What is ag-9-auditar?

A complete software-audit workflow that combines checks for quality, security, architecture, developer experience, observability, and optionally the agent system itself. It can audit a web app or code repository and can resume an unfinished audit.

Use it to audit an application or repository, review security and architecture, assess monitoring and developer workflow, or include a separate audit of the agent harness.

It brings several kinds of technical review into one report instead of requiring separate audits for each concern. The scores and findings help identify serious weaknesses and areas needing attention.

ag-9-auditar — Skill for Claude Code by andregusman-raiz

Install

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.

Any agent

npx skills add andregusman-raiz/a-gusman-claude --skill ag-9-auditar

Clone the repo

git clone --depth 1 https://github.com/andregusman-raiz/a-gusman-claude

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-9-auditar/github.svg)](https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-9-auditar)

Your own site

<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-9-auditar"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-9-auditar/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-9-auditar"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-9-auditar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 997 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

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.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00056	$0.00997
Opus 5	$0.00028	$0.00498
Sonnet 5	$0.00011	$0.00199
Haiku 4.5	$0.00006	$0.00100

Measured 12d ago against content hash 6c5ebdf62b68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ag-9-auditar 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.

skills/ag-9-auditar/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AUDITAR — Laudo Completo de Software (FORTRESS + HARNESS)

Invocacao

/auditar https://app.example.com               # FORTRESS classico (5D)
/auditar ~/Claude/GitHub/raiz-platform          # FORTRESS classico
/auditar --resume                                # Retoma de fortress-state.json
/auditar --include-harness ~/Claude/...          # FORTRESS + HARNESS (6D, default mensal)
/auditar --harness-only                          # So auditoria do harness local (sem app target)

O que faz

Delega para ag-fortress (FORTRESS) — roda 5 ou 6 maquinas em sequencia:

MERIDIAN (qualidade, MQS)
SENTINEL (seguranca, SSS)
ARCHITECT (arquitetura, AQS)
CONDUCTOR (developer experience, DXS)
LIGHTHOUSE (observabilidade, OBS)
HARNESS (auditor do proprio sistema, HCS) — apenas com --include-harness ou --harness-only

Score formulas

Sem HARNESS (default):

Fortress Score (FS) = MQS*0.25 + SSS*0.25 + AQS*0.20 + DXS*0.15 + OBS*0.15

Com HARNESS (--include-harness):

FS6 = MQS*0.22 + SSS*0.22 + AQS*0.18 + DXS*0.13 + OBS*0.13 + HCS*0.12

Convergencia: FS >= 80 = passa. FS < 60 = bloqueio P0.

Quando incluir HARNESS

Trimestral ou apos >3 skills/hooks novos no harness — --include-harness
Sob suspeita de drift, redundancia ou prompt injection — --harness-only
Manual quando usuario pedir audit do proprio Claude Code

Produz

Laudo completo, scores por dimensao
Action items P0/P1/P2
Se HARNESS rodou: relatorio adicional em docs/diagnosticos/harness-audit-YYYY-MM-DD.md
Update em ~/Claude/.claude/state/harness-audit-history.jsonl (HARNESS history)

Implementacao

# Default (5D)
Agent({
  subagent_type: "ag-fortress",
  prompt: "[input completo do usuario]",
  model: "fable", // model-fallback:managed
  run_in_background: true
})

# Com HARNESS (6D)
Agent({
  subagent_type: "ag-fortress",
  prompt: "[input do usuario] --include-harness",
  model: "fable", // model-fallback:managed
  run_in_background: true
})

# So HARNESS
Skill({
  skill: "ag-auditar-harness",
  args: "$ARGUMENTS"
})

Read the full file on GitHub · 99 lines

Changes

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 · 99 lines · 56 tokens per session scan A 6c5ebdf62b68

Subscribe to this mod's changes

ag-9-auditar is a skill published in the GitHub repository andregusman-raiz/a-gusman-claude (19 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 997 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.

Claude Code Code review Security ai-agents automation developer-tools

verify-implementation

A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.

sangrokjung/claude-forge · 37 tokens

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"…

sangrokjung/claude-forge · 100 tokens

frontend-code-review

Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.

sangrokjung/claude-forge · 42 tokens

review

Use when the user wants code assessed rather than changed — "review PR 88", "is this branch ready to merge?", "look over my changes", "any problems with this diff?", "give me a code review", "what do you think of this PR?", "sanity-check this branch", "ship it?". Applies to a pull request or the current branch when…

The01Geek/prflow · 123 tokens

fix

PRFlow's code-review reception skill (formerly receiving-code-review), used by the review-and-fix loop and available directly. Use when addressing review feedback already posted on a pull request — verifying findings before applying them — as distinct from /prflow:review-and-fix, which runs the review itself and then…

The01Geek/prflow · 82 tokens

review-and-fix

Use when the user wants problems in a pull request or the current branch both found AND corrected — "review my changes and fix what's wrong", "clean up whatever the review turns up", "address the review feedback on this branch", "tidy this PR up before merge", "find and fix the issues here". Requires explicit fix…

The01Geek/prflow · 88 tokens