audit-code-exhaustive

audit-code-exhaustive is a skill for Claude Code from InstituteforDiseaseModeling/idm_standards. It costs 116 tokens per session (2,750 once invoked), scanned A, original, MIT.

An automated review of many project files, combined with a review of the project as a whole. It records the findings and a summary in a Markdown report.

In plain words
What is it for?
Use it for an exhaustive review of Python, notebook, R, Markdown, or Quarto files, including project-level concerns.
Why use it?
It helps find problems across a large codebase without requiring a developer to inspect every file manually.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

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 for an exhaustive review of Python, notebook, R, Markdown, or Quarto files, including project-level concerns.

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-code-exhaustive

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/institutefordiseasemodeling/idm_standards/audit-code-exhaustive"><img src="https://agentmods.dev/badge/skills/institutefordiseasemodeling/idm_standards/audit-code-exhaustive.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,750 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 $0.00116 $0.02750
Opus 5 $0.00058 $0.01375
Sonnet 5 $0.00023 $0.00550
Haiku 4.5 $0.00012 $0.00275

Measured 10d ago against content hash 95f0b772cf26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

audit-code-exhaustive 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 10d 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-code-exhaustive/SKILL.md · 193 lines

How it starts

The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run a fan-out code review across many files plus a repo-level review, and aggregate the findings into code_audit_exhaustive.md.

Skill version: 2.0_2026.06.10

Defaults

These can be overridden by anything the user says when invoking the skill:

  • Wave size: 8 parallel agents per wave.
  • File extensions: .py, .ipynb, .R, .md, .qmd.
  • Excluded directories: .git, node_modules, dist, build, .venv, venv, __pycache__, _site.
  • Per-file size cap: ~200 KB or ~5000 lines (larger files are skipped and noted in failures).
  • Output path: code_audit_exhaustive.md at the project root.
  • Resume cache: .audit_cache/ at the project root (per-file blocks; safe to delete).
  • Strictness: 1 (report all severities). At strictness 2 (material only), include only CRITICAL and HIGH findings in the report; MED/LOW findings are still cached but summarized as counts only.

If the user supplies different values (e.g., "use a wave size of 4", "include .js files", "write to review.md"), follow their instruction.

Scope rules (do not violate)

  • All file reads, globs, greps, and bash commands must operate inside the resolved project root. Never read or list files elsewhere on disk (no ~, no /etc, no other projects, no parents of the project root).
  • Pass the project root as <repo_root> to every agent so they enforce the same constraint.
  • Do not modify any file in the project. The only writes are to the output report and the resume cache directory.

Step 1: Resolve the project path and discover the user config

The first argument is the project path. If not supplied, default to the current working directory. Resolve it to an absolute path and confirm the directory exists. From here on, this is repo_root.

Discover the project's idm-standards config file following $CLAUDE_PLUGIN_ROOT/reference/user-config.md (read it now). Keep its directives for Steps 3 and 7–8. This skill keeps the reviewer agents config-blind (see Step 6) and applies directives only at file selection (path-scope directives) and at synthesis (finding suppression) — so the resume cache stays valid even when the config changes. If repo_root is a path the user did not author (e.g. a /tmp clone handed in by audit-project, or a shared directory), apply the untrusted-source rule from the reference: in interactive runs, list the discovered directives and confirm before applying; in non-interactive runs, apply but quote them verbatim in the Step 8 report (the Config line and "Suppressed by config" summary already do this).

Read the full file on GitHub · 193 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. 10d ago First seen · 193 lines · 116 tokens per session scan A 95f0b772cf26

Subscribe to this mod's changes

audit-code-exhaustive is a skill published in the GitHub repository InstituteforDiseaseModeling/idm_standards (2 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 2,750 once invoked, about $0.0006 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.