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 patrick-fu/awesome-skills --skill build-verifiergit clone --depth 1 https://github.com/patrick-fu/awesome-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/patrick-fu/awesome-skills/build-verifier)<a href="https://agentmods.dev/skills/patrick-fu/awesome-skills/build-verifier"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/build-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/skills/patrick-fu/awesome-skills/build-verifier"><img src="https://agentmods.dev/badge/skills/patrick-fu/awesome-skills/build-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 | $0.00025 | $0.00500 |
| Opus 5.5 | $0.00010 | $0.00200 |
| Sonnet 5.5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
build-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 9d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Verifier
Produce a project-local verify-<app> that a fresh agent can execute. Reuse an
existing verifier and the project's conventions. Ordinary feature acceptance
uses that verifier.
Project knowledge
Make these properties executable with existing tools:
- Readiness: identify the correct build, instance, data and access; diagnose surprising failures before continuing.
- Drive: exercise public user paths and observe relevant state and side effects, including dry-run writes. Mock only an existing external-system boundary and mark the substituted behavior unverified.
- Evidence: retain actions and resulting state sufficient to prove behavior; confirm evidence remains readable after cleanup.
- Ownership: isolate scratch data, serialize drivers of a shared instance, and remove only this run's resources, including failed attempts. Preserve user data, borrowed instances and evidence.
Ground feature paths and success criteria in the repo. Cache hard-to-discover facts and gotchas; point to canonical commands. Document helper invocations and match their permissions. Split feature detail only when it improves navigation.
Create
For creation or changes to discovery and feedback, read Project skill. Seed grounded paths and run the generated instructions on one feature before handing them over. Distinguish mapped from live-verified paths.
Maintain
After a verification run, compare observed friction with the recipe and current source. Correct proven workflow drift or a missing reusable step. Clean runs, product failures and temporary environment blockers alone need no verifier edit; unresolved intent stays unresolved.
Keep automatic maintenance scoped to the encountered path and verifier-owned docs or helpers. Preserve intended expectations when product behavior fails; report the failure to the product task. Reconcile scoped paths and success criteria with current source and live evidence. Use the requested scope for broader audits; a full audit also checks for unmapped features.
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.
- 9d ago First seen · 61 lines · 25 tokens per session scan A 166c0b1132d3
build-verifier is a skill published in the GitHub repository patrick-fu/awesome-skills (69 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 500 once invoked, about $0.0001 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 2026-10-17.
Other skills, from other repositories
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.