Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jl-cmd/claude-dev-envnpx agentmods add skills/jl-cmd/claude-dev-env/auditing-claude-configWrote 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/jl-cmd/claude-dev-env/auditing-claude-config)<a href="https://agentmods.dev/skills/jl-cmd/claude-dev-env/auditing-claude-config"><img src="https://agentmods.dev/badge/skills/jl-cmd/claude-dev-env/auditing-claude-config.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 | $0.00091 | $0.01638 |
| Opus 5 | $0.00046 | $0.00819 |
| Sonnet 5 | $0.00018 | $0.00328 |
| Haiku 4.5 | $0.00009 | $0.00164 |
Grade A, and why
auditing-claude-config 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 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.
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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing Claude Config
This skill audits what gets eagerly loaded into every Claude Code session and identifies wins — duplicate imports, lazy-load candidates, skill-conversion candidates, and pointer-shrink opportunities. It is grounded in three Anthropic docs cited at the bottom.
When to invoke
/memoryshows files the user did not expect to be loaded- The user is adding new rules and wants to know if the preload is growing past the recommended ceiling (CLAUDE.md target: under 200 lines)
- Sessions feel sluggish or adherence to rules has degraded (the docs warn that bloated CLAUDE.md files cause Claude to ignore actual instructions)
- A new template or shared
.claude/directory has just been adopted - Periodic hygiene — quarterly is a reasonable cadence
Background facts the audit relies on
These come from the official Claude Code documentation; do not re-derive them.
| Fact | Source phrasing |
|---|---|
@path imports in CLAUDE.md and rules expand into context at launch — they are not pointers |
"Imported files are expanded and loaded into context at launch alongside the CLAUDE.md that references them" |
Splitting into @-imports does not reduce context |
"Splitting into @path imports helps organization but does not reduce context, since imported files load at launch" |
Files in .claude/rules/ without paths: frontmatter load every session |
"Rules without paths frontmatter are loaded unconditionally and apply to all files" |
| Path-scoped rules load lazily when matching files are accessed | "Rules can be scoped to specific files using YAML frontmatter with the paths field. These conditional rules only apply when Claude is working with files matching the specified patterns" |
| Skills preload metadata only | "At startup, only the metadata (name and description) from all Skills is pre-loaded. Claude reads SKILL.md only when the Skill becomes relevant, and reads additional files only as needed" |
@-imports inside fenced/inline code blocks do not trigger imports |
Empirical (verified in this skill's source session) — referenced files alongside backtick-wrapped @ paths do not appear in session-start context |
What ships with it
3 files 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 · 115 lines · 91 tokens per session scan A 319e3f314244
auditing-claude-config is a skill published in the GitHub repository jl-cmd/claude-dev-env (5 stars, last pushed today), licensed MIT. It adds 91 tokens to every session and 1,638 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…