RPent is an open framework for building embodied agents, software systems that perceive and act in the physical world while combining reasoning, memory, execution, and adaptation. It is intended for embodied-intelligence researchers working on physical tasks and related evaluations.
Borrowing it
Nothing to install: this file belongs to RLinf/RPent. 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/RLinf/RPent/main/AGENTS.mdgit clone --depth 1 https://github.com/RLinf/RPentWrote 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/rlinf/rpent/agents-md)<a href="https://agentmods.dev/instructions/rlinf/rpent/agents-md"><img src="https://agentmods.dev/badge/instructions/rlinf/rpent/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/rlinf/rpent/agents-md"><img src="https://agentmods.dev/badge/instructions/rlinf/rpent/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 | $0.00790 | $0.00790 |
| Opus 5.5 | $0.00316 | $0.00316 |
| Sonnet 5.5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
RPent 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 18d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on RPent
Follow CONTRIBUTING.md for development conventions, including module ownership and interface contracts, and for testing and pull requests. Use the implementation and its callers to verify behavior; report disagreements with documentation instead of assuming either is correct.
Repository map
rpent/planner/,rpent/session/, andrpent/prompt/: planner adapters, execution sessions, and shared prompt construction.rpent/tools/andrpent/memory/: tool execution, observations, and memory.rpent/robots/: robot discovery, descriptors, shared runtime, and Env/VLA components.robots/<robot>/owns each concrete integration.rpent/cli/,rpent/dashboard/, andrpent/evaluation/: entry points, interactive execution, and run results.tests/: offline tests and integration checks; see tests/README.md.docs/source-en/anddocs/source-zh/: paired user and developer documentation.
Development principles
- Confirm the working branch and relevant upstream state before editing. Read the closest current implementation and both sides of changed interfaces. Preserve unrelated working-tree changes.
- Reuse existing configuration, registration, RPC, runtime, and artifact helpers. Prefer RLinf's supported Env/VLA implementations with thin RPent adapters.
- Base compatibility paths and new abstractions on actual consumers or supported data.
- Validate external inputs at the boundary that owns the operation. Keep internal control flow direct, avoid repeated checks of established state, and preserve useful errors. Make resource ownership and cleanup explicit.
- Keep optional simulator/model imports at their use sites so basic imports, robot discovery, and CLI help work without every robot extra installed.
- Follow neighboring code for naming and structure, use the project logger, and follow CONTRIBUTING's type annotation and docstring conventions.
- Write prose about current behavior and non-obvious constraints. Keep review exchanges and implementation history in PR discussions or migration notes. Translate meaning into natural Chinese and preserve technical identifiers.
- Keep prompts and tool descriptions focused on the model's task. Remove repetition without dropping required behavior or operational constraints.
- Test observable behavior and concrete regressions, reusing existing cases and fixtures where possible. Avoid tests that merely restate implementation details. Never weaken failing tests to make a change pass.
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.
- 18d ago Changed · -19 tokens per session 3dee148c648d
- 1mo ago First seen · 66 lines · 809 tokens per session scan A 4cf050064efc
RPent AGENTS.md is an instructions file published in the GitHub repository RLinf/RPent (1,640 stars, last pushed 3d ago), licensed Apache-2.0. It adds 790 tokens to every session, about $0.0032 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 2026-09-17.
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).
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.