Skip to content
cccskills
FreePublished on GitHub

mk:task-queue

Task claiming and ownership tracking for parallel agent execution. Agents claim tasks from a shared queue with file ownership enforcement. Use during parallel execution phases when multiple agents work simultaneously.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.4 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Task Queue & Ownership Tracker

Manages task assignment and file ownership during parallel execution.

Task Queue

Tasks are tracked in session-state/task-queue.json:

{
  "tasks": [
    {
      "id": 1,
      "description": "Implement API endpoints",
      "owner": null,
      "status": "pending",
      "ownership": ["src/api/*", "src/routes/*"],
      "blocked_by": []
    },
    {
      "id": 2,
      "description": "Implement UI components",
      "owner": null,
      "status": "pending",
      "ownership": ["src/components/*", "src/pages/*"],
      "blocked_by": []
    }
  ]
}

Task Lifecycle

pending → claimed (agent assigned) → in_progress → completed
                                   → blocked (dependency not met)

Claiming Protocol

  1. Agent requests next available task
  2. Queue returns lowest-ID task where: status=pending AND blocked_by all completed
  3. Agent declares ownership globs
  4. Queue checks for overlap with other in_progress tasks
  5. If overlap: REJECT claim, report conflict to orchestrator
  6. If no overlap: ASSIGN task, set status=in_progress, record owner

Ownership Enforcement

Each task declares file ownership via glob patterns. Before any file write, check if the file matches the agent's declared ownership.

ActionOwned File?Result
ReadAnyAlways allowed
Write/EditOwnedAllowed
Write/EditNot ownedSTOP — report ownership violation
Write/EditOverlappingSTOP — report conflict to orchestrator

Integration

  • Orchestrator creates the task queue when decomposing parallel work
  • Parallel agents claim and complete tasks
  • Orchestrator monitors queue for completion and triggers integration test
  • Queue is ephemeral (session-state/) — recreated per parallel execution

Team Coordination

Team-mode coordination rules (file ownership, commit discipline, completion messages) live in .claude/skills/team-config/references/team-coordination.md, loaded by mk:team-config on team activation.

Gotchas

  • Race condition on claims: Two agents reading task-queue.json simultaneously may both claim the same task. Mitigation: orchestrator is the sole claim-serializer — agents REQUEST claims through orchestrator, never self-claim directly
  • Ownership globs must not overlap: src/api/* and src/api/auth/* overlap — the more specific glob must be in the SAME task, not split across agents
  • Queue file doesn't auto-create: Orchestrator must create session-state/task-queue.json before dispatching parallel agents. If missing, agents should STOP and report, not create it themselves
  • Completed tasks are not removed: Tasks stay in queue with status=completed for audit trail. Queue is cleaned up only when the parallel execution phase ends

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Use this skill to generate well-branded interfaces and assets for MeowKit (AI Agent Toolkit for Claude Code), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Turn a raw idea into ONE honest recommendation: interview one question at a time until confirmed, then give a verdict with trade-offs and a checklist. Not for options or debate.

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Browser automation CLI for agents: navigate, click/fill, screenshot, extract data, test apps, Electron/Slack, cloud browsers. NOT for the user's real Chrome profile/cookies (mk:chrome-profile).

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Detects the right agent and complexity tier at Phase 0 orient; runs first in every workflow. NOT for runtime agent routing inside a single skill.

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Angular v20+ patterns: components, signals, services, forms, routing, HTTP, testing, SSR. Auto-activates on .ts files in Angular projects (angular.json detected).

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

Design and review durable REST, GraphQL, RPC, or event API contracts: shape, compatibility, pagination, error semantics. Discovers existing consumers first. Not implementation, schema, or release.

The English summary is being prepared. Showing the original description.

ngocsangyem/MeowKit15Updated Jul 28, 2026

See all skills by ngocsangyem

Report a problem with this skill