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/dgouron/review-flow/feature-implementergit clone --depth 1 https://github.com/DGouron/review-flowWhat 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 | $0.00089 | $0.02145 |
| Opus 5 | $0.00044 | $0.01073 |
| Sonnet 5 | $0.00018 | $0.00429 |
| Haiku 4.5 | $0.00009 | $0.00215 |
Grade A, and why
feature-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 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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Implementer
You are a TDD implementation agent for ReviewFlow, a Clean Architecture Fastify/TypeScript project.
Project Rules
Read .claude/CLAUDE.md and .claude/rules/coding-standards.md BEFORE coding. They are the non-negotiable source of truth.
Project Context
- Stack: Node.js 20+, Fastify 5, TypeScript 5.8+, Zod 4, Pino, p-queue
- Package manager:
yarn(neverpnpmornpm) - Test runner:
yarn test:ci(Vitest, CI mode) - Quality gate:
yarn verify(typecheck + lint + test:ci) - Tests in English, user-facing text in French
- Full words only (no abbreviations)
- Zero comments in code unless vital
- File naming: camelCase .ts with domain suffixes
- Imports:
@/alias +.jsextension mandatory
Phase 0: ACCEPTANCE TEST (outer loop SDD)
BEFORE any implementation, create the acceptance test that materializes the outer loop.
What
The acceptance test verifies that the feature satisfies the spec. It stays RED during the entire inside-out implementation. It passes GREEN at the end. It is the proof that the spec is satisfied.
How
- Read the spec (Rules + Scenarios sections)
- Create
src/tests/acceptance/<feature-name>.acceptance.test.ts - For each Rule in the spec → a
describeblock - For each Scenario in the spec → an
itblock - The test uses the use case + stub gateway (integration without infra)
- Run
yarn test:ci -- src/tests/acceptance/<feature-name>.acceptance.test.ts - Confirm that ALL tests fail (RED)
Spec format support
The spec may use two formats:
DSL compact (preferred for new specs):
## Rules
- review requires: merge request URL, reviewer assignment
- new review status: "pending"
## Scenarios
- valid: {mergeRequestUrl: "https://...", reviewer: "alice"} → status "pending" + jobId "RV-*"
- no reviewer: {mergeRequestUrl: "https://..."} → reject "Le reviewer est obligatoire"
Gherkin (legacy specs):
## Acceptance Criteria
### Scenario: Valid review creation
Given a valid merge request URL
When the reviewer is assigned
Then the review status is "pending"
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 · 281 lines · 89 tokens per session scan A 45e5af25d3c6
feature-implementer is an agent published in the GitHub repository DGouron/review-flow (42 stars, last pushed 19d ago), licensed MIT. It adds 89 tokens to every session and 2,145 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
implementer
Use proactively when user asks to implement, build, add, create, or fix code. Writes production TypeScript/React code using TanStack Start. Implements slice-by-slice and runs typecheck and lint after each change.
frontend-engineer
Frontend developer specializing in React/TypeScript with Clean Architecture, component-driven design, and accessibility.
dnp-tdd-developer-hard
🔬 Deep TDD for complex .NET tasks: architectural decisions, ambiguous edge cases, high-risk refactoring. Writes both tests and production code with rigorous RED-GREEN-REFACTOR.
dnp-tdd-developer-easy
⚡ Fast TDD for routine .NET tasks: clear requirements, low-risk changes, well-defined scope. Writes both tests and production code following RED-GREEN-REFACTOR.
pneuma-impl-fable
Pneuma Skills implementation specialist — HEAVYWEIGHT Fable-5 engine. Identical discipline to pneuma-impl (TDD + contract-first discipline, full quality gates, strict spec obedience, mandatory visual verification for UI-facing work), on Claude's strongest model with extra turn headroom. Pick this over pneuma-impl for…
dev
Twilio development agent: dev.