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
Test-driven development
Agent
Codex
Priority
Balanced
Start over

Rules + reviewed metadata only. No LLM. Same inputs produce the same plan.

03 SKILLS · Install order

Your Skill Plan

Install and verify one role at a time. The plan never forces three Skills when fewer are enough.

Read the public task guide ↗
01Core execution

Native · Codex

tdd

Drives the red, green, refactor loop.
Open 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 · 885e2ca4
02Guardrail

Portable · Codex

create-implementation-plan

Keeps the test tied to the actual change boundary.
Open profile and install guide ↗
Review permissions, limitations, and evidence
Agent fit
Portable · Codex
Main limitation
Demanding zero ambiguity can create oversized plans or false precision for exploratory work.
First risk
False certainty from generated detail · Medium
Source
Pinned source · 318066d2
03Evidence

Native · Codex

minimal-run-and-audit

Runs the smallest relevant suite and records the result.
Open profile and install guide ↗
Review permissions, limitations, and evidence
Agent fit
Native · Codex
Main limitation
It does not choose the reproduction target, train a model, conduct broad paper analysis, or hide scientific-meaning changes.
First risk
Scientific changes hidden as setup fixes · High
Source
Pinned source · 3ab50525

Combined permission budget

This is the union of declared permissions across the plan. Review each package before installation.

Read filesWrite testsRun test commandsWrite documentsRun commandsReview package instructions before install

Finish with evidence

Make the desired behavior executable before implementation and keep the change small.

One behavior at a time; do not rewrite unrelated code to make a test pass.

  1. 3-step acceptance check
  2. Show the new test failing for the intended reason.
  3. Make the smallest implementation change that passes it.
  4. Run the adjacent regression tests before refactoring.
  • Stop conditions
  • The test only mirrors implementation details.
  • Unrelated behavior changes to make the test pass.
  • The full suite is skipped after shared code changes.