humanerd-drew/opencode-drewgent/kanban-worker

Claude Code and agent skill by humanerd-drew/opencode-drewgent

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Install

npx vskill@latest install humanerd-drew/opencode-drewgent/kanban-worker

SKILL.md

The same SKILL.md was published earlier as humanerd-drew/opencode-drewgent/kanban-worker.


title: Kanban Worker name: kanban-worker type: document space: concept tags: [concept] created: 2026-05-20 updated: 2026-06-10 links:

  • "[[@action/skills/SKILL-INDEX]]"
  • "[[@memory/growth/{{AGENT_NAME_LOWER}}-kanban-implementation-plan]]"
  • "[[kanban-dashboard]]"
  • "[[kanban-orchestrator]]"
  • "[[references/protocol.md]]"
  • "[[@identity/brain/rules]]"---

Kanban Worker Skill

Task execution skill for kanban worker agents. A worker agent picks up tasks from the {{AGENT_NAME}} kanban board, executes them, and reports results.

Overview

A kanban worker is an autonomous agent that:

  1. Claims a task from the board (or receives a task_id via env)
  2. Reports heartbeat while working
  3. Executes the task (code, research, writing, etc.)
  4. Reports completion with result/summary

Workers are dispatched by the kanban dispatcher cron job or receive tasks via KANBAN_TASK_ID in the environment.

Workflow

Startup — Acquire Task

A worker can acquire a task in two ways:

Option A: Dispatcher assigns task_id via env

KANBAN_TASK_ID=t_abc123
KANBAN_WORKER_PID=12345

Read KANBAN_TASK_ID to know which task to work on.

Option B: Self-claim from board

kanban_list(status="ready")
# Pick a task
kanban_claim(task_id, ttl_seconds=3600)
During Work — Heartbeat

Long-running tasks must send heartbeats every ~60 seconds:

kanban_heartbeat(task_id, note="Step 2/5: running tests")

Heartbeat purpose:

  • Prevents claim expiry (default TTL: 1 hour)
  • Lets dispatcher monitor progress
  • Provides audit trail in task_events
Task Completion

When done, call kanban_complete:

kanban_complete(
task_id,
result="<what was produced or accomplished>",
summary="<one-line summary for board display>",
metadata={
"changed_files": ["file1", "file2"],
"steps_completed": 3,
},
created_cards=["t_xxx", "t_yyy"], # optional: any sub-tasks created
)

Hallucination check: created_cards IDs are verified against the DB. Any fake IDs cause a completion_blocked_hallucination event and exception.

Task Failure

If task cannot be completed:

kanban_complete(
task_id,
result="FAILED: <reason>",
summary="<short summary>",
metadata={"error": "<error details>"},
)

Consecutive failures are tracked. After max_retries failures, task is moved to failed state.

Blocking a Task

If task cannot proceed due to a dependency or external blocker:

kanban_block(task_id, reason="Blocked by upstream: need API credentials")

Unblock when ready:

kanban_unblock(task_id)

Task Lifecycle

ready → claimed → in_progress → completed
↘ blocked (can return to claimed)
↘ failed (max retries exceeded)
TransitionTriggerTool Call
ready → claimedWorker claims taskkanban_claim()
claimed → in_progressFirst heartbeat sentkanban_heartbeat()
in_progress → completedTask donekanban_complete()
in_progress → blockedDependency unmetkanban_block()
blocked → in_progressBlocker clearedkanban_unblock()
in_progress → failedmax_retries hitkanban_complete() with failure

Workspace

Workers operate in their own workspace:

FieldDescription
workspace_kind'local' \'docker' \'ssh'
workspace_pathPath to working directory

Use workspace_path as the working directory for all file operations.

Reference

See [[references/protocol.md]] for the full task lifecycle protocol, API schema, and examples.

Environment Variables

VariableDescription
KANBAN_TASK_IDTask ID assigned by dispatcher (if dispatched)
KANBAN_WORKER_PIDPID of the worker process
KANBAN_BOARDBoard name (default: 'default')
DREWENT_HOME{{AGENT_NAME}} home path (~/.{{AGENT_NAME_LOWER}})

Dispatcher Notes (for cron job agents)

The kanban dispatcher is not invoked via from tools.{{AGENT_NAME_LOWER}}_kanban_db import dispatch_once — that import path does not resolve in production. The actual dispatch mechanism uses standalone scripts:

Scripts: ~/.{{AGENT_NAME_LOWER}}/scripts/dispatch_once_{board}.py (one per board: default, content, integrations)

Execution (run directly, no import gymnastics):

bash
~/.{{AGENT_NAME_LOWER}}/source/{{AGENT_NAME_LOWER}}-agent/.venv/bin/python ~/.{{AGENT_NAME_LOWER}}/scripts/dispatch_once_default.py

Each script opens its own SQLite connection and runs 5 phases:

  1. Phase 0 (watchdog): os.kill(pid, 0) to check worker liveness; dead workers reclaimed immediately
  2. Phase 0.5 (affinity): Skips tasks with 3+ consecutive failures (cooldown)
  3. Phase 1 (TTL reclaim): Reclaims tasks past claim_expires (but skips if worker PID is still alive)
  4. Phase 2 (claim): Claims ready tasks with adaptive MAX_CLAIM (scales with queue depth)
  5. Phase 3 (spawn): Spawns run_kanban_worker.py via Popen with logfile redirect (no PIPE deadlock)

Worker logs: ~/.{{AGENT_NAME_LOWER}}/P4-cortex/scripts/kanban/logs/workers/{task_id}.log

Output protocol: [SILENT] if no work done; otherwise detailed breakdown with per-task details.

Related Skills

  • [[kanban-orchestrator]] — Task decomposition and linking
  • [[kanban-dashboard]] — Board visualization via n8n
  • [[kanban-dispatcher-hardening]] — Dispatcher watchdog + logfile redirect internals
  • [[kanban-dispatcher-stalled]] — Diagnose dispatcher stalls when cron stops running

Related

  • [[@memory/growth/{{AGENT_NAME_LOWER}}-kanban-implementation-plan]]
  • [[@action/skills/SKILL-INDEX]]

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
3
Repository forks
8
7-day trend score
0

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/humanerd-drew/opencode-drewgent/kanban-worker/badge)](https://verified-skill.com/skills/humanerd-drew/opencode-drewgent/kanban-worker)

Something wrong with this skill or its page? Tell us.