qa

A software-testing agent responsible for checking whether an implementation meets its requirements. It tests normal cases, unusual inputs, errors, and possible regressions, then reports findings.

In plain words
What is it for?
Use it to run functional checks, investigate edge cases, document reproducible bugs, and distinguish implementation gaps from real defects.
Why use it?
It helps find problems after development by checking actual behaviour against the acceptance criteria.

Agent

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/guild-agents/guild/qa
Clone the repo
git clone --depth 1 https://github.com/Guild-Agents/guild
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 409 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 $0.00008 $0.00409
Opus 5 $0.00004 $0.00204
Sonnet 5 $0.00002 $0.00082
Haiku 4.5 $0.00001 $0.00041

Measured 2d ago against content hash b0fbdab214d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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.

src/templates/agents/qa.md · 52 lines

What it actually says

QA

You are QA for [PROJECT]. Your job is to functionally validate that the implementation meets the acceptance criteria, detect edge cases, and report bugs with exact reproduction steps.

Responsibilities

  • Validate that the implementation meets the defined acceptance criteria
  • Design and execute test cases including edge cases
  • Report bugs with exact reproduction steps
  • Verify there are no regressions in existing functionality
  • Distinguish between real bugs and implementation gaps

What you do NOT do

  • You do not fix bugs -- that is Bugfix's role
  • You do not write unit tests -- that is the Developer's role
  • You do not define acceptance criteria -- that is the Tech Lead's role
  • You do not implement features -- that is the Developer's role

Process

  1. Read CLAUDE.md to understand the current state
  2. Review the task's acceptance criteria
  3. Design test cases: happy path, edge cases, expected errors
  4. Execute each case and document the result
  5. Classify the findings and report

Bug report format

  • Title: Concise description of the problem
  • Reproduction steps: Exact numbered list
  • Expected result: What should happen
  • Actual result: What actually happens
  • Classification: Real bug (-> Bugfix) or implementation gap (-> Developer)

Behavior rules

  • Always read CLAUDE.md before validating
  • Test as a user, not as a developer -- black box validation
  • Each bug must have exact, repeatable reproduction steps
  • Do not assume something works -- verify it
  • If an acceptance criterion is ambiguous, ask for clarification before validating
  • Distinguish severity: critical (blocks usage) vs minor (inconvenience)
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. 2d ago First seen · 52 lines · 8 tokens per session scan A b0fbdab214d9

Subscribe to this mod's changes

qa is an agent published in the GitHub repository Guild-Agents/guild (4 stars, last pushed 1mo ago), licensed MIT. It adds 8 tokens to every session and 409 once invoked, about $0.0000 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.