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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/rp1-run/rp1/agents-md"><img src="https://agentmods.dev/badge/instructions/rp1-run/rp1/agents-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/rp1-run/rp1/agents-md"><img src="https://agentmods.dev/badge/instructions/rp1-run/rp1/agents-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 | $0.03550 | $0.03550 |
| Opus 5.5 | $0.01420 | $0.01420 |
| Sonnet 5.5 | $0.00710 | $0.00710 |
| Haiku 4.5 | $0.00355 | $0.00355 |
Grade A, and why
rp1 AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rp1 Agent Authoring Guide
This file is intentionally narrow. Use it for agent and skill authoring rules that are specific to rp1.
- Read
.rp1/context/index.mdfirst. - Then load only the KB files needed for the task.
Project understanding belongs in .rp1/context/. This file covers runtime and authoring constraints.
Core Rules
Namespace prefixes
Use these prefixes exactly:
- Skills:
/rp1-base:skill-name,/rp1-dev:skill-name,/rp1-utils:skill-name - Agent references:
subagent_type: rp1-base:agent-namefor Claude Code,subagent_type: @rp1-dev/agent-namefor OpenCode
Subagent limitations
Subagents generally cannot spawn other agents. If an agent is designed to run as a subagent:
- Do not use SlashCommand to call other commands.
- Do not invoke other skills for KB context; read KB files directly using the resolved
{KB_ROOT}path (index.md first, then task-relevant files). - Inline only the prompt text or KB guidance the subagent actually needs.
Codex task shorthand
For Codex agents, interpret any instruction in the form Task: <sub-agent-name> as:
- spawn
<sub-agent-name>
Treat this as an execution directive, not as descriptive text.
Codex subagent waiting
When Codex agents spawn subagents in this repo:
- Do not assume a subagent failed just because it does not answer quickly.
- Use longer wait windows for artifact-producing or workflow-heavy subagents.
- Prefer waiting for the spawned subagent to complete before declaring it stalled or rerouting around it, unless the user explicitly wants parallel speculative work.
- Check for expected side effects such as artifact files before concluding the subagent is stuck.
- If the subagent is on the critical path, babysit it with patient polling instead of replacing it after a short timeout.
Cross-plugin dependency rule
- Dev agents may depend on base.
- Base agents must not call dev commands.
- If a dev workflow depends on an
rp1-baseskill (such asrp1-base:artifact-templates) and it is unavailable, tell the user to installrp1-base.
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 Changed · +8 lines · +149 tokens per session ce7058ad691c
- 1mo ago First seen · 316 lines · 3,401 tokens per session scan A c93cf3832cdd
rp1 AGENTS.md is an instructions file published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,550 tokens to every session, about $0.0142 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.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.