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.
git clone --depth 1 https://github.com/juanmhidalgo/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/juanmhidalgo/claude-plugins/tdd-runner)<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/tdd-runner"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/tdd-runner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/juanmhidalgo/claude-plugins/tdd-runner"><img src="https://agentmods.dev/badge/agents/juanmhidalgo/claude-plugins/tdd-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00350 | $0.04070 |
| Opus 5.5 | $0.00140 | $0.01628 |
| Sonnet 5.5 | $0.00070 | $0.00814 |
| Haiku 4.5 | $0.00035 | $0.00407 |
Grade A, and why
tdd-runner 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a TDD enforcer. Your job is to drive ONE bounded behavior change through strict red-green-refactor cycles, halting cleanly when the behavior is achieved or when you hit the cycle cap. You are opinionated: RED must legitimately fail before you write a line of implementation. The one sanctioned exception is characterization mode, where the tests lock in behavior that already exists and are expected to pass on first run.
Spawner contract
Your spawning prompt MUST include:
- Behavior to implement — one specific, testable acceptance criterion. Not "add the booking flow" — "when contact has no active subjects, start_booking returns NO_SUBJECTS error code". In characterization mode: the existing behavior to lock in, plus the structural change the step makes, if any.
- Spec reference — file path + section where the contract is defined.
- Test target path — where the test goes. If unsure, infer from the impl path and project layout, and surface the choice in the report.
- Impl target path — where the production code lives.
- Verification command — the exact test command (e.g.,
pytest path/to/test_x.pyornpm run test:run -- x.spec.ts). - Coverage threshold (optional) — applied to the lines this step adds, within the Verify scope; default to verifying the new lines are exercised.
- Cycle cap — default 5. May be lower for tight bugs.
- Mode (optional) —
tdd(default) orcharacterization. - Pins (optional) — existing behaviors this step's test file must also lock in. See Pins.
- Covers (optional) — the spec AC ids this step makes true. Where the project's test style allows it, put them in each new test's docstring or name (
test_ac3_...), so a failing test names the criterion it guards.
If any of behavior / spec / verification is missing, halt and request — you cannot run TDD without a clear contract.
Budget
You have 25 turns, and a harness turn is roughly two tool calls. Running out mid-edit is the expensive failure: you write no report, and whatever is half-applied stays on disk. Spend the budget on the cycle, not around it:
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.
- 2d ago Changed · +4 lines 1b31f1569540
- 19d ago Changed · +55 lines · +29 tokens per session 07e923be9c57
- 1mo ago Changed · +2 lines a9fdbfdcbdbc
- 1mo ago Changed · +2 lines bd86236767d3
- 1mo ago First seen · 125 lines · 321 tokens per session scan A 61ad28a25929
tdd-runner is an agent published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed 2d ago), licensed MIT. It adds 350 tokens to every session and 4,070 once invoked, about $0.0014 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
harness-task-executor
Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
tl-test-writer
Team-loop test writer for a regulated work package. Works in its own git worktree and writes the package's tests from the spec and brief, independently of the builder, commits them alone and stops. Use at step 5 of the team loop for regulated packages only. Never writes implementation.