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/skills/docs-check/SKILL.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/skills/rlinf/rpent/docs-check)<a href="https://agentmods.dev/skills/rlinf/rpent/docs-check"><img src="https://agentmods.dev/badge/skills/rlinf/rpent/docs-check/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/rlinf/rpent/docs-check"><img src="https://agentmods.dev/badge/skills/rlinf/rpent/docs-check.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 | $0.00755 |
| Opus 5.5 | $0.00016 | $0.00302 |
| Sonnet 5.5 | $0.00008 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
docs-check 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 29d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check documentation and prose
Follow AGENTS.md and the documentation requirements in CONTRIBUTING.md. Establish the changed files and intended audience, then read their owning implementation and nearby examples. For documentation structure, terminology, and layout, follow docs/STYLE_GUIDE.md.
For restructuring, record the pre-edit revision and content destinations. Compare commands, dependency options, defaults, output descriptions, numeric tables and their conditions, and media references after the final edit. Keep the leaderboard and incomplete integration entries unless a requested change explicitly covers them. Check simulator overview fields and shared section order against the style guide, and inspect Chinese inline markup in generated HTML; a warning-free build does not establish correct rendering.
Check meaning and coverage
- Verify commands, flags, configuration keys, defaults, paths, API names, and capability claims against the relevant revision and actual consumers. A successful build does not prove these claims. For public behavior changes, identify the affected guides, API docstrings, examples, and README entries.
- Read the paired pages under
docs/source-en/anddocs/source-zh/when both cover the feature, even if only one changed. Preserve equivalent behavior, commands, prerequisites, limitations, and reported results in both languages. - Translate meaning into natural Chinese using nearby terminology. Preserve identifiers, commands, and proper names; choose context-appropriate technical terms instead of literal substitutions. Do not force identical sentence structure across languages.
- Describe current behavior and useful non-obvious constraints. Remove review exchanges, authoring notes, redundant implementation narration, and obsolete comparisons while retaining factual qualifications and necessary rationale. Historical explanations belong in migration or change records when needed.
- Match neighboring pages for headings, links, code blocks, and examples. Keep comments near their owning contract and avoid repeating the same rule across several files.
- Inspect prompts and tool descriptions as model inputs: check tool names, placeholders, actual rendered context, conflicting rules, and unnecessary repetition. Preserve behavioral instructions and distinguish prose cleanup from changes that require runtime evidence.
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.
- 29d ago Changed · +10 lines 6b605dbc19a5
- 1mo ago Changed · +1 lines 554a20fd8139
- 1mo ago First seen · 61 lines · 40 tokens per session scan A 534ff9d72ba7
docs-check is a skill published in the GitHub repository RLinf/RPent (1,640 stars, last pushed 3d ago), licensed Apache-2.0. It adds 40 tokens to every session and 755 once invoked, about $0.0002 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 skills, from other repositories
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.