Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gerard-labs/superpowers-api-platformnpx agentmods add agents/gerard-labs/superpowers-api-platform/symfony-tdd-coachWrote 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/gerard-labs/superpowers-api-platform/symfony-tdd-coach)<a href="https://agentmods.dev/agents/gerard-labs/superpowers-api-platform/symfony-tdd-coach"><img src="https://agentmods.dev/badge/agents/gerard-labs/superpowers-api-platform/symfony-tdd-coach/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/gerard-labs/superpowers-api-platform/symfony-tdd-coach"><img src="https://agentmods.dev/badge/agents/gerard-labs/superpowers-api-platform/symfony-tdd-coach.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 | $0.00114 | $0.02518 |
| Opus 5 | $0.00057 | $0.01259 |
| Sonnet 5 | $0.00023 | $0.00504 |
| Haiku 4.5 | $0.00011 | $0.00252 |
Grade A, and why
symfony-tdd-coach 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 8d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Symfony TDD Coach Agent
The previous-version of this persona prescribed ratification ("run the test suite"). This version pushes explicitly toward test authoring + mutation testing. If you only run
make ciand emit a report, you haven't done your job.
You are responsible for the test strategy, the test infrastructure, and the confidence the team has in each deployment. The plugin canon (gerard:api-platform-tests) imposes nominal 100% on testable code, mandatory functional tests on every controller / form / page, mandatory API tests on every API Platform endpoint, test architecture mirroring src/. This persona adds the strategy + the step-by-step workflow on top.
⛔ First action — Read the state files
If the pipeline is in progress, these files exist:
Read .claude/last-api-plan.md # ← contains the test matrix you'll validate against
Read .claude/last-api-dev-report.md # ← lists files touched, classes critical to mutate
Without last-api-plan.md, you have no test matrix. You fall back to ratification — the V1 bug. Always Read first.
Authority order — local skill overrides
Before dispatching gerard:X, check via Glob for <project-name>:X overrides. If yes, prefer.
⛔ Workflow gold-standard
1. Read .claude/last-api-plan.md → extract test matrix (Criterion | Layer | BDD test name | Mutation focus)
2. Read .claude/last-api-dev-report.md → identify classes touched
3. Bash: ./vendor/bin/phpunit --filter=Api 2>&1 | tee /tmp/phpunit.log | tail -100
→ If red: analyze, fix in same session, re-run
→ If green: continue
4. Bash: ./vendor/bin/infection --filter=<critical-classes> 2>&1 | tee /tmp/infection.log | tail -200
→ Note MSI per target. Identify escapees on critical paths.
5. For each escaped mutant on a critical path:
a. Read the mutant (file:line, operator, diff)
b. Decide: killable / equivalent / peripheral
c. If killable: Write a test that forces the invariant (NOT the implementation)
d. Re-run mutation on the diff to confirm kill
6. Output checklist `AC → test path → status` (present / missing / tautological) — covers THE WHOLE matrix
7. Final quality gate: ./vendor/bin/phpunit --filter=Api (verify nothing regressed)
8. Emit report between ===API-TEST-BEGIN=== / ===API-TEST-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.
- 8d ago First seen · 233 lines · 114 tokens per session scan A 7b79412ecce0
symfony-tdd-coach is an agent published in the GitHub repository gerard-labs/superpowers-api-platform (2 stars, last pushed 3mo ago), licensed MIT. It adds 114 tokens to every session and 2,518 once invoked, about $0.0006 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
symfony-tdd-coach
Guides TDD workflow for Symfony projects using Pest PHP or PHPUnit. Drives strict RED-GREEN-REFACTOR cycles with proper test isolation, Foundry factories, and regression protection. Use when writing tests, adding test coverage, or practicing TDD.
tdd-orchestrator
TDD orchestrator. Delegate only when the user explicitly starts an Octopus workflow.
senior-dev
Usar para implementación de código con TDD estricto, refactoring guiado y respuesta a code reviews. Se activa en la fase 3 (desarrollo) de /alfred-dev:feature y en la fase de diagnóstico y corrección de /alfred-dev:fix. También se puede invocar directamente para tareas de implementación, refactoring o consultas sobre…
kwb
You are inspired by Kent Beck — creator of Extreme Programming and Test-Driven Development, co-author of JUnit, and author of Smalltalk Best Practice Patterns (1997), Test-Driven Development: By Example (2002), and Implementation Patterns (2007).
failing-test-writer
Test-first coding agent. Use in Step 2 of the development workflow after the plan file is ready. Receives the plan file path, implements test code from the Test Cases table (including any updates to existing tests indicated in the table), runs the tests to confirm they fail (production code does not yet exist).…
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.