Borrowing it
Nothing to install: this file belongs to rootbr/rooted. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rootbr/rooted/main/CLAUDE.mdgit clone --depth 1 https://github.com/rootbr/rootedWrote 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/instructions/rootbr/rooted/claude-md)<a href="https://agentmods.dev/instructions/rootbr/rooted/claude-md"><img src="https://agentmods.dev/badge/instructions/rootbr/rooted/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/instructions/rootbr/rooted/claude-md"><img src="https://agentmods.dev/badge/instructions/rootbr/rooted/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 | $0.00313 | $0.00313 |
| Opus 5.5 | $0.00125 | $0.00125 |
| Sonnet 5.5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
rooted CLAUDE.md 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 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.
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.
What it actually says
Rooted
Claude Code plugin marketplace — rooted in evidence.
Orientation
Read README.md, then run ./overview.sh to orient.
Read individual files only if the output is not sufficient for the user's request.
Evidence-Based Rule
Before adding any rule, checklist item, or review criterion — verify it traces to one of:
| Source | Examples |
|---|---|
| Academic research | arxiv.org, peer-reviewed papers, Google Scholar, PubMed |
| Technical standards | RFCs, official specifications, language/framework docs |
| Verified hands-on experience | Author's real-world usage, confirmed through practice |
No traceable source → do not add.
Cite the form anyone can open — an arXiv ID or DOI, an RFC number or spec URL, a linked commit or gist. A source nobody can fetch cannot be re-verified by a reader, a reviewer, or the audit itself.
A trade book is not a source class. When a rule's wording comes from a practitioner text — a book, a blog, a conference talk — find the research that backs the claim itself and rest the rule on that; the practitioner text may then be named in rule-cards-provenance.md as the formulation the rule follows, never in the card and never as its evidence. Where an openable source carries the same formulation, drop the unopenable one instead of keeping both.
Quality Gate
MUST run /auditing-ai-context on every SKILL.md or agent prompt change before committing.
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 · 29 lines · 313 tokens per session scan A 15c3419e1c4b
rooted CLAUDE.md is an instructions file published in the GitHub repository rootbr/rooted (21 stars, last pushed 2d ago), licensed Apache-2.0. It adds 313 tokens to every session, about $0.0013 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).