audit-project

audit-project is a skill for Claude Code from InstituteforDiseaseModeling/idm_standards. It costs 95 tokens per session (1,440 once invoked), scanned A, original, MIT.

A project-wide review that checks code and documentation using one shared set of questions, then saves the combined findings in a Markdown report.

In plain words
What is it for?
Use it to review a local project or a GitHub repository, assess its code and docs against IDM standards, and produce a projectaudit.md summary.
Why use it?
It avoids running separate reviews with repeated setup and gives you one place to see problems in both the software and its documentation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the idm-standards plugin — 10 skills shipped together

Good fit Use it to review a local project or a GitHub repository, assess its code and docs against IDM standards, and produce a projectaudit.md summary.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add InstituteforDiseaseModeling/idm_standards
Claude Code
/plugin install idm-standards

Made for: Claude Code.

Or install idm-standards, the plugin that ships this one along with the rest of its 10 skills.

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-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/institutefordiseasemodeling/idm_standards/audit-project/github.svg)](https://agentmods.dev/skills/institutefordiseasemodeling/idm_standards/audit-project)
Your own site
<a href="https://agentmods.dev/skills/institutefordiseasemodeling/idm_standards/audit-project"><img src="https://agentmods.dev/badge/skills/institutefordiseasemodeling/idm_standards/audit-project/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-project

Your own site · 80×15
<a href="https://agentmods.dev/skills/institutefordiseasemodeling/idm_standards/audit-project"><img src="https://agentmods.dev/badge/skills/institutefordiseasemodeling/idm_standards/audit-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,440 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 $0.00095 $0.01440
Opus 5 $0.00048 $0.00720
Sonnet 5 $0.00019 $0.00288
Haiku 4.5 $0.00010 $0.00144

Measured 12d ago against content hash 8995f2a6dac3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

audit-project 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.

idm_standards_plugin/skills/audit-project/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the IDM code and/or documentation audits on a project, asking the user's preferences once, and write a combined project_audit.md summary.

Skill version: 2.0_2026.06.10

Step 1: Parse arguments and resolve the project

The user provides up to three arguments: project (local path or GitHub URL; default current directory), tier (1–3), and strictness (1–2). Tier definitions and strictness semantics are the same as in audit-code.

If a GitHub URL is given: clone it once with gh repo clone <url> /tmp/audit-project-$(date +%s) and use that local path for every sub-audit (the docs audit has no URL support of its own).

Discover the user config once, following $CLAUDE_PLUGIN_ROOT/reference/user-config.md (read it now), against the resolved local path. Hold its directives (and any frontmatter tier/strictness) to pass into every sub-audit in Step 3, so they aren't re-discovered three times. If the project came from a GitHub URL or a path the user didn't author, surface the directives for confirmation in Step 2 before applying.

Step 2: Ask the user once

Use a single AskUserQuestion call covering (omit any already supplied as arguments or by invocation instructions):

  1. Which audits to run? (multiSelect)
    • "Code audit (Recommended)" — engineering quality scoring (audit-code, or audit-r-code for R projects)
    • "Docs audit (Recommended)" — documentation completeness, structure, audience fit (audit-docs)
    • "Exhaustive code review" — per-file review of the whole codebase (audit-code-exhaustive); note: much slower The default is code + docs ("both").
  2. Tier: the three tier options, with an inferred tier as the recommended option (infer as in audit-code Step 2). Tier 1 is the strictest (large reusable library / DPG); Tier 3 is the loosest (one-off / exploratory). Keep each tier number glued to its definition: when the recommended option is moved to the top, its number moves with it — never relabel a definition with a different tier number. A published/packaged library is Tier 1, not Tier 3.
  3. Strictness: 1 (strict — everything) or 2 (material only).

Read the full file on GitHub · 84 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 · 84 lines · 95 tokens per session scan A 8995f2a6dac3

Subscribe to this mod's changes

audit-project is a skill published in the GitHub repository InstituteforDiseaseModeling/idm_standards (2 stars, last pushed 3d ago), licensed MIT. It adds 95 tokens to every session and 1,440 once invoked, about $0.0005 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.