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-3-entregargit 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-3-entregar)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-3-entregar"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-3-entregar/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-3-entregar"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-3-entregar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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.
- medium Excessive Agency · line 57 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00038 | $0.00830 |
| Opus 5 | $0.00019 | $0.00415 |
| Sonnet 5 | $0.00008 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
Grade A, and why
ag-3-entregar 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ENTREGAR — Maquina Autonoma de Entrega
Canonical delegation (ADR-0001)
Esta machine delega para skills oficiais quando aplicável:
| Detecção | Canonical | Ação |
|---|---|---|
vercel.json OR .vercel/project.json presente |
vercel:deployments-cicd |
Orquestrar via skill oficial Vercel |
railway.json presente |
railway:use-railway |
Orquestrar via skill oficial Railway |
| Deploy manual via CLI | vercel:vercel-cli |
Usar CLI guidance oficial |
| Env vars gestão | vercel:env-vars |
Delegar configuração |
| Rollback Vercel | vercel:deployments-cicd (modo rollback) |
Delegar |
Para deploys simples em projetos Vercel, preferir invocar diretamente vercel:deployments-cicd. Esta machine (ag-3-entregar) adiciona valor quando: pipeline multi-ambiente (preview → staging → prod), quality gates customizados, integração com Sentry release, ou recovery multi-tentativa.
Invocacao
/entregar # Preview (default seguro)
/entregar producao # Pipeline completo producao
/entregar rollback # Rollback verificado
/entregar --resume # Retomar
O que faz
Deploy completo AUTONOMO em 5 fases:
ASSESS → PREFLIGHT → DEPLOY → SMOKE → MONITOR → REPORT
- ASSESS: Detecta modo (preview/production/rollback), verifica CLI auth
- PREFLIGHT: Credentials + typecheck + lint + test + build (production only)
- DEPLOY: Push/merge/vercel deploy conforme modo
- SMOKE: Verifica URL (homepage, assets, auth, console errors)
- MONITOR: Observa metricas por 5min (production only)
Modos
| Modo | Sinais | Pipeline |
|---|---|---|
| preview | default, "preview" | push branch → auto-deploy Vercel |
| producao | "producao", "prod" | preflight completo → merge PR → Vercel |
| rollback | "rollback", "reverter" | listar deploys → promover anterior |
Output
ENTREGAR COMPLETO
Modo: [preview/producao/rollback]
URL: [deploy_url]
Smoke: [pass/fail]
Monitor: [status]
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 · 76 lines · 38 tokens per session scan A d36c7558b9f5
ag-3-entregar is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 3d ago), licensed MIT. It adds 38 tokens to every session and 830 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
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.
graincrawl
Maintain, verify, and release graincrawl, the local-first Granola archive CLI, including SQLite archive behavior, read-only Granola source boundaries, Homebrew tap packaging, and crawlkit-powered TUI/snapshot surfaces.
crawlkit
Maintain and release the crawlkit Go library, preserving downstream compatibility for gitcrawl, slacrawl, discrawl, and notcrawl.
release
Prepare code for release (version bumps, changelog, README updates) and create an annotated tag to trigger the GoReleaser workflow.
release-notes
Generates brief, truth-based release notes for a release PR (typically main → prod) by listing each squash-merged PR, a one-paragraph summary drawn from each PR body, and the linked issue-tracker tickets (Linear, Jira, GitHub Issues, Asana, ClickUp, Shortcut, Plane, etc. — any tracker, configured via a URL template).…
linear-flow
Migrate a repo to the dev-trunk/main-release fast-forward model (no merge commits) and load its doctrine. One-shot setup; day-to-day rules live in each repo's CLAUDE.md afterwards.