Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/robocurve/inspect-robots/claude-mdgit clone --depth 1 https://github.com/robocurve/inspect-robotsWrote 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/robocurve/inspect-robots/claude-md)<a href="https://agentmods.dev/instructions/robocurve/inspect-robots/claude-md"><img src="https://agentmods.dev/badge/instructions/robocurve/inspect-robots/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 | $0.02035 | $0.02035 |
| Opus 5 | $0.01018 | $0.01018 |
| Sonnet 5 | $0.00407 | $0.00407 |
| Haiku 4.5 | $0.00203 | $0.00203 |
Grade A, and why
inspect-robots 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 5d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inspect Robots — agent guide
Inspect Robots is the "Inspect AI for robotics": an open-source evaluation framework for physical AI / VLA (vision-language-action) models. This repo is the framework; concrete benchmarks and backend adapters live elsewhere (see below).
The one big idea
LLM evals have one swappable input (the model). Robotics evals have two:
Policy(the VLA "brain") — observation →ActionChunk(open-loop horizon).Embodiment(the robot/sim "body + world") — executes actions, owns spaces.
A Task (a dataset of Scenes + scorers) is defined independently of both.
eval() checks a (policy, embodiment) pair is compatible, runs the closed-loop
rollout, scores it, and writes an immutable EvalLog. Mirrors Inspect AI's
Task = dataset + solver + scorer, eval(), EvalLog, registry/decorator model.
Layout
src/inspect_robots/— the package (seesrc/inspect_robots/CLAUDE.mdfor the module map).tests/— pytest; theCubePickmock world exercises the whole stack with no hardware or sim.plans/— design docs.plans/0001-foundation-design.mdis the authoritative spec (read its §9–§11 "binding resolutions" before changing core interfaces).examples/— runnable demos (quickstart.py).plugins/*— first-party plugin packages (concrete sims/VLAs that are out of scope for the numpy-only core), each its own package with its own pyproject, entry point, tests, and coverage scope. A uv workspace ([tool.uv.workspace]) ties them in:uv sync --all-packages --extra devinstalls core + all plugins editable. They never count toward the core 100% gate (coverage is scoped toinspect_robots). E.g.plugins/inspect-robots-isaacsim/(Isaac Lab embodiment),plugins/inspect-robots-ros/(ROS 1/ROS 2 embodiment speaking rosbridge with no ROS dependency),plugins/inspect-robots-xpolicylab/(policy adapter speaking the XPolicyLab websocket protocol — 40+ served VLAs, no xpolicylab dep), andplugins/inspect-robots-agent/(LLMs as policies via the OpenAI-compatible wire formats or Anthropic's native Messages API — httpx only, no provider SDKs; registered asagent), andplugins/inspect-robots-capx/(CaP-X code-as-policy over perception and IK HTTP servers; registered ascapx), andplugins/inspect-robots-voice/(local microphone transcription with Parakeet and local Kokoro policy narration; registered as thevoiceoperator input andspeakersink).
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.
- 5d ago First seen · 128 lines · 2,035 tokens per session scan A 6588af02f4dc
inspect-robots CLAUDE.md is an instructions file published in the GitHub repository robocurve/inspect-robots (205 stars, last pushed 2d ago), licensed MIT. It adds 2,035 tokens to every session, about $0.0102 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
ClawBench AGENTS.md
AGENTS.md instructions for TIGER-AI-Lab/ClawBench, covering clawbench -- agent context, what this is, project structure, setup and 2. configure at least one model.
autonomous-os CLAUDE.md
Claude Code instructions for autonomous-ai/autonomous-os, covering claude.md, multi-ide rules (cursor + claude code), subagent usage, device access rules and project overview.
autonomous-os AGENTS.md
AGENTS.md instructions for autonomous-ai/autonomous-os, covering agents.md, multi-ide rules, working style, parallel work / subagents and device access rules.
rosclaw AGENTS.md
AGENTS.md instructions for ros-claw/rosclaw, covering rosclaw agent instructions, runtime boundary, tool policy, robot integration setup and capability apps.
rosclaw CLAUDE.md
Claude Code instructions for ros-claw/rosclaw, covering claude.md — rosclaw project onboarding, rosclaw runtime boundary (managed), safety contract (p0), robot integration setup and capability apps.
worldforge AGENTS.md
AGENTS.md instructions for AbdelStark/worldforge, covering agent guide, project identity, architecture map, tech stack and commands.