Borrowing it
Nothing to install: this file belongs to Robiton/notebooklm-mcp-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Robiton/notebooklm-mcp-cli/main/.agents/skills/verify/SKILL.mdgit clone --depth 1 https://github.com/Robiton/notebooklm-mcp-cliWrote 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/robiton/notebooklm-mcp-cli/verify)<a href="https://agentmods.dev/skills/robiton/notebooklm-mcp-cli/verify"><img src="https://agentmods.dev/badge/skills/robiton/notebooklm-mcp-cli/verify/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/robiton/notebooklm-mcp-cli/verify"><img src="https://agentmods.dev/badge/skills/robiton/notebooklm-mcp-cli/verify.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 | $0.00096 | $0.00956 |
| Opus 5.5 | $0.00038 | $0.00382 |
| Sonnet 5.5 | $0.00019 | $0.00191 |
| Haiku 4.5 | $0.00010 | $0.00096 |
Grade A, and why
verify 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 12d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify
A verification pass for work that is about to be called done. "It ran" is not verification —
this skill checks the claim, at the right layer, with evidence, and reports calibrated.
It is the invocable form of ai/PLANNING.md → Verification; that file is the source of truth.
The pass — run every step
1. Restate the claims
List what "done" is claiming, explicitly. One line each. ("The parser handles quoted commas." "The README matches the new flags." "All 14 call sites were updated.") If a claim can't be stated, it can't be verified — go back and scope it.
2. Verify each claim at its own layer
- If the claim is "the output is correct" — look at the output, not the exit code.
- If the claim is "the page renders" — render the page, not just the build.
- If the claim is "N things were changed" — count them.
- Exit code 0, "it compiles," and "the diff looks right" only prove the layer below the claim.
3. Use evidence you didn't generate
Re-open the file that was written. Run the code or its tests. Diff before against after. Screenshot and read the screenshot. Intention is not evidence; observation is.
4. Sample the tails
Check the first item, the last item, and the weirdest item — empty input, unicode, the boundary value. Happy-path spot checks hide the failures that matter.
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.
- 12d ago First seen · 82 lines · 96 tokens per session scan A 96770a0d061c
verify is a skill published in the GitHub repository Robiton/notebooklm-mcp-cli (0 stars, last pushed 5d ago), licensed MIT. It adds 96 tokens to every session and 956 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other skills, from other repositories
verify-cli
Run smoke tests against the mpak CLI to verify all commands work correctly before publishing a new release.
od-code-migration
Default reference pipeline for the code-migration taskKind — code-import → design-extract → token-map → rewrite-plan → patch-edit ↔ build-test devloop → diff-review → handoff.
live-audit
Audit steam-games-mcp — build/test/lint gate, live MCP tool edge-case sweep (input validation, SteamID64/vanity/appid edge cases, key-gating), and source-level code review. Use when asked to test/audit the published or just-fixed steam-games-mcp package, hunt for bugs/edge cases, or repeat "the same kind of testing as…
prompt-check
Live-test every MCP Prompt in src/tools/prompts.ts through the real MCP protocol (not a static read) across every argument combination. Use when a prompt is added or its argument-handling logic changes, or as part of a live-audit pass.
vue-component-testing
Applies the three-tier test taxonomy for Vue 3 applications: writes unit tests for composables and Pinia stores with Vitest, component tests for behaviour and user interactions with @testing-library/vue, and acceptance tests for full user flows with Playwright. Ensures tests focus on observable behaviour, not…
next-application-structure
Establishes or reviews directory layout, server/client boundaries, routing, data-fetching strategy, and testing structure for Next.js 14+ App Router TypeScript applications. Invoked when the user asks to structure a Next app, set App Router conventions, or review architecture for React parity.