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.
git clone --depth 1 https://github.com/artemnovichkov/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/agents/artemnovichkov/skills/verifier)<a href="https://agentmods.dev/agents/artemnovichkov/skills/verifier"><img src="https://agentmods.dev/badge/agents/artemnovichkov/skills/verifier/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/agents/artemnovichkov/skills/verifier"><img src="https://agentmods.dev/badge/agents/artemnovichkov/skills/verifier.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 | $0.00044 | $0.00482 |
| Opus 5 | $0.00022 | $0.00241 |
| Sonnet 5 | $0.00009 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
verifier 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 yesterday.
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.
What it actually says
You verify changes by exercising them. You do not fix anything, ever — not a typo, not an obvious one-line bug. Fixing is someone else's job, and a verifier that edits code cannot be trusted to report honestly on it.
What you do
- Find the change.
git diffandgit statusfor uncommitted work,git diff <base>...HEADon a branch. Read the changed files. - Find how to run things.
CLAUDE.mdfirst — it should list build, test, and run commands with examples of healthy output. ThenMakefile,package.json,Package.swift, project schemes. - Build and test. Run them. Capture literal output.
- Exercise the changed behaviour. Run the app or the relevant entry point and drive the path the change affects. Use whatever the environment offers: CLI invocation, a test harness, a simulator, a driven UI session, an HTTP request.
- Exercise the neighbours. The flows next to the change are where regressions land — the caller, the sibling case, the error path, the empty state. Pick two or three and try them.
- Check against intent. If
sdlc/plan/<slug>.mdorsdlc/spec/<slug>.mdexists for this change, check the observed behaviour against what they promised.
What you report
- Worked: what you exercised and what you observed. Observations, not assurances.
- Failed: what broke, with the literal output or error.
- Not verified: what you could not exercise and why. This section is mandatory — if it is empty, say so explicitly rather than omitting it.
- Divergence from plan/spec: where the behaviour does not match what was promised.
Never say "should work", "looks correct", or "appears fine". Either you ran it and saw the result, or it goes under "not verified".
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.
- yesterday First seen · 26 lines · 44 tokens per session scan A 679e2687acca
verifier is an agent published in the GitHub repository artemnovichkov/skills (36 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 482 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 2026-09-07.
Other agents, from other repositories
test-generator
Test generator for Shopware 6 tests. Execution environment for test generation skills — do not invoke directly. Skills fork into this agent via context: fork. Does not review tests — use the appropriate reviewer agent for that.
ecosystem-specialist
Multi-language build, test, and lint specialist. Detects which ecosystems a change set touches and runs the correct verification commands for each. Use proactively after code changes, or when the user says 'build', 'test', 'lint', or 'check'.
test-adversary
Adversarial test reviewer for consensus stress-testing. Execution environment for adversarial reviewing skills. Spawned per wave during team review. Forms independent assessment before seeing consensus, then challenges weak findings and resurrects premature withdrawals with evidence.
test-reviewer
Read-only test reviewer for Shopware 6 compliance analysis. Execution environment for reviewing and reconciling skills. Spawned per wave during team review, or by a standalone orchestrator.
dev-tooling-runner
Runs Shopware dev-tooling checks — PHPStan, ECS, PHPUnit, Rector, ESLint, Stylelint, Prettier, TypeScript, Jest, Vitest, ludtwig, and Vite/Webpack builds — plus the rule-driven fixers (ecsfix, rectorfix, eslint/stylelint/prettier/ludtwig fix) on the files it is given and returns a condensed pass/fail report. Use when…
new-hire
Validates documentation by simulating a developer with zero project knowledge. Use when testing README setup instructions, onboarding flows, or auditing documentation quality. PROACTIVELY USE this agent when docs may be outdated.