audit-code

A code-architecture audit that searches skill registries for relevant recommendations and compares a codebase with them.

In plain words
What is it for?
Use it when improving a codebase’s architecture: it finds matching skills from configured or local registries, then audits the code against their recommendations.
Why use it?
It gives the review a broader source of architectural guidance instead of relying only on local opinions or conventions.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/prosusai/prism/audit-code
Any agent
npx skills add ProsusAI/prism --skill audit-code
Clone the repo
git clone --depth 1 https://github.com/ProsusAI/prism

Made for: Claude Code, Codex.

Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,592 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00027 $0.02592
Opus 5 $0.00014 $0.01296
Sonnet 5 $0.00005 $0.00518
Haiku 4.5 $0.00003 $0.00259

Measured 2d ago against content hash 3513e8b9be45, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-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 2d 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.

import json, os, urllib.request, urllib.error
skills/audit-code/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use this skill

Use when the user wants to improve their codebase architecture by checking it against skills present in the registry. Invoked as /audit-code (Claude Code) or @audit-code (Cursor).

Configuration

  • Primary source: All configured registries in ~/.prism/registries.json (with per-registry caching and source tagging)
  • Fallback 1: Local skill-registry.json in the current project directory
  • Fallback 2: Local _analysis/extracted_skills_codebase/ skill directories
  • Authentication: REGISTRY_TOKEN environment variable (global override) or per-registry token from registries.json

Skills from multiple registries are merged and each result is tagged with [registry-name] (e.g., [team], [community]) to identify the source.

Instructions

Step 1 -- Resolve skill registry source

Read ~/.prism/skills/_shared/registry-fetch.md and follow its instructions. It resolves all configured registries with ETag caching and local fallbacks, returning a skills array where each entry is tagged with _registry.

Outcomes:

  • Valid JSON array → use as the skills list, proceed to Step 2
  • REGISTRY_EMPTY → registry reached but empty, proceed to Step 2
  • NO_REGISTRIES → no registry reachable, stop (the shared file handles the user message)

Step 2 -- Check for empty registry

If the skills array from the resolved source is empty, respond with: "No skills have been published to the registry yet." and stop.

Step 2.5 -- Check for existing analysis files

Check which analysis files exist:

for f in _analysis/full_report.md _analysis/design.md _analysis/directives.md _analysis/incidents.md; do
  test -f "$f" && echo "FOUND: $f" || echo "MISSING: $f"
done

If at least one file is found, list them and ask the user:

"Found existing analysis files in _analysis/: {list found files}

Use these for matching, or run a fresh codebase scan?"

  • Fresh scan chosen → skip to Step 3, Path B.
  • Use existing files chosen → read all found files now (see table below), then continue to Step 3, Path A.
  • No files found → skip to Step 3, Path B.

Read the full file on GitHub · 230 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. 2d ago First seen · 230 lines · 27 tokens per session scan A 3513e8b9be45

Subscribe to this mod's changes

audit-code is a skill published in the GitHub repository ProsusAI/prism (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 27 tokens to every session and 2,592 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens