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.
npx skills add digital-stoic-org/agent-skills --skill edit-claudegit clone --depth 1 https://github.com/digital-stoic-org/agent-skillsWrote 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/digital-stoic-org/agent-skills/edit-claude)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/edit-claude"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/edit-claude/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/digital-stoic-org/agent-skills/edit-claude"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/edit-claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 142 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Rogue Agent · line 17 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00051 | $0.02828 |
| Opus 5.5 | $0.00020 | $0.01131 |
| Sonnet 5.5 | $0.00010 | $0.00566 |
| Haiku 4.5 | $0.00005 | $0.00283 |
Grade A, and why
edit-claude 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 29d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for Managing CLAUDE.md Files
Determine Action Type
CREATE: New CLAUDE.md file requested UPDATE: Modify existing CLAUDE.md (keywords: "update", "add", "modify", "change") OPTIMIZE: Audit and clean an existing CLAUDE.md chain (keywords: "optimize", "audit", "clean up", "reduce tokens", "improve")
Updating Existing CLAUDE.md Files
Make surgical edits in the relevant section (or a new heading), preserving the file's existing organization. After editing, check the file's line count against the size guidance below, because longer files consume more context and may reduce adherence.
Optimizing CLAUDE.md Files
The goal is that every line earns its place for the current model, not the shortest file. Rules lose value when cut from their reason, so compress wording, never reasons.
- Dated-pattern pass: invoke
/claude-api prompt-auditscoped to the CLAUDE.md chain (and.claude/rules/), with the current session model as target. It returns a report and a diff covering pressure language, fossils and restated defaults. Call it by skill name only: its bundled file path is versioned per Claude Code release and breaks on upgrade, and a copy here would go stale, so do not copy it either. - CLAUDE.md-specific pass (prompt-audit does not cover these):
- Move path/domain-specific content to
.claude/rules/withpathsfrontmatter, so it loads only when needed;@importscan organize long material but still load at launch - Remove secrets and frequently changing data
- Check each file's line count (
wc -l) and what actually loads (/context) against the size guidance below
- Move path/domain-specific content to
- Present both diffs and apply only what the user accepts.
See reference.md § Optimization Strategies for rewrite examples.
Fit check (CREATE)
CLAUDE.md is loaded into every session, so it only holds content that is persistent, used in most sessions, and non-sensitive. Route what fails that to its better home and say so: secrets to env vars, one-off asks to the conversation, long docs to a README referenced by path, detailed guidelines to .claude/rules/. For mixed requests, write the part that fits and route the rest.
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.
- 29d ago Changed · -36 lines 82028358d2f9
- 1mo ago First seen · 239 lines · 51 tokens per session scan A 6df05084cdf8
edit-claude is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 12d ago), licensed MIT. It adds 51 tokens to every session and 2,828 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…