tdd-executor
Skill0 starsChanged 4 months agoMITView on GitHub
Runs red/green/refactor loops against acceptance criteria and TEST_STRATEGY. Use when practicing TDD or when tests should lead implementation. Emits TDD_SESSION. Never skips red, never refactors on red, never claims green without command evidence.
In this repository27 other files it gives its agents.
- adr-enforcerSkill
- ai-eval-harnessSkill
- api-contract-guardianSkill
- change-impact-analyzerSkill
- code-reviewerSkill
- context-loaderSkill
- defect-analystSkill
- delivery-plannerSkill
- engineering-mentorSkill
- engineering-osSkill
- feature-implementerSkill
- guardrails-configuratorSkill
- incident-commanderSkill
- loop-engineerSkill
- migration-surgeonSkill
- model-routerSkill
- observability-designerSkill
- performance-auditorSkill
- postmortem-writerSkill
- pr-generatorSkill
- quality-gateSkill
- refactoring-advisorSkill
- requirements-grillSkill
- security-auditorSkill
- spec-validatorSkill
- test-strategy-designerSkill
- threat-modelerSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 31
Upstream: test-strategy-designer, delivery-planner, spec-validator.
- Distinctive: line 43
Stop if AC is untestable — hand back to spec-validator.
- Very specific: line 51
Update TDD_SESSION log per cycle.
- Distinctive: line 52
After cycles, summarize coverage vs AC IDs.
- Distinctive: line 92
Never write implementation before a failing test in TDD mode (unless user aborts TDD).
- Distinctive: line 93
Never refactor on red.
- Distinctive: line 94
Never invent green test results.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Purpose
Implement behavior test-first with a disciplined red → green → refactor loop tied to AC IDs.
When to Use / When NOT to Use
Use when: user asks for TDD; high-correctness units; pairing with TEST_STRATEGY; implementing pure logic/API contracts.
Do not use when: spike/prototype explicitly throwaway; pure docs; exploratory defect triage (defect-analyst first).
Preconditions
At least one testable AC or behavior statement. Prefer TEST_STRATEGY + TASK_GRAPH. Project test command discoverable.
Inputs / Outputs
Inputs: AC IDs, TEST_STRATEGY, CONTEXT_PACK, task scope.
Outputs: TDD_SESSION (+ code/tests); may produce/update IMPL_REPORT fields.
Upstream / Downstream
Upstream: test-strategy-designer, delivery-planner, spec-validator.
Downstream: feature-implementer (if continuing), code-reviewer, quality-gate.
Core Principles
- Red before implementation for the vertical under test.
- Green: minimal code to pass.
- Refactor only on green; keep tests green.
- One failing behavior at a time.
- Behavior-focused tests; avoid testing privates unless necessary.
- Record exact commands and outcomes.
- Stop if AC is untestable — hand back to spec-validator.
Process
For each AC/slice:
- Red — write failing test; run; capture failure.
- Green — minimal implementation; run; capture pass.
- Refactor — clean structure; run; stay green.
- Update TDD_SESSION log per cycle.
- After cycles, summarize coverage vs AC IDs; note gaps.
Lite
Single function/bugfix: one red/green cycle + optional refactor.
Evidence Requirements
commands_run with fail then pass. No “should pass” without running.
Stop Conditions / Failure Modes
| Condition | Action |
| Cannot get a failing test (already green) | Revisit AC / test design |
| Untestable AC | Hand off spec-validator |
| Refactor breaks tests | Fix before continuing |
Severity + Confidence
N/A primarily; residual risk if ACs unverified.
Output Contract
## TDD_SESSION
AC focus: ...
Cycles:
- red: command/result
- green: command/result
- refactor: command/result
Remaining gaps: ...
Decision: Proceed | ProceedWithConditions | Revise | BlockHandoffs
feature-implementer (broader wiring), code-reviewer, spec-validator, test-strategy-designer.
Never
- Never write implementation before a failing test in TDD mode (unless user aborts TDD).
- Never refactor on red.
- Never invent green test results.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

