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 mthines/agent-skills --skill test-provenance-guardgit clone --depth 1 https://github.com/mthines/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/mthines/agent-skills/test-provenance-guard)<a href="https://agentmods.dev/skills/mthines/agent-skills/test-provenance-guard"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/test-provenance-guard/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/mthines/agent-skills/test-provenance-guard"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/test-provenance-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 70 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00207 | $0.02597 |
| Opus 5 | $0.00103 | $0.01299 |
| Sonnet 5 | $0.00041 | $0.00519 |
| Haiku 4.5 | $0.00021 | $0.00260 |
Grade A, and why
test-provenance-guard 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Provenance Guard
Catches the failure mode where a new test file re-implements the function it claims to test, then asserts against its own copy. The tests pass. The CI is green. The tests provide zero regression protection.
This skill detects that pattern and, when invoked autonomously, fixes it without user intervention.
This
SKILL.mdis a thin index. Detailed procedures live inrules/*.mdand load on demand. The case-study post-mortem and failure-mode taxonomy live inreferences/*.md.
Contents
- Inputs
- Workflow
- Quick Decision Flow
- Required Reading by Phase
- Output Contract
- Core Principles
- Anti-patterns
- Definition of Done
- Related Skills
Inputs
Parse $ARGUMENTS:
| Argument | Default | Meaning |
|---|---|---|
--diff |
off | Discover changed test files via git diff --name-only <base>...HEAD. |
--base <ref> |
main |
Base ref for --diff. |
<positional paths> |
— | Explicit test files to check (overrides --diff). |
--mode static|mutate|both |
both |
Which checks to run. |
--fix |
on when called from autonomous-workflow; off for slash invocation | Apply self-heal: extract logic, rewrite tests, re-verify. Gated by confidence(code) ≥ 90 % unless --no-confidence-gate is passed. |
--report-only |
off | Force off --fix even when called from autonomous-workflow. |
--no-confidence-gate |
off | Manual override — skip the pre-heal confidence gate. Reserved for human-driven slash invocations; never set inside the autonomous loop. |
What ships with it
5 files 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 · 235 lines · 207 tokens per session scan A f93d665a8368
test-provenance-guard is a skill published in the GitHub repository mthines/agent-skills (13 stars, last pushed yesterday), licensed MIT. It adds 207 tokens to every session and 2,597 once invoked, about $0.0010 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
raw-sql-querybuilder-testing-patterns
Guides Go services that use database/sql directly with a lightweight in-house query builder (not an ORM like GORM or a codegen tool like sqlc), including how to make repositories unit-testable via mock-generated interfaces. Use when writing or reviewing a repository method built on database/sql, adding a new…
tdd-workflow
Runs the full TDD workflow for a TypeScript/JavaScript feature — user journeys to test cases, unit tests (Jest/Vitest + Testing Library), API/integration tests, Playwright E2E, and a coverage gate wired into CI. Use when building a Next.js/React/Node feature end to end, not just a single unit test, or when asked to…
test-generation
Generates comprehensive unit, table-driven, and concurrency tests for a given function or module — happy paths, error paths, boundary values, and mocked dependencies — following Go and TypeScript idioms. Use when a function or file needs test coverage, a bug fix needs a regression test, or existing tests only cover…
testing-setup
Analyze and create a testing strategy for native Android apps - install testing libraries, set up test infrastructure, create harnesses for unit tests, UI tests, screenshot tests, and end-to-end tests.
migrate-xunit-to-xunit-v3
Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…
crap-score
Calculates CRAP (Change Risk Anti-Patterns) for a named .NET method, class, or file. USE FOR: explicit CRAP calculation or coverage-and-complexity risk within that named target, including which tests to prioritize. DO NOT USE FOR: project-wide coverage/CRAP, plateaus, or project-wide blockers/priorities…