SKILL PLAN · DETERMINISTIC
A small plan for a real job
Start with the minimum useful stack. Add nothing unless it has a clear responsibility in the run.
- Task
- Debug and reproduce
- Agent
- Codex
- Priority
- Balanced
Change any option, then update this plan. Rules + reviewed metadata only. No LLM. Same inputs produce the same plan.
01Core execution
Native · Codex
Repo Intake and Plan
Maps the relevant execution path before changing code. Open Repo Intake and Plan profile and install guide ↗Review permissions, limitations, and evidence
- Agent fit
- Native · Codex
- Main limitation
- Detailed package files are not fully catalogued.
- First risk
- Review before install · Medium
- Source
- Pinned source · fb3ccdf5
02Guardrail
Native · Codex
grill-me
Forces a minimal run and challenges unsupported assumptions. Open grill-me profile and install guide ↗Review permissions, limitations, and evidence
- Agent fit
- Native · Codex
- Main limitation
- The package is a launcher that calls the separate grilling Skill; installing grill-me alone may not include the interview itself.
- First risk
- Decision fatigue · Low
- Source
- Pinned source · c55ee460
03Evidence
Native · Codex
tdd
Turns the reproduced failure into a lasting regression check. Open tdd profile and install guide ↗Review permissions, limitations, and evidence
- Agent fit
- Native · Codex
- Main limitation
- The workflow needs a functioning test runner and clear public behavior.
- First risk
- False confidence · Medium
- Source
- Pinned source · c55ee460
Core executioncontext-map
- Choose this when
- you want fewer declared permissions for the same role
- Tradeoff to check
- The workflow is intentionally brief and may miss dynamic dependencies or runtime ownership.
Inspect context-map ↗GuardrailMinimal Run and Audit
- Choose this when
- this role's workflow fits your project better after you inspect the tradeoff
- Tradeoff to check
- Detailed package files are not fully catalogued.
Inspect Minimal Run and Audit ↗Evidencewebapp-testing
- Choose this when
- you want stronger published documentation to start from
- Tradeoff to check
- It assumes Python Playwright and a runnable local application are available.
Inspect webapp-testing ↗ Combined permission budget
This is the union of declared permissions across the plan. Review each package before installation.
Read repository filesWrite a planRead project contextRead filesWrite testsRun test commands
Finish with evidence
Reduce an intermittent report to the smallest repeatable failure and a regression check.
Observe first; change one variable at a time and preserve the original failure evidence.
- 3-step acceptance check
- Reproduce the same failure twice from a documented starting state.
- Identify the smallest input or state transition that triggers it.
- Add a check that fails before the fix and passes after it.
- Stop conditions
- The reproduction depends on unknown external state.
- Multiple variables are changed before the failure is isolated.
- Logs may contain secrets or personal data.