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.
/plugin marketplace add InstituteforDiseaseModeling/idm_standards/plugin install idm-standardsWrote 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.
[](https://agentmods.dev/skills/institutefordiseasemodeling/idm_standards/audit-code-exhaustive)<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.
<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>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 | $0.00116 | $0.02750 |
| Opus 5 | $0.00058 | $0.01375 |
| Sonnet 5 | $0.00023 | $0.00550 |
| Haiku 4.5 | $0.00012 | $0.00275 |
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.
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:
8parallel 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.mdat the project root. - Resume cache:
.audit_cache/at the project root (per-file blocks; safe to delete). - Strictness:
1(report all severities). At strictness2(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).
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.
- 10d ago First seen · 193 lines · 116 tokens per session scan A 95f0b772cf26
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…