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/raulvidis/openclaw-multi-agent-kit/agents-mdgit clone --depth 1 https://github.com/raulvidis/openclaw-multi-agent-kitWhat 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 | $0.00470 | $0.00470 |
| Opus 5 | $0.00235 | $0.00235 |
| Sonnet 5 | $0.00094 | $0.00094 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
openclaw-multi-agent-kit 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 yesterday.
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
READ ./.agents/AGENTS.base.md BEFORE ANYTHING (skip if missing).
READ ./AGENTS.local.md AFTER this file if present (machine-only overrides, git-ignored).
Work style: telegraph; noun-phrases ok; drop grammar; min tokens. Repo-specific hard rules only. Shared rules (Reviews, PR/CI, Git, Runtime Safety, Workflows) live in AGENTS.base.md.
Core
- Template/docs-only repo — nothing executes; everything is markdown/JSON/JSONC copied into OpenClaw workspaces
- Public repo — no secrets, tokens, internal IPs, or machine-specific paths in tracked files
- docs/architecture.md carries the structure tree + platform concepts — update it whenever files, structure, or config keys change (was CLAUDE.md's job)
- Canonical OpenClaw docs = docs.openclaw.ai — verify config keys against the live reference before editing schema-related templates
Project Defaults (repo-specific)
- Model-agnostic: never pin model ids in templates or example configs; agents inherit the runtime default
- YAML frontmatter at line 1 of every SOUL.md / SKILL.md — never prepend H1s or blockquotes above it
- Placeholders stay placeholders:
[Your ... Name],YOUR_*,{WORKSPACE}— never real values examples/full-team.json(10 core agents) andexamples/minimal-team.json(3) must stay in sync, validate as JSON, and omitmodelfields- Multi-agent topics: ALL bots
requireMention: true; orchestratorenabled: falseon topics owned by others - Cross-agent flows follow docs/inter-agent-handoff-standard.md (HANDOFF/ACK/DONE/BLOCKED)
- Skills format: YAML frontmatter (
name,description,version) + markdown body with## Install - Editing checklists (what else to touch when adding agents/docs/skills/config keys): docs/architecture.md § Editing guidelines
- INSTRUCTIONS.md = single source of truth for the AI-readable setup flow
Workflows (repo-specific)
- No release pipeline (docs-only kit) — no
releasecommand; curate CHANGELOG per landed series viachangelog
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.
- yesterday First seen · 29 lines · 470 tokens per session scan A 7cf964a2769c
openclaw-multi-agent-kit AGENTS.md is an instructions file published in the GitHub repository raulvidis/openclaw-multi-agent-kit (395 stars, last pushed 1mo ago), licensed MIT. It adds 470 tokens to every session, about $0.0024 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.