geniro-claude-harness: Skill for Claude Code

.claude/skills/audit-plugin/SKILL.md

audit-plugin is a skill for Claude Code from geniro-io/geniro-claude-harness. It costs 207 tokens per session (5,123 once invoked), scanned A, original, Apache-2.0.

A whole-repository audit workflow for a Geniro plugin. It checks skills, agents, hooks, helper code, rules, and documentation for consistency, correctness, safety, missing connections, and unnecessary complexity.

In plain words
What is it for?
Use it to audit the complete plugin, run mechanical checks, review focused quality and safety dimensions, verify findings, and receive a prioritized report with possible actions.
Why use it?
It finds problems that are easy to miss when reviewing files one at a time, such as stale references or declared features that are not wired up. It verifies findings before reporting them and waits for approval before applying fixes.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

This is geniro-io/geniro-claude-harness's own configuration. It tells Claude Code how to work on geniro-claude-harness itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything geniro-claude-harness configures →

Part of the geniro plugin — 37 skills, 8 agents, 1 hook shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to geniro-io/geniro-claude-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/geniro-io/geniro-claude-harness/main/.claude/skills/audit-plugin/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/geniro-io/geniro-claude-harness

Made for: Claude Code.

Or install geniro, the plugin that ships this one along with the rest of its 37 skills, 8 agents, 1 hook.

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 audit-plugin

README.md
[![agentmods](https://agentmods.dev/badge/skills/geniro-io/geniro-claude-harness/audit-plugin/github.svg)](https://agentmods.dev/skills/geniro-io/geniro-claude-harness/audit-plugin)
Your own site
<a href="https://agentmods.dev/skills/geniro-io/geniro-claude-harness/audit-plugin"><img src="https://agentmods.dev/badge/skills/geniro-io/geniro-claude-harness/audit-plugin/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 audit-plugin

Your own site · 80×15
<a href="https://agentmods.dev/skills/geniro-io/geniro-claude-harness/audit-plugin"><img src="https://agentmods.dev/badge/skills/geniro-io/geniro-claude-harness/audit-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 207 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,123 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.
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 $0.00207 $0.05123
Opus 5 $0.00103 $0.02561
Sonnet 5 $0.00041 $0.01025
Haiku 4.5 $0.00021 $0.00512

Measured 9d ago against content hash deaf5038e51e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

audit-plugin 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.

.claude/skills/audit-plugin/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit-plugin — whole-repo plugin audit pipeline

Contents

  • Phases overview · Loop invariants · Anti-rationalization · Budgets · Subagent tiering
  • Phase 0 (scope & inventory) · Phase 1 (mechanical pre-pass) · Phase 2 (dimension reviewers)
  • Phase 3 (merge, verify, filter) · Phase 4 (report) · Phase 5 (action gate)
  • State recovery · Definition of done · REFERENCE

You are the audit orchestrator. You run deterministic checks yourself, delegate semantic review to parallel dimension reviewers, re-verify every finding before admitting it, and present a tiered report. Every run also sweeps for subtraction and reports what it found — including nothing. Fixes are applied only after the user approves them at the action gate.

Phases overview

  1. Phase 0 — Scope & inventory. Parse $ARGUMENTS, build the file inventory, load the rubric (every .claude/rules/*.md file + dimensions-reference.md).
  2. Phase 1 — Mechanical pre-pass. Run the D1 deterministic battery (tests, lint, shellcheck, wiring greps). Output: machine findings + candidate lists that seed the reviewers.
  3. Phase 2 — Parallel dimension reviewers. Spawn one reviewer per selected dimension (D5 splits into markdown + shell) in ONE response, within the §Budgets spawn cap.
  4. Phase 3 — Merge, verify, filter. Dedupe, count convergence, re-read every cited line, drop unverifiable and do-not-flag items, assign tiers.
  5. Phase 4 — Report. Write design/scratch/plugin-audit-<YYYY-MM-DD>.md (health summary → tier tables → per-dimension verdicts → highest-value fix) and summarize in chat.
  6. Phase 5 — Action gate. AskUserQuestion: fix now / pick / report only. Approved fixes go through implementation subagents, then the mechanical battery re-runs to verify. Cleanup + commit offer.

Loop invariants

The shared audit-pipeline invariants apply in full — skills/_shared/audit-pipeline.md §Shared invariants. This skill binds their three parameterized ones and adds one of its own:

Read the full file on GitHub · 162 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 162 lines · 207 tokens per session scan A deaf5038e51e

Subscribe to this mod's changes

audit-plugin is a skill published in the GitHub repository geniro-io/geniro-claude-harness (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 207 tokens to every session and 5,123 once invoked, about $0.0010 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 2026-08-31.