ag-auditar-harness

ag-auditar-harness is a skill for Claude Code from andregusman-raiz/a-gusman-claude. It costs 56 tokens per session (1,995 once invoked), scanned B, original, MIT.

A Portuguese-language audit workflow for an agent system's skills, hooks, rules, and connections to external tools. It checks for instruction drift, unsafe prompt-injection risks, duplicated guidance, missing completion requirements, and poor-value tool connections.

In plain words
What is it for?
Use it for periodic or requested audits, especially after adding several skills, to produce a scored report with findings and suggested quick fixes.
Why use it?
It helps maintain the reliability and safety of the instructions that guide coding agents. It surfaces weak or conflicting automation before those problems affect development work.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; positional $N argument.

Good fit Use it for periodic or requested audits, especially after adding several skills, to produce a scored report with findings and suggested quick fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/andregusman-raiz/a-gusman-claude/ag-auditar-harness
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-auditar-harness
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.

agentmods badge for ag-auditar-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-auditar-harness/github.svg)](https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-auditar-harness)
Your own site
<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-auditar-harness"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-auditar-harness/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.

agentmods 80×15 button for ag-auditar-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/andregusman-raiz/a-gusman-claude/ag-auditar-harness"><img src="https://agentmods.dev/badge/skills/andregusman-raiz/a-gusman-claude/ag-auditar-harness.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 1,995 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.01995
Opus 5 $0.00028 $0.00997
Sonnet 5 $0.00011 $0.00399
Haiku 4.5 $0.00006 $0.00199

Measured 12d ago against content hash 39405eaf6ded, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

ag-auditar-harness scanned grade B with 2 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.

Downloads and executes remote codemediumSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

| Hook que `curl | sh` URLs nao-fixas | P0 | `curl $URL | sh` |

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Hook que `curl | sh` URLs nao-fixas | P0 | `curl $URL | sh` |
skills/ag-auditar-harness/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ag-auditar-harness — Auditor do harness

Equivalente local ao AgentShield do ECC, focado nos pontos fracos especificos do sistema rAIz: drift de skills, hooks bloqueantes sem bypass documentado, redundancia semantica entre skills, machines sem score, MCPs com baixo ROI.

Quando invocar

  • Trimestral via ag-curador-skills
  • Sob demanda: /ag-auditar-harness
  • Como dimensao HARNESS de /ag-9-auditar --include-harness
  • Apos qualquer adicao de >3 skills novas (gate manual)

Output

Relatorio em ~/Claude/docs/diagnosticos/harness-audit-YYYY-MM-DD.md com:

  • HCS total (0-100) — media ponderada dos 5 sub-scores
  • Sub-scores (cada um 0-100) — drift, injection, redundancy, dod_violation, mcp_cost
  • Findings P0/P1/P2 — path + linha + fix sugerido
  • Quick wins (se --apply-quick-wins) — PR atomico com fixes triviais

HCS — formula

HCS = (
  HCS_drift      * 0.25 +
  HCS_injection  * 0.30 +    # peso maior — security first
  HCS_redundancy * 0.15 +
  HCS_dod        * 0.20 +
  HCS_mcp_cost   * 0.10
)

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

Sub-auditores

1. HCS.drift — Skills cujo description nao bate com conteudo

Detecta: descricao de skill (frontmatter description:) divergente do corpo do SKILL.md.

Metodo:

  1. Para cada ~/Claude/.claude/skills/*/SKILL.md:
    • Extrai frontmatter description
    • Extrai primeiro paragrafo de prosa (apos # titulo)
    • Compara via:
      • Levenshtein normalizado (rapido, primeiro filtro)
      • Embedding cosine (sentence-transformers/all-MiniLM-L6-v2) se disponivel localmente
  2. Score por skill = max(0, 100 - 100 * (1 - similaridade))
  3. HCS.drift = mean(scores) onde score < 70 conta como finding P1

Heuristica fallback (sem embedding): keywords sobreposicao tf-idf simples via stdlib Python.

Fix sugerido: reescrever description OU atualizar corpo para refletir capacidade real.

2. HCS.injection — Hooks/skills com risco de injection

Detecta:

Read the full file on GitHub · 199 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.

  1. 12d ago First seen · 199 lines · 56 tokens per session scan B 39405eaf6ded

Subscribe to this mod's changes

ag-auditar-harness 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 1,995 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

taiyi-ui-design

A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.

Dong90/oh-my-taiyiforge · 35 tokens

taiyi-evolve

A workflow skill that compares the implemented code with the frozen design after development and testing. It records architecture changes and proposes updates to DESIGN.md, the document describing the intended system structure.

Dong90/oh-my-taiyiforge · 37 tokens

taiyi-diagram-c4

A code-scanning tool that builds C4 architecture documents from a repository. It separates facts observed in the code from conclusions inferred about the design and uses Mermaid diagrams as the source format.

Dong90/oh-my-taiyiforge · 48 tokens

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…

The01Geek/prflow · 91 tokens

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…

The01Geek/prflow · 97 tokens

tmux-lane-orchestrator

Manage one tmux agent lane from its matching ops pane, inspect live pane state and Codex logs on cold start, and produce concise manager summaries for OpenClaw and adjacent project work.

vincentkoc/dotskills · 46 tokens