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 Ezra144israel/governed-agent-skills --skill test-verificationgit clone --depth 1 https://github.com/Ezra144israel/governed-agent-skillsWrote 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/ezra144israel/governed-agent-skills/test-verification)<a href="https://agentmods.dev/skills/ezra144israel/governed-agent-skills/test-verification"><img src="https://agentmods.dev/badge/skills/ezra144israel/governed-agent-skills/test-verification/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/ezra144israel/governed-agent-skills/test-verification"><img src="https://agentmods.dev/badge/skills/ezra144israel/governed-agent-skills/test-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00043 | $0.03326 |
| Opus 5 | $0.00022 | $0.01663 |
| Sonnet 5 | $0.00009 | $0.00665 |
| Haiku 4.5 | $0.00004 | $0.00333 |
Grade A, and why
test-verification 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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
test-verification/SKILL.md
Purpose
Use this skill to write, evaluate, and verify tests that prove behavior rather than implementation details.
Core Rule
Tests prove behavior through public seams, not implementation internals.
A test that breaks when you rename an internal variable without changing behavior is testing the wrong thing. A test that passes when the behavior is broken is worse than no test at all.
Vertical Slice Discipline
Write one test. Implement to pass it. Repeat.
For every behavior change with testable logic, write the smallest targeted test and observe it fail for the missing behavior before changing the implementation. Do not write a broad suite for imagined internals before learning from one vertical slice.
WRONG (horizontal):
RED: write all tests
GREEN: write all implementation
RIGHT (vertical):
RED → GREEN: one test → its implementation → repeat
For a behavior change in existing code:
diagnose → write targeted behavior test → observe RED → implement narrow behavior → observe GREEN
For an extraction or refactor intended to preserve current behavior:
diagnose current behavior → add focused characterization test → observe PASS
→ move logic without changing behavior → observe PASS
A characterization test is not speculative: it pins behavior already present at a durable seam before logic moves. If the slice also changes behavior, characterize the current behavior first, then use a separate observed RED for the behavior change.
Test Quality Checklist
Before accepting a test as complete:
[ ] Test describes behavior, not implementation details
[ ] Test uses a public seam: route, server action, query helper, or pure helper interface
[ ] Test would survive an internal refactor without changing
[ ] Code written is the minimum to pass the current test
[ ] No broad test suite speculates about unverified internal structure
[ ] Test covers at least one failure/rejection case, not just the happy path
[ ] For high-risk seams: failure path, wrong input, unauthorized access are covered
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.
- 3d ago Changed · -137 lines f104c6e641d8
- 4d ago Changed · +203 lines 2bfaf989f952
- 12d ago First seen · 297 lines · 43 tokens per session scan A 17dd8233c921
test-verification is a skill published in the GitHub repository Ezra144israel/governed-agent-skills (21 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 3,326 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
mantis-plan
Formulates a targeted defensive security reviewing plan based on the active threat model and historical learnings. Use when starting a security review campaign to map the codebase boundaries and generate a roadmap (workspace/plan.json). Don't use for executing code reviews, writing test scripts, or patching code.
mantis-summarize
Pre-processes the repository by generating security-focused summaries (mantis-summary.md) for each directory to make planning and research more efficient. Use when starting a review campaign to map the codebase before threat modeling and planning. Don't use for executing code reviews, writing test scripts, or patching…
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
codex-loop
Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.
codex-ab
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
056-design-avoid-breaking-changes
Use when you need to review a plan, OpenSpec change, specification, or implementation proposal for breaking-change risk across commands, skills, generated outputs, XML sources, README/docs, tests, CI, APIs, schemas, configuration, data, migration, and release guidance. This should trigger for requests such as Review…