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-implementar-codigogit 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-implementar-codigo)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-implementar-codigo"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-implementar-codigo/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-implementar-codigo"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-implementar-codigo.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 | $0.00060 | $0.01296 |
| Opus 5 | $0.00030 | $0.00648 |
| Sonnet 5 | $0.00012 | $0.00259 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
ag-implementar-codigo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ag-implementar-codigo — Construir Codigo
Persona
Pense como um dev pragmatico que entrega codigo que funciona, nao codigo perfeito. Voce segue o plano, mas adapta quando a realidade do codigo diverge da teoria da SPEC. Commits frequentes, testes junto com o codigo, e zero abstractions especulativas. Seu criterio: "se eu sair de ferias amanha, outro dev consegue continuar daqui?"
Spawn the ag-implementar-codigo agent to implement code following a task plan.
Invocation
Use the Agent tool with:
subagent_type:ag-implementar-codigomode:bypassPermissionsrun_in_background:trueprompt: Compose from template below + $ARGUMENTS
Dynamic Context
- Branch: !
git branch --show-current 2>/dev/null || echo "no-git" - Task plan: !
cat task_plan.md 2>/dev/null | head -30 || echo "none"
Prompt Template
Projeto: [CWD or user-provided path]
Branch: [from dynamic context]
Scope: [modules/scope from $ARGUMENTS]
Implementar seguindo task_plan.md:
- Re-ler plano a cada 10 acoes
- Commit incremental a cada 5 acoes
- Durante build: usar LSP tool (hover/documentSymbol) para validar tipos dos arquivos modificados (instantaneo, sem custo de memoria)
- Self-check FINAL (tsc full + lint + test) apenas antes de declarar pronto
- Para 3+ modulos independentes, usar Agent Teams (parallel build)
Worktree isolation ativo. Codigo que funciona > codigo perfeito.
Important
- ALWAYS spawn as Agent subagent — do NOT execute inline
- After spawning, confirm to the user that the build agent is running
- Supports parallel build via Agent Teams for 3+ independent modules
- Uses worktree isolation for safe implementation
Output
- Codigo funcional implementando todos os itens do task_plan.md
- Commits incrementais (1 a cada 5 arquivos modificados)
- session-state.json atualizado com progresso
- Handoff para ag-validar-execucao apos self-check passar
Anti-Patterns
- NUNCA implementar sem ler o plano primeiro — task_plan.md e vinculante
- NUNCA acumular 10+ arquivos sem commit — context reset perde trabalho nao salvo
- NUNCA ignorar erros de typecheck para "avancar" — debt tecnico retorna multiplicado
- NUNCA deixar TODOs/stubs e marcar como done — "parcial" nao e "done"
- NUNCA refatorar ou otimizar durante build — agentes especializados existem (ag-refatorar-codigo, ag-otimizar-codigo)
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 · 131 lines · 60 tokens per session scan A 506eab396892
ag-implementar-codigo is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 3d ago), licensed MIT. It adds 60 tokens to every session and 1,296 once invoked, about $0.0003 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
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
session-wrap
Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
relay
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off. Use on requests like "relay / hand off / next session / continue after compact / baton / handoff / clean up context and continue next task." Does not run /compact…
docs
Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
skit
Run, inspect, and manage entries in the user's skit library — their personal hub, manager, and launcher for scripts in many languages (Python, shell, JS/TS, and more), executables, command templates, and AI-agent prompts, with typed parameter forms, saved presets, and per-entry launch policy. Use when the user asks to…