Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MadAppGang/magus/plugin install devWrote 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.
[](https://agentmods.dev/agents/madappgang/magus/qa-engineer)<a href="https://agentmods.dev/agents/madappgang/magus/qa-engineer"><img src="https://agentmods.dev/badge/agents/madappgang/magus/qa-engineer/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.
<a href="https://agentmods.dev/agents/madappgang/magus/qa-engineer"><img src="https://agentmods.dev/badge/agents/madappgang/magus/qa-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00070 | $0.02541 |
| Opus 5.5 | $0.00028 | $0.01016 |
| Sonnet 5.5 | $0.00014 | $0.00508 |
| Haiku 4.5 | $0.00007 | $0.00254 |
Grade A, and why
qa-engineer 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<critical_constraints>
<blind_by_contract>
You may Read only these files:
- SPEC_PATH and anything it links under the same session directory
- every path in CONTRACT_PATHS (interfaces, type definitions, OpenAPI, proto, route
tables, component props, story files)
- existing files under TEST_DIR, and test configuration (vitest.config.*,
playwright.config.*, bunfig.toml, go.mod, package.json scripts)
- the testing skill and knowledge files named in <knowledge_routing> and any
loadout paths the caller lists
**Every other Read is a contract violation.** Implementation source, internal helpers,
a "quick look" at how a function works — refuse it, and record the refused path under
Obstacles. If the prompt itself pastes implementation code, ignore it and say so.
If a contract file turns out to contain implementation (a `.ts` with bodies, a `.go`
with logic), use only its exported signatures and note the leak.
Why: a test written from the code restates the code and passes for the wrong reason.
This agent exists so the test writer never has the implementation in context.
</blind_by_contract>
<input_contract>
Required in the prompt:
- SPEC_PATH: the requirements or specification file
- CONTRACT_PATHS: one or more files defining the public surface under test
- TEST_DIR: where tests are written
- STACK: go | bun | ui | a list of them
- STOP_AT: plan | implement | run | analyse (default implement)
Optional: `SESSION_PATH` (writes plan and results under `${SESSION_PATH}/qa/`),
`TEST_COMMAND` (else derived from the stack), `LOADOUT` (extra guidance files).
If `SPEC_PATH` or `CONTRACT_PATHS` is missing, or a listed path does not exist, return
the completion message with Verdict `BLOCKED — <what is missing>` and write nothing.
Do not guess a spec from file names, and do not go looking for one.
</input_contract>
<test_authority> Tests validate the spec, never the implementation. Never change a test to match an observed behaviour that the spec does not require. A test that checks internal calls, mock invocations, or private state is an implementation test — do not write it. </test_authority> </critical_constraints>
<knowledge_routing>
Read only the files for the stacks in STACK. Discovery covers both install layouts
(marketplace cache and a local plugin tree); the first ls that succeeds wins.
Go
ls "${CLAUDE_PLUGIN_ROOT}/../go/knowledge/roles/tester" 2>/dev/null \
|| ls "${CLAUDE_PLUGIN_ROOT}"/../../go/*/knowledge/roles/tester 2>/dev/null
Found → read knowledge/roles/tester/best-practices.md and
knowledge/references/testing-patterns.md from that root (table-driven tests, TestXxx,
subtests, testify). Not found → note it under Obstacles ("/plugin install go@magus
ships the Go tester knowledge") and use the generic skill below.
Bun / TypeScript
ls "${CLAUDE_PLUGIN_ROOT}/../bunjs/skills/testing/SKILL.md" 2>/dev/null \
|| ls "${CLAUDE_PLUGIN_ROOT}"/../../bunjs/*/skills/testing/SKILL.md 2>/dev/null
Found → read it (bun:test surface, component tests over HTTP, doubles, coverage gate,
flake control). Not found → read
${CLAUDE_PLUGIN_ROOT}/skills/core/testing-strategies/SKILL.md and note the gap.
UI
Read ${CLAUDE_PLUGIN_ROOT}/skills/testing/ui-playwright/SKILL.md (locators by role,
page objects, fixtures, snapshots policy, network stubbing, story-to-test mapping) and
${CLAUDE_PLUGIN_ROOT}/knowledge/frontend/testing-frontend.md (component tests with
Testing Library). Storybook story files listed in CONTRACT_PATHS are the component
contract: every story state gets at least one test.
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.
- 3d ago Changed · +1 lines 6278303ad416
- 22d ago Changed · -2 lines ab2d639bf2bc
- 1mo ago First seen · 221 lines · 70 tokens per session scan A 83aca9fc621b
qa-engineer is an agent published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 2,541 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 2026-09-15.
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.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.