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

.claude/skills/os-self-test/SKILL.md

os-self-test is a skill for Claude Code from lglucas/ai-dev-operating-system. It costs 114 tokens per session (853 once invoked), scanned A, original, MIT.

A self-test for an AI development setup inside a project. It checks whether its standard files, links, registries, hooks, logs, and ignore rules agree with one another.

In plain words
What is it for?
Run it to find missing project files, invalid frontmatter, broken Markdown links, registry mismatches, unindexed session logs, disconnected hooks, and missing entries in gitignore.
Why use it?
It replaces a checklist that people may forget with a repeatable verification that can run after structural changes or in continuous integration.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

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 →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/os-self-test.js.

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/os-self-test/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 os-self-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/lglucas/ai-dev-operating-system/os-self-test.svg)](https://agentmods.dev/skills/lglucas/ai-dev-operating-system/os-self-test)
Your own site
<a href="https://agentmods.dev/skills/lglucas/ai-dev-operating-system/os-self-test"><img src="https://agentmods.dev/badge/skills/lglucas/ai-dev-operating-system/os-self-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 853 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 $0.00114 $0.00853
Opus 5 $0.00057 $0.00426
Sonnet 5 $0.00023 $0.00171
Haiku 4.5 $0.00011 $0.00085

Measured 7d ago against content hash d7bfd1c35d44, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

os-self-test 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 7d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/os-self-test/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OS Self-Test

Rode o script

node scripts/os-self-test.js

É a verificação inteira. Exit 0 = coerente, exit 1 = pelo menos um erro.

Isto era um checklist manual dentro deste arquivo, e esse era o problema. Verificação que depende de alguém lembrar não é verificação — três session-logs (2026-04-30, 2026-05-09, 2026-08-08) registram esta skill não sendo executada exatamente quando teria ajudado. Desde a v0.5.2 é script, e o CI roda em todo push e PR.

O que o script verifica

Grupo Verifica
Estrutura canônica CLAUDE.md, START-HERE.md, WIZARD.md, README.md, CHANGELOG.md, LICENSE, .claude/{agents,rules,skills,commands}, e duplicata na raiz
Frontmatter toda skill tem name + description e o name bate com o diretório; todo agente e comando tem description
Links todo link relativo .md do repo resolve
Registry todo pack está no INDEX.md, e todo link do INDEX.md aponta pack existente
Session-log toda entrada datada está indexada
Hooks os hooks declarados em settings.json existem em disco, e todo hook em disco está declarado
Gitignore cobre .env, node_modules/, CLAUDE.local.md
Artefatos modo repo-do-OS versus projeto derivado, detectado pelo marcador .aios-self

Dois modos

O script se adapta ao contexto:

  • Repo do AI Dev OS (tem .aios-self) — os artefatos de projeto (BUSINESS-PLAN.md, PRODUCT-BRIEF.md…) não devem existir; se existirem, avisa.
  • Projeto derivado — os mesmos artefatos são esperados, e a ausência vira aviso e não erro, porque o wizard pode simplesmente não ter chegado naquela fase.

Seu trabalho quando falha

O script diz o que está quebrado. Interpretar e consertar continua sendo trabalho seu:

  1. Rode e leia os erros.
  2. Para cada um, decida se o certo é corrigir a referência ou remover o alvo — link quebrado às vezes significa que falta o arquivo, às vezes que sobra o link.
  3. Avisos (🟡) não bloqueiam, mas acumulam. Skill sem frase-gatilho na descrição é o caso típico: funciona, mas ninguém a invoca.
  4. Se consertar algo estrutural, registre no session-log/.

Read the full file on GitHub · 59 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. 7d ago First seen · 59 lines · 114 tokens per session scan A d7bfd1c35d44

Subscribe to this mod's changes

os-self-test is a skill published in the GitHub repository lglucas/ai-dev-operating-system (11 stars, last pushed 29d ago), licensed MIT. It adds 114 tokens to every session and 853 once invoked, about $0.0006 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

performance-smell-detection

Detect potential code-level performance smells in Java - streams, collections, boxing, regex, object creation. Provides awareness, not absolutes - always measure before optimizing. For JPA/database performance, use jpa-patterns instead.

decebals/claude-code-java · 51 tokens

tlamatini-flw-doctor

Validate a .flw workflow file: check connection topology, terminal agents, Parametrizer single-lane queue, missing connectors, dangling targetagents.

XAIHT/Tlamatini · 38 tokens

dependency-scan

Phase 1 mandatory dependency scan. Runs all 6 checks in a single invocation - route hrefs, component import consumers, shared type/utility consumers, test file references, FK references, access control policies. Returns a structured report per check with exact file paths and line numbers. Invoke once with the full…

marcoguillermaz/Tierward · 84 tokens

saleae-mcp-debugger

Use this skill for hardware-in-the-loop firmware capture and decode workflows through the Saleae Logic 2 MCP server.

layer1labs/specsmith · 0 tokens

systematic-debugging

Enforce root-cause investigation before any fix. Use when encountering a bug, test failure, unexpected behavior, or build error.

marcoguillermaz/Tierward · 31 tokens

logging-patterns

Java logging best practices with SLF4J, structured logging (JSON), and MDC for request tracing. Includes AI-friendly log formats for Claude Code debugging. Use when user asks about logging, debugging application flow, or analyzing logs.

decebals/claude-code-java · 50 tokens