implement-tasks

Installation
SKILL.md

Implement Tasks

Turn an approved queue into one verified change. Be a thin conductor: you own the model plan, scheduling, write ownership, dependency release, integration, and delivery. implement-and-review owns everything inside a task: its roles and contexts, review cycles, isolation, the implementer's brief, and evidence. Do not restate or override those rules here.

The input is the approved PRD and tasks.md from to-tasks under .ai-workflow/work/<feature>/, laid out as shared/references/work-state.md describes. A bare plan goes to to-prd and to-tasks first. One bounded task with a complete acceptance contract and no open product, security, contract, data, or dependency decision goes straight to implement-and-review.

Plan

  1. Read tasks.md and each task's brief.md. An open decision (a task marked Design: open is not blocked; its debate settles the design), missing access, a dependency cycle, or two tasks owning the same path without a merge plan blocks the affected tasks.
  2. Pick the review mode. A new feature queue uses feature mode: mark tasks critical when they carry high risk or a shared contract, and defer the rest to one final review. Otherwise use task mode, where every task gets its own reviewer. An existing approved plan keeps its mode and routes.
  3. Resolve each task's route with python3 shared/scripts/model_routing.py resolve <route> --provider <host> [--risk high], giving --risk high only for a task that touches the invariants policy.high_risk_triggers names, never for a sensitive feature label. For a task whose brief says Design: open, add the debate seats (challenger and arbiter) from the design-debate route to its row. Add the integration or final reviewer, whose model differs from every author's. Read .rar-skills/config.local.yaml once, if present, as advisory input while forming the plan (shared/references/local-config.md); never reread it after approval.
  4. Show the plan: for each task its roles with model, effort, and host route; the integration or final reviewer; the concurrency cap; the review-cycle limit; and the total call ceiling. Ask: "Approve this plan, or specify changes." A request to use defaults and run approves the unchanged resolved plan. Task approval, --auto, a saved preference, or silence is not model approval. When the user wants one decision for queue and models, show both together; the single response approves both.
  5. Write the approved plan to the top of tasks.md with the user's response and the time. It is fixed from then on. A change to any model, effort, role, host route, or limit needs the affected rows approved again. An unavailable route blocks its own tasks; never swap in another model.

Run

Keep the ledger, not the transcript: tasks.md plus the task reports are the ledger. Update a task's row before dispatch and after its result, and resume from them.

Each wave:

Installs
42
GitHub Stars
2
First Seen
Sep 3, 2026