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/dannymac180/openclaw-operator/agents-mdgit clone --depth 1 https://github.com/DannyMac180/openclaw-operatorWrote 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/dannymac180/openclaw-operator/agents-md)<a href="https://agentmods.dev/instructions/dannymac180/openclaw-operator/agents-md"><img src="https://agentmods.dev/badge/instructions/dannymac180/openclaw-operator/agents-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 | $0.00399 | $0.00399 |
| Opus 5 | $0.00199 | $0.00199 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
openclaw-operator 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 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.
What it actually says
AGENTS.md
Purpose
This repository may contain an OpenClaw installation, workspace, or supporting code.
When a task involves OpenClaw setup, troubleshooting, skills, cron jobs, channels, providers, integrations, or runtime validation, consult skills/openclaw-operator/SKILL.md before planning changes.
Operating rules
- Inspect before editing.
- Prefer official OpenClaw CLI commands and local docs over memory.
- Make the smallest reversible change that satisfies the task.
- Preserve existing structure and naming.
- Validate changes before finishing.
- Never expose secrets in output, logs, diffs, or committed files.
OpenClaw-first workflow
- Identify whether this is a source repo, live workspace, or both.
- Locate the active config, workspace, and relevant skill/integration files.
- If the
openclawCLI exists, start with:openclaw statusopenclaw gateway statusopenclaw docs <topic>openclaw doctor
- Read
skills/openclaw-operator/SKILL.mdfor the detailed task playbook. - Use
skills/openclaw-operator/references/validation_checklist.mdbefore finishing. - Make targeted edits.
- Re-run the most relevant validation commands.
Editing guidance
- Do not rewrite whole config files unless necessary.
- Prefer adding narrowly scoped files over embedding large instructions into root docs.
- Keep skill definitions concise and move lengthy references into supporting files.
- Use
skills/openclaw-operator/assets/for reusable examples, templates, and scaffolds. - If command names or behavior differ from expectation, trust the installed version and local docs.
Response format
When you complete work, summarize:
- What you found
- What you changed
- How you validated it
- Any follow-up risks or next steps
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 · 48 lines · 399 tokens per session scan A ebf0250b0a2f
openclaw-operator AGENTS.md is an instructions file published in the GitHub repository DannyMac180/openclaw-operator (21 stars, last pushed 6mo ago), licensed MIT. It adds 399 tokens to every session, about $0.0020 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
agentsec AGENTS.md
Instructions for semiotic-ai/agentsec, covering agents.md - project rules for agents, package manager, monorepo structure, package naming and dependency graph.
agentsec CLAUDE.md
Instructions for semiotic-ai/agentsec, a project described as: Agent Audit scans AI agent skills for security vulnerabilities, scores them against the OWASP Agentic Skills Top 10, and generates actionable compliance reports.
gangsta AGENTS.md
Instructions for kucherenko/gangsta, covering contributing to gangsta, what this is, what will not be accepted, skill changes and the laws apply to contributors too.
gangsta GEMINI.md
Instructions for kucherenko/gangsta, a project described as: AI agentic skills framework for spec-driven development, built on the organizational model of mafia.
Operator-Use CLAUDE.md
Instructions for Jeomon/Operator-Use, covering operator — claude.md, project overview, repository layout, quick navigation and key invariants.
connectors CLAUDE.md
Claude Code instructions for zapier/connectors: Claude Code loads this file automatically. The canonical AI-agent guidance lives in AGENTS.md so that Claude Code, Codex, Cursor, and any other tool following the AGENTS.md convention read the same content.