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)<a href="https://agentmods.dev/skills/institutefordiseasemodeling/idm_standards/audit-code"><img src="https://agentmods.dev/badge/skills/institutefordiseasemodeling/idm_standards/audit-code.svg" alt="Measured on agentmods" 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 | $0.00119 | $0.06312 |
| Opus 5 | $0.00060 | $0.03156 |
| Sonnet 5 | $0.00024 | $0.01262 |
| Haiku 4.5 | $0.00012 | $0.00631 |
Grade B, and why
audit-code 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 8d 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.
Enumerates the file system for secretsmediumData exfiltration
Searching home directories for .env, .ssh, .aws or credential files is reconnaissance for credential theft.
1. Check for exposed secrets: scan for .env files, hardcoded API keys/tokens/passwords using grep patterns like (api_key|secret|password|token)\s*=\s*['\"][^'"]{8,}. 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.
7. For Tier 1: check if package is on PyPI (curl -I https://pypi.org/pypi/<package>/json), look for CHANGELOG. How it starts
The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Score a software project against the IDM engineering quality guidelines and write a code_audit.md report.
Skill version: 2.0_2026.06.10
Step 0: Record start time
Before doing anything else, run the following bash command and save the result as START_EPOCH:
date +%s
This will be used in Step 9 to compute elapsed time.
Step 1: Parse arguments and detect language
The user provides up to three arguments:
- project: path to a local directory OR a GitHub URL (e.g.,
https://github.com/org/repo). Default: current working directory. - tier: integer 1, 2, or 3. If supplied explicitly, treat it as confirmed (do not re-ask in Step 2).
- strictness: integer 1 or 2. Default: 1.
- Strictness 1 (strict): report everything you find (the default).
- Strictness 2 (material only): only report findings that materially affect correctness, usability, or safety — purely stylistic or convention-based findings are neither penalized nor reported.
If a GitHub URL is given: Use gh repo clone <url> /tmp/audit-code-$(date +%s) to clone to a temporary directory. Set project to that path.
Language detection: determine the project's main language. If the project has a DESCRIPTION file, an renv.lock, or a majority of its source files are *.R/*.Rmd, it is an R project — stop and invoke the audit-r-code skill instead, passing along the project path, tier, strictness, and any other user instructions. If the project is a substantial mix of Python and R (each ≥25% of source files), ask the user which audit to run (or both) — but in non-interactive contexts, or when invoked by audit-project, default to auditing whichever language has more source files (ties → Python) and note the choice in the report.
If the user provided any other specific instructions when invoking this skill, integrate them into the workflow. For example, if they said "ignore missing docstrings", make sure to not penalize the project for that in the scoring and omit it from the recommendations. If the invoking context says the tier and strictness are already confirmed (e.g., this skill was invoked by audit-project), skip the questions in Step 2.
What ships with it
1 file 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.
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.
- 8d ago First seen · 378 lines · 119 tokens per session scan B b87f3f151246
audit-code is a skill published in the GitHub repository InstituteforDiseaseModeling/idm_standards (2 stars, last pushed 3d ago), licensed MIT. It adds 119 tokens to every session and 6,312 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (enumerates the file system for secrets, makes network calls). 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.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.
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…