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-pipeline-deploygit 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-pipeline-deploy)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-pipeline-deploy"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-pipeline-deploy/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-pipeline-deploy"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-pipeline-deploy.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 | $0.00049 | $0.00841 |
| Opus 5 | $0.00024 | $0.00420 |
| Sonnet 5 | $0.00010 | $0.00168 |
| Haiku 4.5 | $0.00005 | $0.00084 |
Grade A, and why
ag-pipeline-deploy 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-pipeline-deploy — Deploy Pipeline
Spawn the ag-pipeline-deploy agent to run the full 8-stage deploy pipeline autonomously with auto-recovery.
Invocation
Use the Agent tool with:
subagent_type:ag-pipeline-deploymode:bypassPermissionsrun_in_background:trueprompt: Compose from template below + $ARGUMENTS
Prompt Template
Projeto: [CWD or user-provided path]
Ambiente: [preview|production]
## Output
- Pipeline 8-stage report: env check → typecheck → lint → test → build → deploy → smoke → final
- Status por etapa (PASS/FAIL/RECOVERED)
- Auto-recovery attempts documentados (max 3 por stage)
Execute o pipeline completo end-to-end:
1. Env check 2. Typecheck 3. Lint 4. Test 5. Build 6. Deploy 7. Smoke test 8. Report
Auto-recovery em cada etapa (max 3 tentativas). Se falha apos 3 tentativas, reportar e parar.
Caminho padrao: PR-based via Vercel Git Integration (pre-deploy-gate.sh no buildCommand). Pipeline manual para repos sem Git Integration.
Important
- ALWAYS spawn as Agent subagent — do NOT execute inline
- Runs in background with fork context (autonomous pipeline)
- After spawning, confirm to the user
Troubleshooting
| Erro | Causa Comum | Solucao |
|---|---|---|
| Build OOM | Bundle grande, memory limit | NODE_OPTIONS='--max-old-space-size=8192' |
| Typecheck timeout | Projeto grande sem incremental | bunx tsc --noEmit --incremental |
| Flaky tests | Race conditions, network deps | --retry=2 ou @flaky tag + skip |
| Missing secrets | Env vars nao configuradas | vercel env ls ou gh secret list |
| Deploy stuck | Vercel queue, rate limit | vercel ls → verificar status |
| Smoke test 404 | Rota nao gerada, rewrite rules | Verificar vercel.json rewrites |
| Build cache stale | Cache corrompido | vercel --force ou limpar .next/ |
| ESLint new errors | Dep update trouxe novas regras | --max-warnings=N temporario |
Recovery Procedures
Build OOM
export NODE_OPTIONS='--max-old-space-size=8192'
bun run build
# Se persistir: analisar bundle com `bunx next build --analyze`
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 · 81 lines · 49 tokens per session scan A c3865abd079a
ag-pipeline-deploy is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 4d ago), licensed MIT. It adds 49 tokens to every session and 841 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 2026-09-03.
Other skills, from other repositories
investigate-ci
Investigates GitHub Actions workflow failures for any repo. Fetches recent runs, identifies failures, extracts error logs, diagnoses root causes, and suggests fixes. Use when a deploy or CI workflow fails and you need to understand why.
working-with-lacquer
Use when working in a lacquer-managed project (one with a .lacquer.toml) and anything about that management comes up: the drift audit inside the "Detect changed paths" CI job fails, lacquer audit exits 3/4/6, a lint config or CI workflow you edited reverts on the next sync, a hook or workflow needs changing, the…
github-ci-fix
Use when PR checks fail, CI is red, or GitHub Actions workflows break - systematically inspects failing checks via gh CLI, pulls logs, checks for flakiness and scopes the breaking commit, scopes external checks, then creates fix plan using existing plan skill.
github-actions
Use when adding CI/CD, creating workflows, auditing GitHub Actions, or fixing action pinning. Creates and audits workflows for SHA pinning and permissions.
tune-repo
Audit and tighten the current repository so Claude Code works faster and more accurately in it — verify the existing CLAUDE.md still matches reality, tighten the build/test/lint verification loop, add only the missing static guardrails, and reduce permission friction. Use when the user wants to "tune", "audit"…
GitHub Actions CI Patterns
Use this skill when adding or debugging GitHub Actions workflows and you want repeatable CI behavior, minimal permissions, and clear failure logs.