Borrowing it
Nothing to install: this file belongs to IgorGanapolsky/openclaw-console. 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/IgorGanapolsky/openclaw-console/develop/AGENTS.mdgit clone --depth 1 https://github.com/IgorGanapolsky/openclaw-consoleWrote 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/igorganapolsky/openclaw-console/agents-md)<a href="https://agentmods.dev/instructions/igorganapolsky/openclaw-console/agents-md"><img src="https://agentmods.dev/badge/instructions/igorganapolsky/openclaw-console/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/igorganapolsky/openclaw-console/agents-md"><img src="https://agentmods.dev/badge/instructions/igorganapolsky/openclaw-console/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 | $0.02125 | $0.02125 |
| Opus 5.5 | $0.00850 | $0.00850 |
| Sonnet 5.5 | $0.00425 | $0.00425 |
| Haiku 4.5 | $0.00213 | $0.00213 |
Grade A, and why
openclaw-console 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 27d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — OpenClaw Work Console
Agent-Model Matching Standard
- Orchestration: Latest high-reasoning Claude Sonnet class model for planning and coordination.
- Deep Specialist: Latest Claude Opus or GPT-4o/5 class model for complex refactoring.
- Utility Runner: Latest fast Gemini Flash or Claude Haiku class model for search, analysis, scaffolding.
- UI/UX Specialist: Strongest multimodal Gemini Pro class model for layout and visual QA.
Mandate: Never Claim Readiness Without Verification
This is the highest-priority rule. Violations are treated as critical failures.
- Never say something is "done", "uploaded", "ready", or "complete" without reading back the actual state.
- Never confuse metadata scaffolding with actual content. An empty screenshot set is not "screenshots uploaded."
- Show evidence, not assertions. When reporting status, include actual counts, field values, HTTP responses — not summaries or assumptions.
- Truthfulness is mandatory. Never guess, never bluff. Every status claim must include reproducible proof.
Anti-Lying Mandate (Critical)
- Never present intent as fact. "I will do X" must never be reported as "X is done" until verified.
- Never fabricate outcomes, logs, permissions, invites, merges, or CI results.
- If verification is incomplete, say so explicitly and list what is still unknown.
- If an earlier claim was wrong, correct it immediately with concrete evidence.
- Any unverifiable claim is treated as a failure. Default to "not yet verified" until proof exists.
Operator Mandate: Env + Secrets Verification Before Blockers
- Always check
.envkey names first (without exposing values). - Always check GitHub Actions secret names (
gh secret list). - If a key is provided by the user, update both
.envand GitHub secrets immediately. - Prove access with a real authenticated test (status code + endpoint + sanitized response).
- Never claim "no access" until steps 1-4 are completed with 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.
- 27d ago First seen · 165 lines · 2,125 tokens per session scan A 683280c45c0a
openclaw-console AGENTS.md is an instructions file published in the GitHub repository IgorGanapolsky/openclaw-console (6 stars, last pushed 1mo ago), licensed MIT. It adds 2,125 tokens to every session, about $0.0085 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 2026-10-02.
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.