ai-dev-operating-system: Skill for Claude Code

.claude/skills/verify-build-works/SKILL.md

verify-build-works is a skill for Claude Code from lglucas/ai-dev-operating-system. It costs 103 tokens per session (656 once invoked), scanned A, original, MIT.

A repeatable check that confirms a project still passes its basic code checks, builds, starts its development server, and loads its main user journey after a change.

In plain words
What is it for?
Run it after substantial edits, rollbacks, bug fixes, before commits and pull requests, and during release checks. It checks type errors, linting, the build, the running server, key UI or API paths, and— for UI—visible changes in a browser.
Why use it?
It catches broken builds, startup failures, and obvious regressions before code is committed, pushed, or released.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is lglucas/ai-dev-operating-system's own configuration. It tells Claude Code how to work on ai-dev-operating-system itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-dev-operating-system configures →

Part of the ai-dev-operating-system plugin — 28 skills, 11 commands, 12 agents, 1 hook shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to lglucas/ai-dev-operating-system. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lglucas/ai-dev-operating-system/main/.claude/skills/verify-build-works/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lglucas/ai-dev-operating-system

Made for: Claude Code.

Or install ai-dev-operating-system, the plugin that ships this one along with the rest of its 28 skills, 11 commands, 12 agents, 1 hook.

Wrote 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.

agentmods badge for verify-build-works

README.md
[![agentmods](https://agentmods.dev/badge/skills/lglucas/ai-dev-operating-system/verify-build-works/github.svg)](https://agentmods.dev/skills/lglucas/ai-dev-operating-system/verify-build-works)
Your own site
<a href="https://agentmods.dev/skills/lglucas/ai-dev-operating-system/verify-build-works"><img src="https://agentmods.dev/badge/skills/lglucas/ai-dev-operating-system/verify-build-works/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.

agentmods 80×15 button for verify-build-works

Your own site · 80×15
<a href="https://agentmods.dev/skills/lglucas/ai-dev-operating-system/verify-build-works"><img src="https://agentmods.dev/badge/skills/lglucas/ai-dev-operating-system/verify-build-works.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 656 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00103 $0.00656
Opus 5 $0.00051 $0.00328
Sonnet 5 $0.00021 $0.00131
Haiku 4.5 $0.00010 $0.00066

Measured 9d ago against content hash 7f2ff4aa0d95, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

verify-build-works 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.

.claude/skills/verify-build-works/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify Build Works

When to run this skill

  • After applying a fix from bug-triage-agent.
  • After a rollback-safe operation.
  • Before any commit larger than a single docs change.
  • Before pushing to remote.
  • Before opening a PR.
  • Before tagging a release.

Verification ladder (run all that apply, in order)

Step 1 — Static checks (cheap, fast)

npm run typecheck
npm run lint

Stop and report at first failure. Don't continue if static layer is broken.

Step 2 — Build

npm run build

If build fails, hand off to bug-triage-agent.

Step 3 — Dev server starts

npm run dev

Confirm: process alive after 15s, HTTP 200 on http://localhost:<port>/, no fatal stderr.

Step 4 — Smoke test the golden path

For UI: load homepage + most critical authenticated page. For API: hit GET /health (or main endpoint) → 2xx.

npm run test:smoke   # if exists

Step 5 — Visual sanity (UI only)

  • Open the affected page in a real browser.
  • Confirm change is visible and not regressed.
  • Confirm at least one adjacent feature didn't break.

Output format

🧪 verify-build-works

Step 1 — Static checks:    ✅ typecheck OK, lint OK
Step 2 — Build:            ✅ build succeeded in 14s
Step 3 — Dev server:       ✅ ready on :3000, GET / → 200
Step 4 — Smoke tests:      ⚠️  no test:smoke script — skipped
Step 5 — Visual sanity:    ✅ home renders, login renders

Verdict: SAFE TO COMMIT.

If any step fails:

🧪 verify-build-works — ❌ FAIL at Step 2 (build)

Erro principal: src/features/auth/sign-in.ts(23,7): TS2322 ...

Próximo passo: invoco o bug-triage-agent.

Tone for the vibe coder

Antes de avisar que terminou, eu sempre testo. Se algo está quebrado, eu falo agora — não na frente do primeiro usuário.

Do NOT

  • Don't claim success without running the steps.
  • Don't suppress errors with || true.
  • Don't skip step 3 because "build passed".
  • Don't run destructive commands (DB migrations, file deletions) as part of verification.

Read the full file on GitHub · 93 lines

Changes

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.

  1. 9d ago First seen · 93 lines · 103 tokens per session scan A 7f2ff4aa0d95

Subscribe to this mod's changes

verify-build-works is a skill published in the GitHub repository lglucas/ai-dev-operating-system (11 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 656 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

test-quality

Write high-quality JUnit 5 tests with AssertJ assertions. Use when user says "add tests", "write tests", "improve test coverage", or when reviewing/creating test classes for Java code.

decebals/claude-code-java · 45 tokens

write-test-plan

Generate a QA/UAT test plan from product specifications and task definitions, covering acceptance testing, integration flows, and exploratory testing. Unit tests are out of scope (handled by write-unit-tests skill).

andresharpe/dotbot · 43 tokens

write-unit-tests

Write comprehensive unit tests with proper setup, assertions, and coverage of happy paths, edge cases, and error scenarios.

andresharpe/dotbot · 26 tokens

tech-preflight-dotnet

Verify .NET SDK compatibility, map project dependency graphs, and run baseline builds before code changes. Use when starting a new task, onboarding to a .NET solution, checking environment readiness, or diagnosing build failures from SDK mismatches.

andresharpe/dotbot · 52 tokens

audit-harness

Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.

alchemiststudiosDOTai/tunacode · 69 tokens

responsive-audit

Responsive audit: test pages at 375/768/1024px breakpoints via Playwright. Checks overflow, tap targets, sidebar collapse, text reflow, WCAG 1.4.4 zoom.

marcoguillermaz/Tierward · 0 tokens