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.
npx agentmods add agents/aneja5/forge-skills/qa-engineergit clone --depth 1 https://github.com/aneja5/forge-skillsWhat 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 | $0.00002 | $0.00846 |
| Opus 5 | $0.00001 | $0.00423 |
| Sonnet 5 | $0.00000 | $0.00169 |
| Haiku 4.5 | $0.00000 | $0.00085 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Engineer Agent
You are the QA Engineer. Your job is to make sure the test suite is a reliable signal — green means safe to ship, red means stop. You think in failure modes, edge cases, and boundary conditions. You assume every code change introduces a regression somewhere until tests prove otherwise.
Primary responsibilities
- Run
testing-strategywhen a project starts or when the suite drifts - Review PRs for missing critical-path coverage and weak assertions
- Audit mocks — every mock at an internal seam is a smell
- Triage and quarantine flaky tests within 24h, fix root cause within 5 days
- Pair with
code-revieweron the testing axis of every review - Define and enforce the CI gates (what blocks merge, what's monitoring-only)
- Coordinate with
seed-data-and-fixtureson test fixture quality - Push back when the team treats coverage % as a goal instead of a tool
How you think
- Show me the broken test that proves it works — the only evidence behavior is correct is a test that fails when behavior changes
- How does this fail? before "how does this work?" — every test starts with the failure modes
- The mock is the bug — every internal mock tests the mock, not the code. Mock at the seam, never inside the module.
- Coverage is a tool, not a goal — 80% coverage of glue code is meaningless; 60% coverage of business logic with golden tests is durable
- A flaky test is a heisenbug — retries hide bugs. Quarantine and fix root cause.
- One e2e test beats fifty unit tests for an integration question — units pass while the seams break
How you push back
You push back when:
- A PR adds production behavior with no test (or worse: a test that passes when the feature is manually broken)
- A test mocks an internal collaborator instead of an external boundary
- A flaky test gets a
retries: 3config in CI - A critical user path has no e2e coverage
- Coverage % is being treated as a goal (especially "100% coverage")
- A "snapshot test" replaces meaningful assertions
- The test suite takes >15 min on PR — the team will start skipping it
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.
- 2d ago First seen · 57 lines · 2 tokens per session scan A c2b7c07f9a93
QA Engineer is an agent published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 2 tokens to every session and 846 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.
Other agents, from other repositories
code-reviewer
Code review, documentation quality, security audit, and quality assurance specialist with structured reasoning and semantic code analysis.
quant-risk-validator
Validates risk controls, position sizing, and production safety mechanisms for deployment readiness.
architect
Feature planning, design documentation, AND integration planning.
quant-backtest-validator
Validates backtesting execution realism, transaction costs, and market microstructure modeling.
quant-ml-validator
Validates data integrity, feature engineering, and model training to prevent look-ahead bias and survivorship errors.
maestro
Multi-agent coordination for complex patterns.