What is feature-implementer?

An implementation agent for ReviewFlow, a Node.js and TypeScript application. It builds a planned feature using TDD, or test-driven development, where tests are written before the code they verify.

Use it to implement a ReviewFlow feature from its plan and specification, create an acceptance test, run the test and quality checks, and save an implementation report.

It provides a repeatable path from an approved specification to working code and checks the result across the application's layers.

How DGouron/review-flow configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to DGouron/review-flow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/DGouron/review-flow/master/.claude/agents/feature-implementer.md

Clone the repo

git clone --depth 1 https://github.com/DGouron/review-flow

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/dgouron/review-flow/feature-implementer/github.svg)](https://agentmods.dev/agents/dgouron/review-flow/feature-implementer)

Your own site

<a href="https://agentmods.dev/agents/dgouron/review-flow/feature-implementer"><img src="https://agentmods.dev/badge/agents/dgouron/review-flow/feature-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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/dgouron/review-flow/feature-implementer"><img src="https://agentmods.dev/badge/agents/dgouron/review-flow/feature-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,145 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00089	$0.02145
Opus 5.5	$0.00036	$0.00858
Sonnet 5.5	$0.00018	$0.00429
Haiku 4.5	$0.00009	$0.00215

Measured 2mo ago against content hash 45e5af25d3c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

.claude/agents/feature-implementer.md · 281 lines

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 (never pnpm or npm)
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 + .js extension 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 describe block
For each Scenario in the spec → an it block
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"

Read the full file on GitHub · 281 lines

Changes

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.

2mo ago First seen · 281 lines · 89 tokens per session scan A 45e5af25d3c6

Subscribe to this mod's changes

feature-implementer is an agent published in the GitHub repository DGouron/review-flow (44 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 2,145 once invoked, about $0.0004 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 2026-08-30.

Code review Planning Testing Writing and docs ai automation claude clean-architecture dashboard

consistency-qa

The brooks-lint verification gate. Runs npm run validate, npm test, and npm run evals, then cross-checks the documents the validator can't fully diff — the four plugin manifests, all six README badges, the docs landing-page JSON-LD, CHANGELOG, AGENTS.md, GEMINI.md, and the derived book count — for drift. Reports…

hyhmrright/brooks-lint · 123 tokens

eval-curator

Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…

hyhmrright/brooks-lint · 97 tokens

review-flow: Agent for Claude Code