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 andregusman-raiz/a-gusman-claude --skill ag-documentar-projetogit clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claudeWrote 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/andregusman-raiz/a-gusman-claude/ag-documentar-projeto)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-documentar-projeto"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-documentar-projeto/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/andregusman-raiz/a-gusman-claude/ag-documentar-projeto"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-documentar-projeto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 4 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00031 | $0.00694 |
| Opus 5 | $0.00015 | $0.00347 |
| Sonnet 5 | $0.00006 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
ag-documentar-projeto 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-documentar-projeto — Documentar Projeto
Spawn the ag-documentar-projeto agent to create and maintain project documentation: README, API docs, guides, changelog, and ADRs.
Docs Location (OBRIGATORIO)
Antes de salvar qualquer arquivo, resolver PROJECT_ROOT via git rev-parse --show-toplevel (ou usar o path do argumento). Se for $HOME/Claude (workspace raiz) — PARAR e perguntar qual projeto. Detalhes: ~/Claude/.claude/shared/patterns/docs-location.md. Hook docs-location-guard.sh bloqueia escrita em ~/Claude/docs/.
Invocation
Use the Agent tool with:
subagent_type:ag-documentar-projetomode:autorun_in_background:falseprompt: Compose from template below + $ARGUMENTS
Prompt Template
Projeto: [CWD or user-provided path]
Tipo: [readme|api|guia|changelog|adr]
Escopo: [modulo ou area especifica, se aplicavel]
Crie ou atualize a documentacao solicitada mantendo sincronia com o codigo atual.
README deve permitir setup em 10 min. API docs devem cobrir endpoints e schemas.
Guias devem ser praticos com exemplos. ADRs seguem template em docs/adr/.
Important
- ALWAYS spawn as Agent subagent — do NOT execute inline
- After spawning, confirm to the user
Output
- README com setup em 10 min (install, build, run, test)
- Documentacao de API (endpoints, schemas, auth, error codes)
- Guides de uso (praticos com exemplos)
- Changelog formatado e ADRs em docs/adr/
Anti-Patterns
- NUNCA documentar codigo obvio — docs repetindo codigo sao ruido; documentar "why", nao "what"
- NUNCA criar docs desconectados — docs nao atualizados com codigo enganam; manter sincronizados
- NUNCA pular ADR para decisoes significativas — sem ADR, ninguem sabe a justificativa
Quality Gate
- Doc reflete estado atual do codigo?
- Dev novo consegue setup em 10 min seguindo README?
- Decisoes arquiteturais tem ADR correspondente?
Regra PDF → Markdown (obrigatoria — economia de tokens)
Qualquer PDF consumido por esta skill DEVE ser convertido ANTES via markitdown:
bash ~/Claude/.claude/scripts/pdf2md.sh <arquivo.pdf> → Read/Grep no .md gerado (cache automatico).
NUNCA Read direto de .pdf para extrair texto. Excecao visual (layout/slides): converter primeiro, Read multimodal depois. Enforcement: hook pdf-read-guard.sh. Detalhes: .claude/rules/pdf-markitdown.md.
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 · 64 lines · 31 tokens per session scan A 01bbe04b1d30
ag-documentar-projeto is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 694 once invoked, about $0.0002 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.
Other skills, from other repositories
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
implement-issue
Drive a GitHub issue from branch to pull request — read the issue, create a feature branch, implement the change, run the project's build and tests, then commit, push, and open a PR. Language and build-tool agnostic. Use when asked to implement, fix, or resolve a GitHub issue by number.
ticket-triage
Rank the open tickets, work out what is genuinely startable versus blocked, run the startable ones in parallel through to merged — then KEEP GOING: re-triage every time an agent finishes, so the backlog drains without being re-asked. Use for "what's next", "review tickets", "triage the backlog", "prioritise", "start…
daily-working
End-to-end pipeline: pull a task from the project's task tracker by ID (Redmine or GitHub Issues today, more addable via a new adapter), sanity-check and impact-assess it against the codebase before touching anything, implement it with the Claude CLI, verify the result in a real browser via the Claude Chrome extension…
project-updates
Drafts Linear project status updates for each project the user leads, following the Done / In Progress / Next / Blockers template. Gathers context from Linear issues and comments, git history across configured repos, GitHub PRs, Slack mentions, Notion edits, and Gmail/Calendar. Never auto-posts — always shows the…
daily-brief
Surfaces recent updates relevant to you from GitHub, Linear, Slack, and other configured sources — PR reviews, new assignments, ticket changes, mentions, and CI failures. Use when starting work, catching up after being away, or prepping for standup.