Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vraj-ai/skillsnpx agentmods add skills/vraj-ai/skills/verify-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/vraj-ai/skills/verify-skills)<a href="https://agentmods.dev/skills/vraj-ai/skills/verify-skills"><img src="https://agentmods.dev/badge/skills/vraj-ai/skills/verify-skills/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/vraj-ai/skills/verify-skills"><img src="https://agentmods.dev/badge/skills/vraj-ai/skills/verify-skills.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 | $0.00051 | $0.00376 |
| Opus 5.5 | $0.00020 | $0.00150 |
| Sonnet 5.5 | $0.00010 | $0.00075 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
verify-skills 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 5d 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.
What it actually says
Verify skills
This repository is a skill catalogue and a Node installer. Proof is the command output, not a summary of it. Run both commands from the repository root. A non-zero exit is a failure. Paste the validate-skills: line and the test summary into the PR body.
Feature map: frontmatter, cross-references.
Frontmatter and cross-references
node scripts/validate-skills.mjs
That command lints every catalogue skill and this skill:
- frontmatter parses, with
name,description, and, for catalogue skills, a semverversion namematches the directory- the description stays inside the routing budget
- every
dependenciesentry names a catalogue skill - every relative markdown link inside a skill directory resolves
- every skill named in
route's intent table is a catalogue skill - the body does not invoke a retired skill name
poteto-mode, interrogate, how, architect, and ketchup are pstack skills. They are not catalogue entries, so route must not list them as its destination.
Tests
npm test
npm test runs scripts/run-tests.mjs, including the structural and routing evals.
Evidence
Keep both summaries. If either command fails, verification failed. Do not start a server. There is nothing to tear down.
What ships with it
3 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.
- 5d ago First seen · 42 lines · 51 tokens per session scan A 5c909518bde2
verify-skills is a skill published in the GitHub repository vraj-ai/skills (4 stars, last pushed 6d ago), licensed MIT. It adds 51 tokens to every session and 376 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-15.
Other skills, from other repositories
test-failure-explorer
Import and query an existing Vitest 3.2 JSON report to explore test failures, file-level errors and original diagnostic evidence.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
skillshare-implement-feature
Implement a feature from a spec file or description using TDD workflow. Use this skill whenever the user asks to: add a new CLI command, implement a feature from a spec, build new functionality, add a flag, create a new internal package, or write Go code for skillshare. This skill enforces test-first development…
dd-triage-flaky-test
Load when investigating a specific flaky test. Gets history, failure pattern, and category, then recommends fix, quarantine, or escalate.