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 xobotyi/cc-foundry --skill claude-mdgit clone --depth 1 https://github.com/xobotyi/cc-foundryWrote 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/xobotyi/cc-foundry/claude-md)<a href="https://agentmods.dev/skills/xobotyi/cc-foundry/claude-md"><img src="https://agentmods.dev/badge/skills/xobotyi/cc-foundry/claude-md/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/xobotyi/cc-foundry/claude-md"><img src="https://agentmods.dev/badge/skills/xobotyi/cc-foundry/claude-md.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 | $0.00040 | $0.03482 |
| Opus 5.5 | $0.00016 | $0.01393 |
| Sonnet 5.5 | $0.00008 | $0.00696 |
| Haiku 4.5 | $0.00004 | $0.00348 |
Grade B, and why
claude-md scanned grade B 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 1mo 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.
Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
- Cite the specific line and give the replacement inline. Do not lecture How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md is delivered as a user message after the system prompt, not as configuration. It is read and weighed, never enforced — which is why a rule that must hold every time belongs in a hook or a permission, and why the goal here is compliance, not completeness. A short file that gets followed beats a full one that gets ignored.
What Loads, and When
Routing and trimming decisions are wrong whenever the loading model is wrong. Establish this first.
- CLAUDE.md and CLAUDE.local.md load at launch from the working directory and every directory above it. Content is
ordered from the filesystem root down, so the file closest to the launch directory is read last. Within one directory,
CLAUDE.local.mdis appended afterCLAUDE.md. - Files in subdirectories below the working directory do not load at launch. They load when Claude reads a file in that directory. A rule that must hold from the first turn cannot live in a nested CLAUDE.md.
- Layer scope, broadest to narrowest — managed policy (
/Library/Application Support/ClaudeCode/CLAUDE.mdon macOS,/etc/claude-code/CLAUDE.mdon Linux and WSL,C:\Program Files\ClaudeCode\CLAUDE.mdon Windows) →~/.claude/→ the project (./CLAUDE.mdor./.claude/CLAUDE.md) →./CLAUDE.local.md. Managed policy cannot be excluded. - Load order is not precedence. Every discovered file is concatenated; when two layers contradict, Claude may follow either. Reconcile the conflict rather than relying on "later wins".
@pathimports expand at launch, up to four hops deep. Splitting a large CLAUDE.md into imports buys organization and never buys context. A path inside backticks stays literal instead of importing.- A CLAUDE.md over 4 MiB is skipped entirely — no warning in the file itself.
- Block-level HTML comments are stripped before injection. Notes for human maintainers cost no tokens.
claudeMdExcludesskips files by absolute-path glob, set at any settings layer, with arrays merging across layers. It is the monorepo tool for another team's files, and it excludes their rules along with their CLAUDE.md.- Verify what actually loaded with
/context, under Memory files. TheInstructionsLoadedhook logs each file as it loads, which is how a lazily-loaded rule is debugged.
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.
- 1mo ago First seen · 223 lines · 40 tokens per session scan B 123ab3c4ba78
claude-md is a skill published in the GitHub repository xobotyi/cc-foundry (22 stars, last pushed 7d ago), licensed MIT. It adds 40 tokens to every session and 3,482 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (strips warnings and disclaimers). 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…
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…