danielmax937/agent-im-kanban-api
.cursor/skills/agent-im-kanban-api/SKILL.md
Calls the local agent-im Kanban HTTP API (projects, sprints, tasks create/assign, kanban-roles, bridge, local-config). Use when the user wants to create or assign Kanban tasks via API, automate the board, or curl workflows against agent-im (default port 3300). Primary focus: POST /api/workflows/tasks/create and assign.
development
Updated Apr 16, 2026
$ install --global
skillsauthnpx skillsauth add danielmax937/agent-im agent-im-kanban-apiInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 8:05 AM6.2s2 files scanned
SKILL.md
- name:
- agent-im-kanban-api
- description:
- >-
- (default port 3300). Primary focus:
- POST /api/workflows/tasks/create and assign.
agent-im Kanban HTTP API
Local agent-im exposes REST under AGENT_IM_BASE_URL (default http://127.0.0.1:3300). Canonical reference: repository docs/API.md.
Prerequisites
- Next / PM2 process is running (
./start-bg.shornpm run dev). - For create sprint / assign: Git repo at
repository.localPathmust exist and remotes must work when the API runs git commands.
Environment
| Variable | Default | Meaning |
|----------|---------|---------|
| AGENT_IM_BASE_URL | http://127.0.0.1:3300 | Base URL with no trailing slash |
Primary flow: create task (and optionally assign to dev lane)
GET /health— optional sanity check.GET /api/sprints?projectId=<id>— picksprintId(often the first active sprint).POST /api/workflows/tasks/create— body:
Response includes{ "projectId": "<id>", "sprintId": "<uuid>", "title": "<title>" }id(task session id) andissueId.- Optional — assign from todo —
POST /api/workflows/tasks/assign:
Use{ "projectId": "<id>", "sprintId": "<uuid>", "issueId": "<from step 3>", "taskSessionId": "<from step 3>", "kanbanAgent": "agent-dev" }agent-devorcodex-seniorwhen picking up a todo card (assignFromTodo).
Helper script (repo)
From the agent-im repository root:
export AGENT_IM_BASE_URL=http://127.0.0.1:3300 # optional
bash .cursor/skills/agent-im-kanban-api/scripts/create-kanban-task.sh <projectId> "<title>" [agent-dev]
- Third argument
agent-dev(or omit): if provided, calls assign after create.
Related endpoints (quick index)
| Action | Method | Path |
|--------|--------|------|
| Projects list | GET | /api/projects |
| Create/update project | POST | /api/projects |
| Bridge + config | GET/PUT/POST | /api/local-config |
| Runners | GET | /api/platform/runners |
| Bridge start/stop | POST | /api/bridge/start, /api/bridge/stop body {"slug":"..."} |
| Start sprint | POST | /api/workflows/sprints/start |
| Kanban roles | GET/PUT | /api/projects/:projectId/kanban-roles |
| Create task | POST | /api/workflows/tasks/create |
| Assign task | POST | /api/workflows/tasks/assign |
Full request bodies and examples: docs/API.md.
Agent behavior
- Prefer
curlor the helper script to avoid inventing URLs. - On non-2xx responses, surface the response body to the user.
- Do not log secrets;
config.envand tokens may appear in API payloads—handle carefully.
Related Skills
danielmax937/kanban-e2e-runner
development
VerifiedTrustedCommunity
Use when running end-to-end Kanban workflow tests against a live agent-im server, verifying state transitions, API behavior, coverage gates, private repo CI lane, UAT, blocking, hotfix, and async close flows from docs/KANBAN-TESTCASES.md
SKILL.mdUpdated Apr 16, 2026
danielmax937/pre-execution-security-audit
tools
VerifiedTrustedCommunity
Pre-action security audit for AI agents before running shell, scripts, or tools: prompt-injection refusal, sensitive-path denylist, destructive-command gates, high-risk human-in-the-loop (CONFIRM), supply-chain preview for external code, post-action cleanup and change summary. Use when the user wants safe execution discipline, or when running commands that could affect assets, network, or system.
SKILL.mdUpdated Apr 16, 2026
openclaw/openclaw-secret-scanning-maintainer
development
VerifiedTrustedCommunity
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
357,764SKILL.mdUpdated Apr 15, 2026
openclaw/openclaw-release-maintainer
development
VerifiedTrustedCommunity
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
357,764SKILL.mdUpdated Apr 10, 2026