n2. Use the agent email (e.g. `agent@agentdomain.com`).\n3. Owner invites the PA via Admin → Users → Invite.\n\n### Get an API Token\n\n1. Log into monday.com as the agent.\n2. Click avatar → **Developers** → **My Access Tokens** → **Copy**.\n3. Set the token as an environment variable via OpenClaw's config (preferred) or your system's secret manager.\n   ❌ Do **not** write the token to a plaintext file or add it to shell startup files.\n   ❌ Do **not** commit tokens to version control.\n\n**Recommended: OpenClaw env config**\nAdd `MONDAY_API_TOKEN` to your OpenClaw agent environment via the Ocana dashboard or `openclaw.json` `env` block — never hardcode it in scripts.\n\n**For local dev only (not production):**\n```bash\nexport MONDAY_API_TOKEN=\"TOKEN_HERE\"  # current shell only, not persisted\n```\n\n### Setup Checklist\n\n```\n[ ] PA has a monday.com account (agent email, not owner's)\n[ ] MONDAY_API_TOKEN set in OpenClaw agent environment (not a plaintext file)\n[ ] Workspace access confirmed\n[ ] Verified with: monday_query '{\"query\": \"{ me { id name } }\"}'\n[ ] If using MCP: server added to config and tested\n```\n\n---\n\n## Section 2 — Operations\n\n### API Basics\n\nMonday.com uses a single **GraphQL endpoint**:\n\n```\nhttps://api.monday.com/v2    (preferred)\nhttps://api.monday.com/graphql  (also works)\n```\n\n#### Reusable Helper\n\n```bash\nMONDAY_API_URL=\"https://api.monday.com/v2\"\n\n# MONDAY_API_TOKEN must be set in the agent's environment (not read from file)\nif [ -z \"$MONDAY_API_TOKEN\" ]; then\n  echo \"ERROR: MONDAY_API_TOKEN is not set. Configure it in your OpenClaw agent environment.\" >&2\n  exit 1\nfi\n\nmonday_query() {\n  RESPONSE=$(curl -s -X POST \"$MONDAY_API_URL\" \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: $MONDAY_API_TOKEN\" \\\n    -H \"API-Version: 2024-10\" \\\n    -d \"$1\")\n\n  if echo \"$RESPONSE\" | python3 -c \"\nimport sys, json\nd = json.load(sys.stdin)\nif d.get('errors'):\n    print('API ERROR:', d['errors'])\n    sys.exit(1)\n\" 2>/dev/null; then\n    echo \"$RESPONSE\"\n  else\n    echo \"API ERROR: $RESPONSE\" >&2\n    return 1\n  fi\n}\n```\n\n### Common Operations\n\n```bash\n# List boards\nmonday_query '{\"query\": \"{ boards(limit: 25) { id name description state } }\"}'\n\n# Get items from a board\nmonday_query '{\"query\": \"{ boards(ids: [BOARD_ID]) { items_page(limit: 50) { cursor items { id name group { id title } column_values { id title text type } } } } }\"}'\n\n# Create an item\nmonday_query '{\n  \"query\": \"mutation ($board: ID!, $name: String!) { create_item(board_id: $board, item_name: $name) { id } }\",\n  \"variables\": {\"board\": \"BOARD_ID\", \"name\": \"New Task\"}\n}'\n\n# Update a status column\nmonday_query '{\n  \"query\": \"mutation ($board: ID!, $item: ID!, $col: String!, $val: JSON!) { change_column_value(board_id: $board, item_id: $item, column_id: $col, value: $val) { id } }\",\n  \"variables\": {\n    \"board\": \"BOARD_ID\",\n    \"item\": \"ITEM_ID\",\n    \"col\": \"status\",\n    \"val\": \"{\\\"label\\\": \\\"Done\\\"}\"\n  }\n}'\n\n# Add a comment to an item\nmonday_query '{\n  \"query\": \"mutation ($item: ID!, $body: String!) { create_update(item_id: $item, body: $body) { id } }\",\n  \"variables\": {\"item\": \"ITEM_ID\", \"body\": \"Update text here\"}\n}'\n\n# List columns in a board\nmonday_query '{\"query\": \"{ boards(ids: [BOARD_ID]) { columns { id title type } } }\"}'\n\n# Query subitems\nmonday_query '{\"query\": \"{ items(ids: [ITEM_ID]) { subitems { id name column_values { id text } } } }\"}'\n\n# Get current user\nmonday_query '{\"query\": \"{ me { id name email account { id name } } }\"}'\n```\n\n### Pagination for Large Boards\n\n```bash\n# First page — also returns a cursor\nmonday_query '{\"query\": \"{ boards(ids: [BOARD_ID]) { items_page(limit: 100) { cursor items { id name } } } }\"}'\n\n# Next page — pass the cursor value from the previous response\nmonday_query '{\"query\": \"{ next_items_page(limit: 100, cursor: \\\"CURSOR_VALUE\\\") { cursor items { id name } } }\"}'\n```\n\n### Check Before Creating (Avoid Duplicates)\n\n```bash\nRESULT=$(monday_query '{\"query\": \"{ items_by_multiple_column_values(board_id: BOARD_ID, column_id: \\\"name\\\", column_values: [\\\"Item Name\\\"]) { id name } }\"}')\n\nCOUNT=$(echo \"$RESULT\" | python3 -c \"\nimport sys, json\nd = json.load(sys.stdin)\nprint(len(d.get('data', {}).get('items_by_multiple_column_values', [])))\n\")\n\nif [ \"$COUNT\" -eq 0 ]; then\n  echo \"Item not found — creating\"\nelse\n  echo \"Item already exists — skipping\"\nfi\n```\n\n### Batch Update Multiple Items\n\n```bash\nfor ITEM_ID in 123456 789012 345678; do\n  monday_query \"{\n    \\\"query\\\": \\\"mutation { change_column_value(board_id: BOARD_ID, item_id: $ITEM_ID, column_id: \\\\\\\"status\\\\\\\", value: \\\\\\\"{\\\\\\\\\\\\\\\"label\\\\\\\\\\\\\\\": \\\\\\\\\\\\\\\"In Progress\\\\\\\\\\\\\\\"}\\\\\\\") { id } }\\\"\n  }\"\n  sleep 0.2  # Respect rate limits\ndone\n```\n\n### Rate Limits\n\nMonday.com uses **complexity-based** rate limiting (not simple request counting). Response headers include `x-ratelimit-remaining-complexity`. Keep queries focused, use pagination, and add `sleep 0.2` between batch calls.\n\n---\n\n## Section 3 — MCP Server (Recommended for Daily Use)\n\nThe MCP server lets you work with boards using natural language tools — no manual GraphQL needed.\n\n### Option A: Hosted MCP\n\nAdd to `~/.openclaw/openclaw.json` under `mcpServers`:\n\n```json\n{\n  \"mcpServers\": {\n    \"monday-mcp\": {\n      \"url\": \"https://mcp.monday.com/mcp\"\n    }\n  }\n}\n```\n\nNo local install needed. Uses OAuth.\n\nTest: `mcporter call monday-mcp list_boards`\n\n### Option B: Local MCP (npx)\n\n```json\n{\n  \"mcpServers\": {\n    \"monday-api-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"@mondaydotcomorg/monday-api-mcp@latest\"],\n      \"env\": {\n        \"MONDAY_API_TOKEN\": \"your_token_here\"\n      }\n    }\n  }\n}\n```\n\nSpeed tip: `npm install -g @mondaydotcomorg/monday-api-mcp` then use `\"command\": \"monday-api-mcp\"`.\n\n---\n\n## Section 4 — Troubleshooting\n\n| Error | Cause | Fix |\n|---|---|---|\n| 401 Unauthorized | Token invalid or expired | Regenerate in Developer settings, update file |\n| 403 Forbidden | No board access | Ask owner to share the board with the PA account |\n| \"Column not found\" | Wrong column ID | Run list columns query first |\n| \"Complexity budget exhausted\" | Query too heavy | Use pagination with `limit: 50` |\n| Empty response | Network or JSON issue | `echo $RESPONSE \\| python3 -m json.tool` |\n| Rate limit (429) | Too many requests | Add `sleep 0.2` between calls in loops |\n\n---\n\n## Core Operating Rules\n\nFollow these rules every time, without exception:\n\n1. **Create → API. Operate → MCP.**\n   - New workspace / board / column: use API (curl + GraphQL)\n   - Daily read/update/create items: use MCP (mcporter)\n\n2. **Never guess IDs.**\n   - Before any mutation: run `mcporter call monday.list_workspaces` or `get_board_info` first\n   - Store all IDs in TOOLS.md immediately after creation\n\n3. **One workspace per context.**\n   - Family ≠ Work ≠ PA Network\n   - Never mix contexts in the same workspace\n\n4. **Before any mutation: verify.**\n   - Run `mcporter call monday.get_board_info boardId=X` to confirm column IDs\n   - Wrong column ID = silent failure or data corruption\n\n5. **IDs in TOOLS.md, not memory.**\n   - After creating any resource: `echo \"board-name: $ID\" >> TOOLS.md`\n   - Before using an ID: `grep \"board-name\" TOOLS.md`\n\n6. **Do NOT create or update board items without explicit instruction from owner.**\n   - Always confirm board ID before mutations\n   - Never print or log the API token\n\n---\n\n## Cost Tips\n\n- **Cheap:** MCP handles natural language → API translation. Prefer it over raw GraphQL.\n- **Expensive:** Fetching all items from large boards without pagination. Always use `limit:`.\n- **Small model OK:** Routine ops (list, create, update) work with any model.\n- **Use medium model for:** Debugging GraphQL errors or constructing complex queries.\n\n---\n\n## References\n\n- Column value JSON formats: see `references/column-types.md` in this skill directory\n- Full GraphQL cookbook: see `references/graphql-operations.md` in this skill directory\n- monday.com GraphQL API: https://developer.monday.com/api-reference\n- MCP server docs: https://mcp.monday.com\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn70mvkzt5qbjzp9kdyecvn6jh840nqb\",\n  \"slug\": \"monday-for-agents\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1775146985087\n}\n\nArchive v1.0.0: 2 files, 3926 bytes\n\nFiles: SKILL.md (8460b), _meta.json (136b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: monday-for-agents\ndescription: \"Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a monday.com workspace for a PA, connecting the PA to monday.com, querying boards and items, creating or updating items, or troubleshooting monday.com API access. Covers account creation, token setup, GraphQL operations, and MCP configuration. Works with any LLM model.\"\n---\n\n# monday.com Workspace Skill\n\n## Minimum Model\nAny model for routine operations. Use a medium model for debugging GraphQL errors.\n\n---\n\n## Part 1 — Account Setup\n\n### Create a monday.com Account for a PA\n\nEach PA needs its own account — do not use the owner's.\n\n1. Go to [monday.com/agents-signup](https://monday.com/agents-signup).\n2. Use the agent email (e.g. `agent@agentdomain.com`).\n3. Owner invites the PA via Admin → Users → Invite.\n\n### Get an API Token\n\n1. Log into monday.com as the agent.\n2. Click avatar → **Developers** → **My Access Tokens** → **Copy**.\n3. Save the token:\n\n```bash\n# Create secure credentials directory\nmkdir -p ~/.credentials\nchmod 700 ~/.credentials\n\n# Save token to file with restricted permissions\necho \"TOKEN_HERE\" > ~/.credentials/monday-token.txt\nchmod 600 ~/.credentials/monday-token.txt\n\n# Load token into environment\nexport MONDAY_API_TOKEN=$(cat ~/.credentials/monday-token.txt)\n\n# Make it permanent across sessions\necho 'export MONDAY_API_TOKEN=$(cat ~/.credentials/monday-token.txt)' >> ~/.bashrc\n```\n\n---\n\n## Part 2 — API Usage (GraphQL)\n\n### Setup\n\n```bash\nMONDAY_API_URL=\"https://api.monday.com/v2\"\n\n# Load token from env or file\nif [ -z \"$MONDAY_API_TOKEN\" ]; then\n  MONDAY_API_TOKEN=$(cat ~/.credentials/monday-token.txt 2>/dev/null)\nfi\n\nif [ -z \"$MONDAY_API_TOKEN\" ]; then\n  echo \"ERROR: MONDAY_API_TOKEN not set and ~/.credentials/monday-token.txt not found\"\n  exit 1\nfi\n\n# Reusable helper function for all API calls\nmonday_query() {\n  RESPONSE=$(curl -s -X POST \"$MONDAY_API_URL\" \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: $MONDAY_API_TOKEN\" \\\n    -H \"API-Version: 2024-01\" \\\n    -d \"$1\")\n\n  # Print response or error\n  if echo \"$RESPONSE\" | python3 -c \"\nimport sys, json\nd = json.load(sys.stdin)\nif d.get('errors'):\n    print('API ERROR:', d['errors'])\n    sys.exit(1)\n\" 2>/dev/null; then\n    echo \"$RESPONSE\"\n  else\n    echo \"API ERROR: $RESPONSE\" >&2\n    return 1\n  fi\n}\n```\n\n### Common Operations\n\n```bash\n# List all boards (up to 20)\nmonday_query '{\"query\": \"{ boards(limit: 20) { id name } }\"}'\n\n# Get items from a board\nmonday_query '{\"query\": \"{ boards(ids: [BOARD_ID]) { items_page { items { id name state } } } }\"}'\n\n# Create an item\nmonday_query '{\n  \"query\": \"mutation ($board: ID!, $name: String!) { create_item(board_id: $board, item_name: $name) { id } }\",\n  \"variables\": {\"board\": \"BOARD_ID\", \"name\": \"New Item Name\"}\n}'\n\n# Update a status column\nmonday_query '{\n  \"query\": \"mutation ($board: ID!, $item: ID!, $col: String!, $val: JSON!) { change_column_value(board_id: $board, item_id: $item, column_id: $col, value: $val) { id } }\",\n  \"variables\": {\n    \"board\": \"BOARD_ID\",\n    \"item\": \"ITEM_ID\",\n    \"col\": \"status\",\n    \"val\": \"{\\\"label\\\": \\\"Done\\\"}\"\n  }\n}'\n\n# Add a comment to an item\nmonday_query '{\n  \"query\": \"mutation ($item: ID!, $body: String!) { create_update(item_id: $item, body: $body) { id } }\",\n  \"variables\": {\"item\": \"ITEM_ID\", \"body\": \"Update text here\"}\n}'\n\n# List columns in a board\nmonday_query '{\"query\": \"{ boards(ids: [BOARD_ID]) { columns { id title type } } }\"}'\n\n# Get current user info\nmonday_query '{\"query\": \"{ me { id name email account { id name } } }\"}'\n```\n\n### Pagination for Large Boards\n\n```bash\n# First page — also returns a cursor for the next page\nmonday_query '{\"query\": \"{ boards(ids: [BOARD_ID]) { items_page(limit: 50) { cursor items { id name } } } }\"}'\n\n# Next page — pass the cursor value from the previous response\nmonday_query '{\"query\": \"{ next_items_page(limit: 50, cursor: \\\"CURSOR_VALUE\\\") { cursor items { id name } } }\"}'\n```\n\n### Check Before Creating (Avoid Duplicates)\n\n```bash\n# Search for item by name before creating\nRESULT=$(monday_query '{\"query\": \"{ items_by_multiple_column_values(board_id: BOARD_ID, column_id: \\\"name\\\", column_values: [\\\"Item Name\\\"]) { id name } }\"}')\n\n# Count how many items matched\nCOUNT=$(echo \"$RESULT\" | python3 -c \"\nimport sys, json\nd = json.load(sys.stdin)\nprint(len(d.get('data', {}).get('items_by_multiple_column_values', [])))\n\")\n\n# Create only if it doesn't exist\nif [ \"$COUNT\" -eq 0 ]; then\n  echo \"Item not found — creating it\"\n  # proceed with create\nelse\n  echo \"Item already exists — skipping\"\nfi\n```\n\n### Batch Update Multiple Items\n\n```bash\n# Loop through item IDs with a small delay to respect rate limits\nfor ITEM_ID in 123456 789012 345678; do\n  monday_query \"{\n    \\\"query\\\": \\\"mutation { change_column_value(board_id: BOARD_ID, item_id: $ITEM_ID, column_id: \\\\\\\"status\\\\\\\", value: \\\\\\\"{\\\\\\\\\\\\\\\"label\\\\\\\\\\\\\\\": \\\\\\\\\\\\\\\"In Progress\\\\\\\\\\\\\\\"}\\\\\\\") { id } }\\\"\n  }\"\n  # Pause 200ms between calls to stay under rate limits\n  sleep 0.2\ndone\n```\n\n---\n\n## Part 3 — MCP Server (Recommended)\n\nThe monday.com MCP server lets you work with boards using natural language — no manual GraphQL needed.\n\n### Option A: Hosted MCP\n\nAdd to `~/.openclaw/openclaw.json` under `mcpServers`:\n\n```json\n{\n  \"mcpServers\": {\n    \"monday-mcp\": {\n      \"url\": \"https://mcp.monday.com/mcp\"\n    }\n  }\n}\n```\n\nNo local install needed. Uses OAuth.\n\nTest it:\n```bash\nmcporter call monday-mcp list_boards\n```\n\n### Option B: Local MCP (npx)\n\n```json\n{\n  \"mcpServers\": {\n    \"monday-api-mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\"@mondaydotcomorg/monday-api-mcp@latest\"],\n      \"env\": {\n        \"MONDAY_API_TOKEN\": \"your_token_here\"\n      }\n    }\n  }\n}\n```\n\nIf `npx` is slow:\n```bash\n# Install globally to avoid cold starts\nnpm install -g @mondaydotcomorg/monday-api-mcp\n# Then use \"command\": \"monday-api-mcp\" in the config above\n```\n\n---\n\n## Part 4 — Troubleshooting\n\n| Error | Cause | Fix |\n|---|---|---|\n| 401 Unauthorized | Token invalid or expired | Regenerate token in Developer settings, update file |\n| 403 Forbidden | No board access | Ask owner to share the board with the PA account |\n| \"Column not found\" | Wrong column ID | Run `list columns` query first |\n| \"Complexity budget exhausted\" | Query too heavy | Use pagination with `limit: 50` |\n| Empty response | Network or JSON issue | Run `echo $RESPONSE | python3 -m json.tool` to inspect |\n| Rate limit (429) | >5000 requests/min | Add `sleep 0.2` between calls in loops |\n\n---\n\n## Part 5 — Setup Checklist\n\n```\n[ ] PA has a monday.com account (agent email, not owner's)\n[ ] API token saved to ~/.credentials/monday-token.txt\n[ ] MONDAY_API_TOKEN exported in shell\n[ ] Workspace access confirmed\n[ ] Verified with: monday_query '{\"query\": \"{ me { id name } }\"}'\n[ ] If using MCP: server added to config and tested\n```\n\n**Rules:**\n- Do NOT create or update board items without explicit instruction from owner.\n- Always confirm board ID before mutations.\n- Never print or log the API token.\n\n---\n\n## Cost Tips\n\n- **Cheap:** The MCP server handles natural language → API translation. Use it to avoid writing complex GraphQL.\n- **Expensive:** Fetching all items from large boards without pagination. Always use `limit:`.\n- **Batch:** Use a loop with `sleep 0.2` for bulk updates — not one API call per session.\n- **Small model OK:** Routine operations (list, create, update) work with any model.\n- **Use medium model for:** Debugging GraphQL errors or constructing complex queries.\n\n---\n\n## Core Operating Rules\n\nFollow these rules every time, without exception:\n\n**1. Create → API. Operate → MCP.**\n- New workspace / board / column: use API (curl + GraphQL)\n- Daily read/update/create items: use MCP (mcporter)\n\n**2. Never guess IDs.**\n- Before any mutation: run `mcporter call monday.list_workspaces` or `get_board_info` first\n- Store all IDs in TOOLS.md immediately after creation\n\n**3. One workspace per context.**\n- Family ≠ Work ≠ PA Network\n- Never mix contexts in the same workspace\n\n**4. Before any mutation: verify.**\n- Run `mcporter call monday.get_board_info boardId=X` to confirm column IDs\n- Wrong column ID = silent failure or data corruption\n\n**5. IDs in TOOLS.md, not memory.**\n- After creating any resource: `echo \"board-name: $ID\" >> TOOLS.md`\n- Before using an ID: `grep \"board-name\" TOOLS.md`\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn70mvkzt5qbjzp9kdyecvn6jh840nqb\",\n  \"slug\": \"monday-for-agents\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1775048766248\n}","readmeExcerpt":"Skill: Monday For Agents Owner: netanel-abergel Summary: Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a... Tags: latest:1.1.1 Version history: v1.1.1 | 2026-04-02T16:25:24.438Z | user monday-for-agents 1.1.1 - Renamed documentation file from SKILL.md to skill.md for consistency. - No changes to implementatio","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"export MONDAY_API_TOKEN=\"TOKEN_HERE\"  # current shell only, not persisted"},{"language":"text","snippet":"[ ] PA has a monday.com account (agent email, not owner's)\n[ ] MONDAY_API_TOKEN set in OpenClaw agent environment (not a plaintext file)\n[ ] Workspace access confirmed\n[ ] Verified with: monday_query '{\"query\": \"{ me { id name } }\"}'\n[ ] If using MCP: server added to config and tested"},{"language":"text","snippet":"https://api.monday.com/v2    (preferred)\nhttps://api.monday.com/graphql  (also works)"},{"language":"bash","snippet":"MONDAY_API_URL=\"https://api.monday.com/v2\"\n\n# MONDAY_API_TOKEN must be set in the agent's environment (not read from file)\nif [ -z \"$MONDAY_API_TOKEN\" ]; then\n  echo \"ERROR: MONDAY_API_TOKEN is not set. Configure it in your OpenClaw agent environment.\" >&2\n  exit 1\nfi\n\nmonday_query() {\n  RESPONSE=$(curl -s -X POST \"$MONDAY_API_URL\" \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: $MONDAY_API_TOKEN\" \\\n    -H \"API-Version: 2024-10\" \\\n    -d \"$1\")\n\n  if echo \"$RESPONSE\" | python3 -c \"\nimport sys, json\nd = json.load(sys.stdin)\nif d.get('errors'):\n    print('API ERROR:', d['errors'])\n    sys.exit(1)\n\" 2>/dev/null; then\n    echo \"$RESPONSE\"\n  else\n    echo \"API ERROR: $RESPONSE\" >&2\n    return 1\n  fi\n}"},{"language":"bash","snippet":"# List boards\nmonday_query '{\"query\": \"{ boards(limit: 25) { id name description state } }\"}'\n\n# Get items from a board\nmonday_query '{\"query\": \"{ boards(ids: [BOARD_ID]) { items_page(limit: 50) { cursor items { id name group { id title } column_values { id title text type } } } } }\"}'\n\n# Create an item\nmonday_query '{\n  \"query\": \"mutation ($board: ID!, $name: String!) { create_item(board_id: $board, item_name: $name) { id } }\",\n  \"variables\": {\"board\": \"BOARD_ID\", \"name\": \"New Task\"}\n}'\n\n# Update a status column\nmonday_query '{\n  \"query\": \"mutation ($board: ID!, $item: ID!, $col: String!, $val: JSON!) { change_column_value(board_id: $board, item_id: $item, column_id: $col, value: $val) { id } }\",\n  \"variables\": {\n    \"board\": \"BOARD_ID\",\n    \"item\": \"ITEM_ID\",\n    \"col\": \"status\",\n    \"val\": \"{\\\"label\\\": \\\"Done\\\"}\"\n  }\n}'\n\n# Add a comment to an item\nmonday_query '{\n  \"query\": \"mutation ($item: ID!, $body: String!) { create_update(item_id: $item, body: $body) { id } }\",\n  \"variables\": {\"item\": \"ITEM_ID\", \"body\": \"Update text here\"}\n}'\n\n# List columns in a board\nmonday_query '{\"query\": \"{ boards(ids: [BOARD_ID]) { columns { id title type } } }\"}'\n\n# Query subitems\nmonday_query '{\"query\": \"{ items(ids: [ITEM_ID]) { subitems { id name column_values { id text } } } }\"}'\n\n# Get current user\nmonday_query '{\"query\": \"{ me { id name email account { id name } } }\"}'"},{"language":"bash","snippet":"# First page — also returns a cursor\nmonday_query '{\"query\": \"{ boards(ids: [BOARD_ID]) { items_page(limit: 100) { cursor items { id name } } } }\"}'\n\n# Next page — pass the cursor value from the previous response\nmonday_query '{\"query\": \"{ next_items_page(limit: 100, cursor: \\\"CURSOR_VALUE\\\") { cursor items { id name } } }\"}'"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"skill.md","content":"---\nname: monday-for-agents\ndescription: \"Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a monday.com workspace for a PA, connecting the PA to monday.com, querying boards and items, creating or updating items, or troubleshooting monday.com API access. Covers GraphQL cookbook, column types, and MCP configuration. Works with any LLM model.\"\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"📋\",\n        \"requires\":\n          {\n            \"env\": [\"MONDAY_API_TOKEN\"],\n          },\n      },\n  }\n---\n\n# monday.com for Agents\n\nOne skill for everything monday.com: account setup, daily operations, GraphQL API, MCP server, and troubleshooting.\n\n## Minimum Model\nAny model for routine operations. Use a medium model for debugging GraphQL errors.\n\n---\n\n## Section 1 — Setup\n\n### Option A: Manual Account Creation\n\nEach PA needs its own account — do not use the owner's.\n\n1. Go to [monday.com/agents-signup](https://monday.com/agents-signup).\n2. Use the agent email (e.g. `agent@agentdomain.com`).\n3. Owner invites the PA via Admin → Users → Invite.\n\n### Get an API Token\n\n1. Log into monday.com as the agent.\n2. Click avatar → **Developers** → **My Access Tokens** → **Copy**.\n3. Set the token as an environment variable via OpenClaw's config (preferred) or your system's secret manager.\n   ❌ Do **not** write the token to a plaintext file or add it to shell startup files.\n   ❌ Do **not** commit tokens to version control.\n\n**Recommended: OpenClaw env config**\nAdd `MONDAY_API_TOKEN` to your OpenClaw agent environment via the Ocana dashboard or `openclaw.json` `env` block — never hardcode it in scripts.\n\n**For local dev only (not production):**\n```bash\nexport MONDAY_API_TOKEN=\"TOKEN_HERE\"  # current shell only, not persisted\n```\n\n### Setup Checklist\n\n```\n[ ] PA has a monday.com account (agent email, not owner's)\n[ ] MONDAY_API_TOKEN set in OpenClaw agent environment (not a plaintext file)\n[ ] Workspace access confirmed\n[ ] Verified with: monday_query '{\"query\": \"{ me { id name } }\"}'\n[ ] If using MCP: server added to config and tested\n```\n\n---\n\n## Section 2 — Operations\n\n### API Basics\n\nMonday.com uses a single **GraphQL endpoint**:\n\n```\nhttps://api.monday.com/v2    (preferred)\nhttps://api.monday.com/graphql  (also works)\n```\n\n#### Reusable Helper\n\n```bash\nMONDAY_API_URL=\"https://api.monday.com/v2\"\n\n# MONDAY_API_TOKEN must be set in the agent's environment (not read from file)\nif [ -z \"$MONDAY_API_TOKEN\" ]; then\n  echo \"ERROR: MONDAY_API_TOKEN is not set. Configure it in your OpenClaw agent environment.\" >&2\n  exit 1\nfi\n\nmonday_query() {\n  RESPONSE=$(curl -s -X POST \"$MONDAY_API_URL\" \\\n    -H \"Content-Type: application/json\" \\\n    -H \"Authorization: $MONDAY_API_TOKEN\" \\\n    -H \"API-Version: 2024-10\" \\\n    -d \"$1\")\n\n  if echo \"$RESPONSE\" | python3 -c \"\nimport sys, json\nd = json.load(sys.stdin)\nif d.get('errors'):\n    print('API ERROR:', d['errors'])\n    sys.exit("},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn70mvkzt5qbjzp9kdyecvn6jh840nqb\",\n  \"slug\": \"monday-for-agents\",\n  \"version\": \"1.1.1\",\n  \"publishedAt\": 1775147124438\n}"},{"path":"skill-card.md","content":"## Description:\n\nSet up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[netanel-abergel](https://clawhub.ai/user/netanel-abergel)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nDevelopers and operators use this skill to configure an OpenClaw agent for monday.com and perform board, item, update, and troubleshooting workflows through GraphQL or MCP.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: A monday.com API token may be exposed if placed directly in plaintext configuration files.\n\nMitigation: Use the platform secret or environment mechanism, avoid committing tokens, and use a least-privilege monday.com account.\n\nRisk: The local MCP setup uses an unpinned package that would receive the monday.com API token.\n\nMitigation: Prefer the hosted OAuth MCP option, or pin and review the local MCP package before use.\n\nRisk: Board IDs stored in TOOLS.md can reveal workspace-specific internal metadata.\n\nMitigation: Treat board IDs as internal data and avoid publishing or sharing TOOLS.md outside the intended workspace.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/netanel-abergel/skills/monday-for-agents)\n- [monday.com GraphQL API](https://developer.monday.com/api-reference)\n- [monday.com MCP Server Docs](https://mcp.monday.com)\n- [monday.com Agent Signup](https://monday.com/agents-signup)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown with inline shell, JSON, and GraphQL examples]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Requires MONDAY_API_TOKEN for direct API usage; hosted MCP option uses OAuth.]\n\n## Skill Version(s):\n\n1.1.1 (source: server release evidence)\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":"Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a... Skill: Monday For Agents Owner: netanel-abergel Summary: Set up a monday.com account for an OpenClaw agent and work with monday.com boards, items, and updates via the GraphQL API or MCP server. Use when: creating a... Tags: latest:1.1.1 Version history: v1.1.1 | 2026-04-02T16:25:24.438Z | user monday-for-agents 1.1.1 - Renamed documentation file from SKILL.md to skill.md for consistency. - No changes to implementatio","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1160,"uniquenessScore":47,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T00:06:29.240Z","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":"2026-10-10T00:06:29.240Z","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":"2026-10-10T01:02:36.416Z","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"}]}}}