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-r-code)<a href="https://agentmods.dev/skills/institutefordiseasemodeling/idm_standards/audit-r-code"><img src="https://agentmods.dev/badge/skills/institutefordiseasemodeling/idm_standards/audit-r-code/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-r-code"><img src="https://agentmods.dev/badge/skills/institutefordiseasemodeling/idm_standards/audit-r-code.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 | $0.01938 |
| Opus 5 | $0.00058 | $0.00969 |
| Sonnet 5 | $0.00023 | $0.00388 |
| Haiku 4.5 | $0.00012 | $0.00194 |
Grade A, and why
audit-r-code scanned grade A with 1 finding 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.
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 CRAN (`curl -I https://cran.r-project.org/web/packages/<package>/DESCRIPTION`) or r-universe publication. How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Score an R project against the IDM engineering quality guidelines (including the R-specific guidance in eng_guidance/2b_r.md, which defers to the Tidyverse style guide for style) and write a code_audit.md report.
Skill version: 2.0_2026.06.10
Workflow
This skill follows exactly the same workflow as audit-code — read $CLAUDE_PLUGIN_ROOT/skills/audit-code/SKILL.md now and follow its Steps 0–10 (start time; argument parsing; tier/strictness confirmation; prior-report reading; parallel sub-agent dispatch; score computation; score reconciliation; recommendations and proposed solutions; writing code_audit.md; offering to fix), with the R-specific differences below.
Difference 1: Language routing (replaces audit-code Step 1 detection)
This skill is for R projects: a DESCRIPTION file, an renv.lock, or a majority of source files being *.R/*.Rmd. If the project turns out to be mainly Python, stop and invoke audit-code instead. For substantial Python+R mixes (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 → R, since this skill was selected) and note the choice in the report.
Difference 2: Scoring schema (replaces audit-code Step 3)
Read the R schema from:
$CLAUDE_PLUGIN_ROOT/skills/audit-r-code/r-scoring-schema.yaml
Category weights, metric weights, N/A rules, and failure conditions are identical to the Python schema; the rubric anchors are R-specific.
Difference 3: Tier inference signals (audit-code Step 2)
When inferring a suggested tier:
DESCRIPTION+NAMESPACE+man/+ CRAN/r-universe publication + CI → suggest Tier 1 (package)renv.lock(orDESCRIPTIONwithout package skeleton),R/functions, some tests, README → suggest Tier 2 (shared research code)- Loose
.R/.Rmdscripts, single author → suggest Tier 3 (one-off)
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.
- 9d ago First seen · 78 lines · 116 tokens per session scan A 3eedf230a7fc
audit-r-code is a skill published in the GitHub repository InstituteforDiseaseModeling/idm_standards (2 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 1,938 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (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…