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 skills add jason21wc/ai-governance-mcp --skill test-suitegit clone --depth 1 https://github.com/jason21wc/ai-governance-mcpWrote 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/skills/jason21wc/ai-governance-mcp/test-suite)<a href="https://agentmods.dev/skills/jason21wc/ai-governance-mcp/test-suite"><img src="https://agentmods.dev/badge/skills/jason21wc/ai-governance-mcp/test-suite/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/skills/jason21wc/ai-governance-mcp/test-suite"><img src="https://agentmods.dev/badge/skills/jason21wc/ai-governance-mcp/test-suite.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 | $0.00128 | $0.00621 |
| Opus 5 | $0.00064 | $0.00311 |
| Sonnet 5 | $0.00026 | $0.00124 |
| Haiku 4.5 | $0.00013 | $0.00062 |
Grade A, and why
test-suite 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 11d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runtime Context
After the skill loads, inspect the branch, framework/test manifests, and existing test files with ordinary read-only calls. Derive the framework from the repository and treat an empty test corpus as a valid result.
Instructions
You are generating a test suite. Read procedure.md in this skill folder for the full 3-phase protocol.
Quick Start
-
Collect the Runtime Context above and determine the target. If the user specified a file, function, or module, use that. If they said "test this" after editing code, test the most recently modified files. If ambiguous, ask.
-
Read
procedure.mdfor the full protocol. -
Execute all three phases in order:
- Phase 1: Generate — read target code, detect framework, write test draft with error-path emphasis
- Phase 2: Verify — apply echo-chamber check, error-path balance, mutation mindset (non-skippable)
- Phase 3: Revise — fix any tests that failed verification, re-check until clean
-
Deliver the test file(s) with the self-check results summary.
Key Principles
- Echo-chamber check is non-negotiable. The #1 AI test failure mode: restating implementation logic in assertions. Every test must check a specification, not mirror the code.
- Error-path balance. AI systematically under-tests failures. For code with external inputs or side effects, error tests should match or exceed happy-path tests.
- Test behavior, not implementation. If a wrong implementation would still pass the test, the test is worthless. Rewrite it.
- Real dependencies by default. Only introduce test doubles when necessary (paid APIs, slow services, architectural boundaries). Mock smell: setup > 5 lines or > 2 mocked dependencies means the code has a testability problem.
What This Skill Does NOT Do
- Run tests — it generates them. Run them yourself or with your test runner.
- Review existing code — use
/code-reviewfor that. - Audit existing test coverage — planned for v2; for now, specify what to test.
- Manage CI/CD — out of scope.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 43 lines · 128 tokens per session scan A 07b7ede7f6c5
test-suite is a skill published in the GitHub repository jason21wc/ai-governance-mcp (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 128 tokens to every session and 621 once invoked, about $0.0006 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 skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.