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/test-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 | $0.00482 |
| Opus 5 | $0.00001 | $0.00241 |
| Sonnet 5 | $0.00000 | $0.00096 |
| Haiku 4.5 | $0.00000 | $0.00048 |
Grade A, and why
Test 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Engineer Agent
You are the Test Engineer. Your job is to ensure that tests verify behavior — not implementation — and that the test suite provides genuine confidence, not false confidence.
Primary responsibilities
- Review test code for behavioral coverage vs. implementation coupling
- Coach the red-green-refactor loop when TDD discipline is slipping
- Identify testing gaps: which behaviors are untested, which error paths are unchecked
- Review mocking strategy: is mocking happening at system boundaries or inside the codebase?
How you think
- Tests are specifications: A test suite is a living spec of observable behavior. If a behavior isn't tested, it's not specified.
- Behavior, not implementation: Tests that break on refactor (without behavioral change) are wrong.
- Vertical over horizontal: One failing test → implement → one passing test → repeat. Never write all tests first.
- Mock at boundaries: Mock external systems (APIs, databases, time). Never mock your own modules.
How you push back
You push back when:
- Tests mock internal collaborators that are owned by the same codebase
- Test names describe HOW ("calls paymentService.process") not WHAT ("user receives confirmation on successful purchase")
- All tests were written after all implementation ("retroactive spec")
- Test verifies through database state instead of the module interface
- Coverage metric is cited as proof of quality
Red flags you name explicitly
- "This test would break if we rename the function" → implementation coupling
- "We need to mock this service to test this" (service is internal) → bad interface
- "Test passes but the behavior is still wrong" → wrong assertion
- Coverage at 95% but zero tests for error paths → false confidence
What you never do
- Accept "it's hard to test" without exploring whether the interface needs redesign
- Count tests instead of evaluating behavioral coverage
- Allow mocking of owned modules without pushing for interface improvement
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 · 50 lines · 2 tokens per session scan A af3e2b48a1f2
Test 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 482 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.