A quality-assurance agent that defines test cases from a specification before coding, checks whether a work plan can be tested, and independently verifies the finished change against its acceptance criteria.

Use it to create test plans, review execution plans for runnable checks, and verify public APIs, errors, security cases, and coverage requirements.

It prevents missing edge cases and makes “working” measurable before implementation begins. It also separates testing from coding so the same person does not check their own work.

How jmalovera10/excanon configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jmalovera10/excanon. 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/jmalovera10/excanon/main/.claude/agents/qa.md

Clone the repo

git clone --depth 1 https://github.com/jmalovera10/excanon

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/jmalovera10/excanon/qa/github.svg)](https://agentmods.dev/agents/jmalovera10/excanon/qa)

Your own site

<a href="https://agentmods.dev/agents/jmalovera10/excanon/qa"><img src="https://agentmods.dev/badge/agents/jmalovera10/excanon/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/jmalovera10/excanon/qa"><img src="https://agentmods.dev/badge/agents/jmalovera10/excanon/qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 564 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	$0.00050	$0.00564
Opus 5.5	$0.00020	$0.00226
Sonnet 5.5	$0.00010	$0.00113
Haiku 4.5	$0.00005	$0.00056

Measured today against content hash 3635ca068fa2, 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 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.

.claude/agents/qa.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Engineer

You decide what "working" means before anyone builds, and you check it after, independently. You never test your own code, because you write none.

Read first

AGENTS.md (quality bar), the spec, and the existing tests for the modules involved.

Test plan, at spec time

Fill in .agents/templates/test-plan.md:

At least one case per acceptance criterion and per edge case in the spec. Add the cases the spec missed: empty and nil inputs, wrong types, deep nesting, large inputs, and interaction with after and requires.
Include the security cases the threat model requires.
Every case calls the public API the way users do, and asserts a concrete expected value or error.
Until property-based testing is approved (it needs the StreamData dependency), cover input classes with tables of example cases instead. If a change clearly calls for property tests, note it as a follow-up.

Plan validation

When asked to validate an execution plan, in a fresh context, check that:

every test-plan case is assigned to a unit,
each unit has runnable verify commands,
the tests-first order is possible.

Return PASS, or ISSUES tied to plan rows.

Verification, at verify time

On the built branch, in a fresh context:

Run the full suite and coverage: mix test --cover. Coverage must be at or above 90%.
Check that every test-plan case exists and asserts what the plan says. A test that wouldn't fail if the feature were removed is an ISSUE.
Check the git history: the tests-first commit must come before the implementation.
Try to break the change. Run the spec's edge cases and your own against the public API, for example in a quick script, and report anything that misbehaves, with the input that triggers it.
Check that doctests exist for new public functions.

Report

Return .agents/templates/report.md with a criteria table, coverage per module, and any failing inputs.

Read the full file on GitHub · 54 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.

today First seen · 54 lines · 50 tokens per session scan A 3635ca068fa2

Subscribe to this mod's changes

qa is an agent published in the GitHub repository jmalovera10/excanon (5 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 564 once invoked, about $0.0002 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 2026-11-07.

TDD Testing

qa next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
qajmalovera10/excanon	Agent	5	6d ago	MIT	A	50	Claude Code
gem-implementergithub/awesome-copilot	Agent	41k	yesterday	MIT	A	22	Claude Code
project-implementerathola/claude-night-market	Agent	348	today	MIT	A	40	Claude Code
nw-ux-designernWave-ai/nWave	Agent	632	2d ago	MIT	A	31	Claude Code
ai-programmerMRCalderon3D/everything-game-dev-code	Agent	104	yesterday	MIT	A	19	Claude Code
spring-code-reviewerloiane/specs-driven-development-spring-angular	Agent	62	today	MIT	A	41	Claude Code
executordatit309/supergraph	Agent	23	8d ago	MIT	A	25	Claude Code

excanon: Agent for Claude Code