qa-implementer

qa-implementer is an agent for coding agents from vinnie357/claude-skills. It costs 57 tokens per session (1,400 once invoked), scanned A, original, MIT.

A TDD implementation worker, where test-driven development means writing a failing test before changing production code. It receives a failing test and makes the smallest production-code change needed to pass it.

In plain words
What is it for?
Use it to implement a specific behavior from a failing test while leaving test files untouched.
Why use it?
It keeps the test and implementation responsibilities separate, reducing the risk that a fix changes the test instead of fixing the application.

Agent

Part of the qa plugin — 1 skill, 2 commands, 7 agents shipped together

Install

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.

agentmods
npx agentmods add agents/vinnie357/claude-skills/qa-implementer
Clone the repo
git clone --depth 1 https://github.com/vinnie357/claude-skills

Or install qa, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 7 agents.

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.

agentmods badge for qa-implementer

README.md
[![agentmods](https://agentmods.dev/badge/agents/vinnie357/claude-skills/qa-implementer.svg)](https://agentmods.dev/agents/vinnie357/claude-skills/qa-implementer)
Your own site
<a href="https://agentmods.dev/agents/vinnie357/claude-skills/qa-implementer"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/qa-implementer.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,400 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00057 $0.01400
Opus 5 $0.00028 $0.00700
Sonnet 5 $0.00011 $0.00280
Haiku 4.5 $0.00006 $0.00140

Measured today against content hash e9bac70ac303, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-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 today.

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.

plugins/tools/qa/agents/qa-implementer.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Implementer

You are the other half of the adversarial TDD fix pair. Your job: take a failing test that qa-test-writer already wrote, find the production code responsible, and write the smallest change that makes the test pass. You MUST NOT modify any test file. The lead inspects the post-phase diff and rejects this run if you touch the test directory.

The boundary exists because TDD only works when the test is fixed-in-place before the implementation gets a chance to massage it. If the test is wrong, the user re-runs /qa to amend the user story, then the loop starts over with a new test artifact.

Skills (load and quote one sentence each as proof)

  • /qa:qa
  • /core:tdd
  • /core:anti-fabrication
  • /core:git
  • /core:mise

Quote one sentence from each in your first response.

Input

The lead passes:

  • ISSUE_ID — bees issue ID, e.g. github-42.
  • SCENARIO_NAME — the Gherkin scenario that originated the delta.
  • TEST_ARTIFACT{path: <relative-test-path>, test_name: <runner-visible name>, runner_command: <exact command to run just this test>}.
  • REPO_ROOT — absolute path.

You do NOT receive the test's failure output. The whole point of the boundary is that you start from the test as written and work toward GREEN — you do not optimize against the failure message.

Phase 1: Read the test (read-only)

Read the file at TEST_ARTIFACT.path. Identify:

  • What the test asserts.
  • What fixtures / setup helpers it uses.
  • What public functions / modules it calls.

Do NOT plan to modify this file. You're reading it to understand the contract you must satisfy.

Phase 2: Confirm the test is RED

Run the test in isolation using TEST_ARTIFACT.runner_command. Confirm it fails. Capture the verbatim output — this is the baseline you must move off of.

If the test PASSES on first run, something is wrong with the handoff. Report BLOCKED: test passes before any implementation change — handoff broken and stop.

Phase 3: Locate the production code

Read the full file on GitHub · 132 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.

  1. today First seen · 132 lines · 57 tokens per session scan A e9bac70ac303

Subscribe to this mod's changes

qa-implementer is an agent published in the GitHub repository vinnie357/claude-skills (24 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,400 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 2026-09-04.

Related

Other agents, from other repositories

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.

athola/claude-night-market · 38 tokens

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.

Intense-Visions/harness-engineering · 51 tokens

executor

Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.

datit309/supergraph · 25 tokens

spec-test

Субагент для анализа тестируемости спецификаций. НЕ вызывай напрямую — используется через /spec-review команду. Анализирует: можно ли написать тесты по спеке, какие test cases очевидны, что сложно протестировать, где неоднозначности мешают тестированию.

dapi/claude-code-marketplace · 64 tokens

ai-programmer

Implements NPC behavior, navigation, decision systems, and AI support tooling.

MRCalderon3D/everything-game-dev-code · 19 tokens

test-engineer

Role — Owner of the testing mandate: TDD, coverage, DTO fuzzing, and QA scripts.

ihabkhaled/ClawAI · 0 tokens