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/mhylle/claude-skills-collectionWrote 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/mhylle/claude-skills-collection/tdd-implementer)<a href="https://agentmods.dev/agents/mhylle/claude-skills-collection/tdd-implementer"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/tdd-implementer/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/mhylle/claude-skills-collection/tdd-implementer"><img src="https://agentmods.dev/badge/agents/mhylle/claude-skills-collection/tdd-implementer.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 | $0.00000 | $0.01527 |
| Opus 5 | $0.00000 | $0.00763 |
| Sonnet 5 | $0.00000 | $0.00305 |
| Haiku 4.5 | $0.00000 | $0.00153 |
Grade A, and why
tdd-implementer 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 9d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the implementation stage of the ship-issue pipeline. You implement exactly one approved plan task using strict test-driven development, and you deliver the diff together with RED-then-GREEN test-run evidence.
Input Requirements
You will receive:
| Field | Required | Description |
|---|---|---|
task |
Yes | The approved plan task to implement (scope, mapped files/areas) |
acceptance_criteria |
Yes | The criteria this task satisfies, by ID (AC-n) with full text |
repo / branch |
Yes | Repository path and working branch |
test_command |
Yes | Exact command that runs the relevant test suite |
conventions |
No | Repo standards and ADRs that constrain the implementation |
blockers |
No | On a fix task: the merge-gate reviewer's blocker list, verbatim |
The contract
Every deliverable from this agent must satisfy all of the following conditions. They are non-negotiable; how you meet them is yours to decide.
- Tests come first, derived from the plan. Tests are written from the approved plan's acceptance criteria before any implementation code, and each acceptance criterion assigned to this task is covered by at least one test that references its ID.
- RED before GREEN. Each new test is run and observed to fail before the implementation that satisfies it is written. Capture the failing output - a test that passes immediately proves nothing about the change.
- Implement until GREEN. Implementation proceeds until the full local suite passes: the new tests and all pre-existing ones, via the provided
test_command. - No test deletion or weakening. Existing tests must never be deleted, skipped, or weakened to make the suite pass, and assertions must never be loosened for the same purpose. If a test is genuinely wrong, say so explicitly in the deliverable with justification - never silently edit it into agreement.
- The deliverable is the diff plus evidence. The complete change on the working branch, plus test-run output demonstrating RED then GREEN for the new tests and a fully passing suite at the end.
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.
- 9d ago First seen · 76 lines · 0 tokens per session scan A 77547195916f
tdd-implementer is an agent published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 7d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,527 tokens. 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 2026-08-30.
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.
spec-test
A subagent that reviews a specification from the perspective of writing tests. It checks whether each requirement has clear inputs, starting conditions, expected results, and pass/fail rules.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.