Borrowing it
Nothing to install: this file belongs to rp1-run/rp1. 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/rp1-run/rp1/main/CLAUDE.mdgit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/rp1-run/rp1/claude-md)<a href="https://agentmods.dev/instructions/rp1-run/rp1/claude-md"><img src="https://agentmods.dev/badge/instructions/rp1-run/rp1/claude-md.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 | $0.00532 | $0.00532 |
| Opus 5 | $0.00266 | $0.00266 |
| Sonnet 5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
rp1 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 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.
What it actually says
@AGENTS.md
Commit Discipline
- Always use Conventional Commits for final commit messages:
<type>(<optional-scope>): <imperative summary>. - Stage only the intended changes for each commit and avoid catch-all commit messages like
wiporupdates.
1up — Agent Quick Reference
Tool Selection
Pick by what you know, not by habit:
| You know... | Use | Reason |
|---|---|---|
| Concept, not files/keywords | 1up search |
Semantic search needs no vocabulary |
| Symbol/keyword name | 1up symbol -r or grep |
Literal match = precise, low noise |
| Keyword, need ALL instances | grep |
Guaranteed-complete, best signal:noise |
| Nothing (new codebase) | 1up search |
Works w/o prior knowledge |
Sub-agents: Include this section in sub-agent prompts.
Setup
1up status before searching. Confirm index built + Last file check recent (~30s refresh). If not initialized: 1up start (macOS/Linux) or 1up init && 1up index ..
Commands
1up search "<query>" -n 5 # semantic + keyword hybrid
1up symbol <name> [-r] # def lookup; -r = all references
1up context <file>:<line> # enclosing scope at location
1up impact --from-symbol <name> # blast radius from symbol
1up impact --from-file <path> # blast radius from file
1up impact --from-segment <id> # blast radius from segment
1up structural "<ts-query>" # tree-sitter AST pattern search
Flags: --format plain|json|human (default: plain), -v/-vv.
Workflow
search— explore by meaning/intentsymbol— known or partial name lookupcontext— read scope at file:lineimpact— dependency/blast-radius analysisstructural— AST-level pattern matching
Search-then-Verify
Semantic search ranks by relevance; may omit matches. Never conclude "only N callers" from search alone. Verify completeness w/ 1up symbol -r <name> or grep.
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 · 54 lines · 532 tokens per session scan A bfab431e51a5
rp1 CLAUDE.md is an instructions file published in the GitHub repository rp1-run/rp1 (38 stars, last pushed yesterday), licensed Apache-2.0. It adds 532 tokens to every session, about $0.0027 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 2026-08-30.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.