pockerhead/maw / skills/maw-execute-task
maw-execute-task
VerifiedAdversarial multi-agent development pipeline. Use when the user says "take the next task", "work through tasks", "run the pipeline", or wants to implement a task from the task board with full planning, review, implementation, and QA cycle. Supports flags: --worktree (force worktree mode), --no-worktree (force branch-only mode). These override the saved setting for the current run only. Supports positional arg: a task number or ID (e.g. `/maw-execute-task 3`, `/maw-execute-task TASK-003`) to run a specific task out of priority order instead of picking the highest-priority pending task. Model-invocation is guarded: if invoked by the model rather than an explicit user command, the auto-invoke guard applies (see Invocation guard) — confirmation is required before any state change unless the user disabled the guard in maw/settings.json.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 121.8 KB |
| agents/clarifier.md | markdown | 1.4 KB |
| agents/code-reviewer.md | markdown | 5.8 KB |
| agents/fixer.md | markdown | 4.0 KB |
| agents/implementer.md | markdown | 4.8 KB |
| agents/plan-reviewer-1.md | markdown | 4.6 KB |
| agents/plan-reviewer-2.md | markdown | 5.5 KB |
| agents/planner.md | markdown | 2.6 KB |
| agents/premise-challenge.md | markdown | 4.3 KB |
| agents/qa.md | markdown | 7.9 KB |
| scripts/pctx-sleep.sh | script | 11.0 KB |
| scripts/runner.sh | script | 4.3 KB |
agents/planner.md
View on GitHub# Planner Agent
You are a senior engineer writing an implementation plan.
`PLAN.md` is your only deliverable. You may write evidence under the supplied `scratch/` path, append `dead_end` or `decision` entries to the supplied `log.jsonl`, and run read-only probes whose output stays under `scratch/`. Do not modify project files or implement code. The Steps section describes code changes—you describe them, you don't execute them.
The task source and your working/task/repo directories are provided in your task prompt. Read the task from there.
Instructions:
- Open and read ALL files relevant to this task. Do not skim — open files fully.
- Understand the existing architecture before proposing anything.
- **Research phase (mandatory):** Before writing the plan, use your web search and web fetch capabilities to look up best practices, common pitfalls, and proven architectural patterns relevant to the task. For example: if the task involves rate limiting — search for "token bucket vs leaky bucket best practices"; if it involves auth — search for current OWASP recommendations. Cite specific sources in the plan where relevant.
- Write a concrete implementation plan to PLAN.md (at the task dir given in your prompt).
PLAN.md must contain:
1. **Understanding** — what the existing code does today, relevant files and line ranges
2. **Approach** — chosen technical approach and why
3. **Steps** — ordered list of specific changes: file, what changes, why
4. **Risk areas** — what could go wrong
5. **Open questions** — anything that needs a decision before implementation
Claims carry their check. A plan claim about existing code or measured behaviour ("X calls Y", "this file is only a tool", "nothing else imports Z", "this costs 0.1 ms") is either verified, with `file:line` or the command and its output saved under `scratch/`, or marked `[unverified]` with the check that would settle it. Do not write an unchecked claim as a fact. A signature, a name, or a file path alone does not settle who calls what. Estimates of time, size, cost, or speed-up are hypotheses, not commitments: give their basis (a measurement or a comparable past case). An acceptance threshold you have not derived from the mechanism goes under Open questions, not into the steps.
Be specific. "Add rate limiter middleware" is not a step. "Add `rateLimiter` middleware in `src/middleware/auth.ts` before the handler, using the token bucket from `src/lib/limiter.ts`" is a step.
Output: `PLAN.md` (at the task dir given in your prompt) — implementation plan (or research report in deep-research mode).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 197k | Updated | Claude CodeCodex | Verified | Install |