A test-first workflow for fixing bugs and reorganizing code. TDD means writing a test before the code change; a refactor changes structure without intending to change behavior.

Use bugfix mode for broken behavior and refactor mode for structure-only changes, then run the full checks: TypeScript compilation, tests, and linting.

It catches regressions by recording the expected behavior first and requiring tests, type checks, and linting to stay passing throughout the work.

test-loop — Skill by ao92265

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/ao92265/claude-code-playbook/test-loop

Any agent

npx skills add ao92265/claude-code-playbook --skill test-loop

Clone the repo

git clone --depth 1 https://github.com/ao92265/claude-code-playbook

Made for: Claude Code, Codex.

Or install playbook, the plugin that ships this one along with the rest of its 49 skills, 4 hooks.

Per session 152 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,261 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5	$0.00152	$0.01261
Opus 5	$0.00076	$0.00630
Sonnet 5	$0.00030	$0.00252
Haiku 4.5	$0.00015	$0.00126

Measured 3d ago against content hash 37b7ddb0156b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/test-loop/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Loop

One shared skeleton, two modes. Eliminates wrong-approach / buggy-first-pass friction and regression-on-refactor risk by forcing tests-before-code and CI parity before shipping.

Shared skeleton

Write tests (mode-specific — see below)
Commit the tests as a baseline, separate from any behavior change
Change code in small increments
Keep tests green after every increment
Full CI parity gate before PR: tsc -b && npm test && npm run lint

Mode selection

Bug report, issue number, "fix X is broken" → bugfix mode
Rename/restructure/extract/split/upgrade with no intended behavior change → refactor mode
Ambiguous → ask the user which one before writing anything

Mode: bugfix (failing-test-first)

Phase 1 — RED

Read issue, reproduce bug locally.
Write a test that captures expected behavior. Test MUST fail.
Run tsc -b && npm test — confirm the test fails for the RIGHT reason (not a compile error, not a wrong assertion).
Commit failing test alone: test: failing case for #N.

Phase 2 — GREEN

Implement MINIMAL fix. No refactor, no adjacent cleanup.
After every edit run full CI parity: tsc -b && npm test && npm run lint
Loop until all three pass. NEVER skip a step.
3 failed attempts → STOP, explain blocker, ask user.

Phase 3 — SHIP

Commit fix separate from test: fix: <one line> (#N).
git branch --show-current before push.
gh pr create referencing issue.

Mode: refactor (characterization-first)

For refactors with no intended behavior change: renaming/restructuring, splitting a god component, extracting a hook/util, deduping logic, migrating styles/theme without altering rendered output, or a contained library/version upgrade.

Not for: bug fixes (use bugfix mode above), feature adds, or a mechanical rename across files already covered by existing tests.

Step 1 — Identify target + capture surface

Ask the user (if not stated) for:

Target file/dir
Public surface to preserve: rendered output, network calls, exposed API, side effects

Read the full file on GitHub · 118 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago First seen · 118 lines · 152 tokens per session scan A 37b7ddb0156b

Subscribe to this mod's changes

test-loop is a skill published in the GitHub repository ao92265/claude-code-playbook (10 stars, last pushed 16d ago), licensed MIT. It adds 152 tokens to every session and 1,261 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

TDD Testing

agent-integration

Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last). For individual phases, use /agent-integration:research, /agent-integration:write-tests, or /agent-integration:implement. Use when the user says "integrate agent", "add agent…

entireio/cli · 89 tokens

engram-testing-coverage

TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.

Gentleman-Programming/engram · 25 tokens

code-assist

Guides implementation of code tasks using test-driven development in an Explore, Plan, Code, Commit workflow. Acts as a Technical Implementation Partner and TDD Coach — following existing patterns, avoiding over-engineering, and producing idiomatic, modern code.

mikeyobrien/ralph-orchestrator · 53 tokens

test-loop