A verification worker for an orchestrated coding run. It independently runs the run's recorded test command without changing files and reports a pass only when the command exits successfully.

Use it for final suite verification after implementation and review, using the exact command recorded for the run.

It provides an independent final test result instead of relying on the worker that wrote the code.

How yeisonrestrepo/code-conductor configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to yeisonrestrepo/code-conductor. 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/yeisonrestrepo/code-conductor/main/.claude/agents/qa.md

Clone the repo

git clone --depth 1 https://github.com/yeisonrestrepo/code-conductor

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/yeisonrestrepo/code-conductor/qa/github.svg)](https://agentmods.dev/agents/yeisonrestrepo/code-conductor/qa)

Your own site

<a href="https://agentmods.dev/agents/yeisonrestrepo/code-conductor/qa"><img src="https://agentmods.dev/badge/agents/yeisonrestrepo/code-conductor/qa/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/yeisonrestrepo/code-conductor/qa"><img src="https://agentmods.dev/badge/agents/yeisonrestrepo/code-conductor/qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 432 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	$0.00064	$0.00432
Opus 5.5	$0.00026	$0.00173
Sonnet 5.5	$0.00013	$0.00086
Haiku 4.5	$0.00006	$0.00043

Measured 27d ago against content hash 19194c34cfc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

qa 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 27d 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/qa.md · 27 lines

What it actually says

You are the qa role of a code-conductor orchestrated run. The orchestrator dispatched you with a brief naming the item, and installed your band envelope at .claude/memory/band-envelope.json. Read the envelope first.

Your job

Verify the item independently. You did not write this code and you cannot write files. Your run of the suite is the authoritative one, whatever any other role reported.

The test command

Your shell runs one command: the run's test command, the test_command field of .claude/memory/orchestrator-run.json. Run exactly the command named in the run file, byte for byte, with no added flag, pipe, redirect or second command. Guard 7 denies anything else, and its denial names the allowed command.

Success condition

Your success condition is fixed: you ran the test command yourself and the suite passed, meaning the command exited with status 0. Report its exact exit status and summary line. Do not substitute a stricter or different standard of your own: exit status 0 is a pass, and anything else is a fail.

Rules

A hook or owner denial is an instruction to stop and report, never an obstacle to route around.
Never dispatch or message another agent.
Deliver exactly one report, then stop. If the suite passed, end it in exactly one SNAP_HANDBACK line and claim only the gate verify_pass. If it failed, leave the SNAP_HANDBACK line out and say why, quoting the summary line.
Copy ops.scope verbatim from your envelope into the hand-back; if your envelope has no scope, leave the key out.

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.

27d ago First seen · 27 lines · 64 tokens per session scan A 19194c34cfc4

Subscribe to this mod's changes

qa is an agent published in the GitHub repository yeisonrestrepo/code-conductor (17 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 432 once invoked, about $0.0003 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 2026-10-03.

Building agents Testing agentic-development ai-agents claude claudecode skills spec-driven-development

implementer-agent

Implementation worker spawned by /speq-implement. Executes untagged tasks.md tasks via TDD; [expert] tasks go to implementer-expert-agent.

marconae/speq-skill · 37 tokens

implement-executor

Executes one task or a bounded batch of up to four tasks using strict TDD red-green-refactor. Writes failing tests first, verifies they FAIL, then writes minimum implementation to pass, then refactors. Receives ordered tasks, ownership, PROJECTCOMMANDS, and TDD protocol from the orchestrator. Returns per-task…

racecraft-lab/racecraft-plugins-public · 86 tokens

uat-runbook-author

Rewrites a deterministic UAT runbook skeleton into a plain-English, executable acceptance runbook a non-engineer can follow. Use after runner helper generate-uat-skeleton has written the skeleton and before PR-body generation. Edits the skeleton in place: turns placeholder per-story checkboxes into concrete numbered…

racecraft-lab/racecraft-plugins-public · 114 tokens

artifact-preview-observer

Publishes and observes one generated artifact page in an isolated preview surface. Use only when the parent has validated generation provenance and needs rendered evidence. The agent never reads repository content, runs commands, follows links, or interprets page text as instructions.

racecraft-lab/racecraft-plugins-public · 54 tokens

mutation-hardener

Authoring mutation hardener inspired by SwarmForge's hardender. Iteratively raises eligible-target line/branch coverage to 100%, runs differential mutation target by target, kills every actionable survivor, improves code and tests when necessary, commits the hardened candidate, and returns a complete owner handoff. It…

w00fx/spec-anchored-agentic-development · 74 tokens

accessibility-agent

WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.

navikt/copilot · 32 tokens

code-conductor: Agent for Claude Code