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 agents/miaodx/roboclaws/operating-runbookgit clone --depth 1 https://github.com/MiaoDX/roboclawsWrote 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/agents/miaodx/roboclaws/operating-runbook)<a href="https://agentmods.dev/agents/miaodx/roboclaws/operating-runbook"><img src="https://agentmods.dev/badge/agents/miaodx/roboclaws/operating-runbook.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 | $0.00000 | $0.01813 |
| Opus 5 | $0.00000 | $0.00907 |
| Sonnet 5 | $0.00000 | $0.00363 |
| Haiku 4.5 | $0.00000 | $0.00181 |
Grade A, and why
operating-runbook 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 4d 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Operating Runbook
This file holds repo-specific operating details that are too long for
AGENTS.md but useful to coding agents. Read only the sections relevant to the
current task.
Environment Setup
Roboclaws uses one repo-local Python environment per checkout/worktree:
.venv/, managed by uv from pyproject.toml and uv.lock.
uv sync --extra dev
Use uv sync for declared project environments and uv pip install only for
explicit one-off local installs. Do not use plain pip install for repo setup.
The dev extra includes the standard MolmoSpaces/MuJoCo CPU runtime used by
local cleanup demos. Keep Isaac Lab isolated in .venv-isaaclab/ and install
other optional extras only when a workflow explicitly needs them.
After reviewing and accepting the NVIDIA Omniverse EULA, persist that
machine-local decision in the gitignored repo .env:
OMNI_KIT_ACCEPT_EULA=YES
just loads .env automatically. Isaac preflight and smoke harnesses derive
their acceptance default from this variable, while an explicit
accept_nvidia_eula=false remains available for CI and guarded negative tests.
If PyPI downloads are slow or flaky, keep mirror selection machine-local:
UV_DEFAULT_INDEX=https://pypi.tuna.tsinghua.edu.cn/simple \
uv sync --extra dev
Worktree Setup Hooks
This checkout uses project hooks from .githooks/; core.hooksPath should
point there. Install or repair it with:
git config core.hooksPath .githooks
.githooks/post-checkout auto-creates a worktree-local .venv/, a
.venv-visual-grounding/, copies gitignored local config such as .env, and
symlinks .venv-isaaclab/ from the main checkout when it already exists.
Submodules under vendors/ are mostly reference/vendor inputs. Inspect the main
checkout or git submodule status --recursive first; initialize a submodule in
the current worktree only when you need to modify it, run isolated verification,
or prove the exact checkout.
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.
- 4d ago First seen · 202 lines · 0 tokens per session scan A 6e401cf4fc08
operating-runbook is an agent published in the GitHub repository MiaoDX/roboclaws (6 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,813 tokens. 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 2026-08-31.
Other agents, from other repositories
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
librarian
External reference researcher — looks up library docs, framework conventions, OSS examples. Read-only, no memory injection. (Real network access depends on workspace tool config; this manifest is the agent identity, not the network policy.).
Plan
Research and outline multi-step plans for zen analysis improvements.
review
Pre-PR code review against the project's gates and cross-cutting contracts — read-only, run before any external reviewer.
smart-test-fixer
Run checks and tests, then fix every failure. Use recent Git changes to decide whether code or tests are wrong.
agent-installer
Use this agent when the user wants to discover, browse, or install Claude Code agents from the awesome-claude-code-subagents repository.