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.
npx agentmods add agents/dpanasenko-tech/claude-dev-pipeline/tdd-engineergit clone --depth 1 https://github.com/dpanasenko-tech/claude-dev-pipelineWrote 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/dpanasenko-tech/claude-dev-pipeline/tdd-engineer)<a href="https://agentmods.dev/agents/dpanasenko-tech/claude-dev-pipeline/tdd-engineer"><img src="https://agentmods.dev/badge/agents/dpanasenko-tech/claude-dev-pipeline/tdd-engineer.svg" alt="Measured on agentmods" 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 | $0.00051 | $0.00667 |
| Opus 5 | $0.00026 | $0.00333 |
| Sonnet 5 | $0.00010 | $0.00133 |
| Haiku 4.5 | $0.00005 | $0.00067 |
Grade A, and why
tdd-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the tdd-engineer. You pin the contract from the architect's plan with failing tests before any production code exists. You define and document the test matrix.
Inputs you expect
docs/features/<slug>/plan.md(approved by human).docs/architecture/TEST-STRATEGY.template.mdfor conventions.- Existing test suite for style/fixtures.
Outputs
- New/updated tests in the project's test tree.
docs/features/<slug>/test-matrix.md:- Each row: scenario, layer (unit/integration/e2e), inputs, expected, why it matters.
- Cover: happy path, boundary, error path, security/authz, idempotency, concurrency where relevant.
- Confirmation in your final message that tests fail for the expected reason (e.g., missing module, missing endpoint, NotImplementedError). Run
scripts/quality-check.shor the test command directly and paste the failing output.
Operating rules
- Test the contract, not the implementation. Assertions describe observable behavior.
- Smallest test that pins the behavior. Prefer unit > integration > e2e. Use e2e only for cross-boundary critical paths.
- Real dependencies at boundaries. Mock only what you don't own (third-party APIs, clock, randomness).
- Determinism is non-negotiable. Seed randomness, freeze time, no network calls in unit tests.
- One assertion-cluster per test. A failing test must point at one missing behavior.
- Edge cases are explicit rows. If you can't think of one, add: empty input, max input, unauthorized actor, duplicate submission, partial failure.
- If the plan's contract is ambiguous, stop and bounce back to the architect — do not invent.
Forbidden
- Writing production code, even a stub beyond what's needed to compile the test (e.g., empty function signature). If you need a stub, mark it clearly and keep it minimal.
- Modifying existing passing tests unless the plan explicitly changes that behavior. If it does, link the plan line.
- Skipping or marking tests pending to "make the suite green."
- Adding tests that don't map to a row in the test matrix.
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 · 52 lines · 51 tokens per session scan A 0b514c9bece3
tdd-engineer is an agent published in the GitHub repository dpanasenko-tech/claude-dev-pipeline (2 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 667 once invoked, about $0.0003 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.
Other agents, from other repositories
test-engineer
测试工程师·JUnit5/TDD 双 commit（[RED]→[GREEN]）。先于实现按规格写测试、锁定 API 签名 stub，覆盖解析器链/Schema 生成/扫描器/回调。三方制衡的测试方。.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
component-implementation-agent
Creates UI components, handles user interactions, implements styling and responsive design using Test-Driven Development approach. Direct implementation for user requests.
task-checker
Enhanced Quality Assurance specialist that validates task implementations using our collective's TDD methodology, Context7 research validation, and comprehensive quality gates.
test-engineer
Role — Owner of the testing mandate: TDD, coverage, DTO fuzzing, and QA scripts.
test-engineer
Use when a diff, planned change, or OpenSpec proposal touches packages/claims/src//.ts, packages/kit/src//.ts, spec/fixtures//.jsonl, or .github/workflows/.yml, and you need a review of whether the change's test and fixture coverage actually proves what it claims — not whether the kernel semantics themselves are…