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-2-corrigirgit 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-2-corrigir)<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-2-corrigir"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-2-corrigir/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-2-corrigir"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-2-corrigir.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 | $0.00052 | $0.01409 |
| Opus 5 | $0.00026 | $0.00705 |
| Sonnet 5 | $0.00010 | $0.00282 |
| Haiku 4.5 | $0.00005 | $0.00141 |
Grade A, and why
ag-2-corrigir 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CORRIGIR — Maquina Autonoma de Correcao
Invocacao
/corrigir login nao funciona apos Clerk update # Bug unico
/corrigir tipos # Sweep TypeScript
/corrigir lista: [bug1, bug2, bug3] # Batch
/corrigir debt modulo financeiro # Tech debt
/corrigir --triage-only erros reportados pelo QA # So diagnosticar
/corrigir --resume # Retomar
O que faz
Correcao completa AUTONOMA em 4 fases:
ASSESS → DIAGNOSE → FIX → VERIFY → (loop ate green) → SHIP
↑ │
└───────┘ (convergencia: max 3 cycles — Definition of Done CLAUDE.md)
Emissao de Phase Tags (observabilidade)
Emitir linha de status a cada transicao de fase:
[ASSESS ✓] modo=bug ciclos_max=3
[DIAGNOSE ✓] causa_raiz="null ref em adapter" confianca=alta hipoteses=3
[FIX →] aplicando fix em 2 arquivos...
[VERIFY ✓] typecheck=0 lint=0 tests=8/8 ciclo=1/3
[SHIP ✓] branch=fix/X PR=#43
Se VERIFY falha: [VERIFY ✗] ciclo=2/3 erros=3 → voltando para FIX
- ASSESS: Auto-detecta modo (bug/tipos/batch/debt/triage), estima volume
- DIAGNOSE: Causa raiz, categoriza, prioriza (ag-depurar-erro se obscuro). Listar 3+ hipoteses concorrentes (Deep Reasoning Directive).
- FIX: Corrige (ag-corrigir-bugs/B-53 conforme modo). Loop convergente.
- VERIFY: Typecheck + lint + testes. Se red → volta para FIX.
- SHIP: PR com diagnostico e evidencia.
ReasoningBank — Fix Strategy Persistence
Ao encerrar fix bem-sucedido (VERIFY verde), extrair e persistir o pattern:
# Append em meridian-kb/fix-strategies.json (criar se nao existe)
FIX_ENTRY=$(python3 -c "
import json, sys, datetime
entry = {
'ts': '$(date -u +%Y-%m-%dT%H:%M:%SZ)',
'sintoma': 'SINTOMA_AQUI',
'causa_raiz': 'CAUSA_AQUI',
'fix_aplicado': 'FIX_AQUI',
'arquivos': [],
'modo': 'MODO_AQUI',
'ciclos': 1
}
print(json.dumps(entry))
")
mkdir -p meridian-kb
STRATEGIES_FILE="meridian-kb/fix-strategies.json"
if [ -f "\$STRATEGIES_FILE" ]; then
python3 -c "
import json
with open('\$STRATEGIES_FILE') as f:
data = json.load(f)
data['strategies'].append(\$FIX_ENTRY)
with open('\$STRATEGIES_FILE', 'w') as f:
json.dump(data, f, indent=2)
"
else
echo '{ \"strategies\": [\$FIX_ENTRY] }' > "\$STRATEGIES_FILE"
fi
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 · 129 lines · 52 tokens per session scan A 005e0bf55794
ag-2-corrigir is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 1,409 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 2026-08-30.
Other skills, from other repositories
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
systematic-debugging
Structured debugging methodology — use before proposing fixes for any error or failure. Covers: code bugs, build errors, deploy failures, config conflicts, dependency issues, infra problems. Also use when previous fix attempts failed or root cause is unclear.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
docs-release-notes
Use when a change needs a user-visible release-note, changelog, or changeset entry — "add a release note", "add a changeset for this", "what goes in the changelog?", "write up what shipped", "note this for the next release" — or when finalizing a branch whose customer-visible features, bug fixes, or UI changes should…
retrospective-audit
Stage B of /prflow:retrospective-weekly: given a most-recent-first subset of one recurring pattern's occurrence-PR context bundles (bounded by auditbundlecap), re-derive the root cause and return one JSON object carrying a ranked findings array (one to three sub-patterns) — no edits, no worktree. Invoked as a subagent…
taiyi-health
A codebase health review process that samples recently changed production modules and test files, then checks for issues such as duplication, unused code, and unused dependencies.