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/thesysdev/openclaw-os/agents-mdgit clone --depth 1 https://github.com/thesysdev/openclaw-osWhat 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 | $0.00777 | $0.00777 |
| Opus 5 | $0.00388 | $0.00388 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
openclaw-os 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 2d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents
- ALWAYS use pnpm.
OpenClaw Types
OpenClaw types come from the openclaw npm package via subpath exports:
import { definePluginEntry } from "openclaw/plugin-sdk/plugin-entry"import { ... } from "openclaw/plugin-sdk/core"for API types and helpers- Put
openclawin devDependencies/peerDependencies, NOT dependencies - Plugins are loaded via jiti at runtime — the gateway provides the openclaw module
- Plugins can be raw .ts files (no build step required) since jiti handles TS
Gateway protocol types (browser clients)
The openclaw package does not export gateway protocol types publicly — only plugin-sdk/* paths are available. For browser/frontend clients, copy the required constants and interfaces from the source:
- Client IDs & Modes (typed constants, use these instead of bare strings):
src/gateway/protocol/client-info.ts—GATEWAY_CLIENT_IDS,GATEWAY_CLIENT_MODES - Protocol frame schemas (TypeBox definitions for all RPC payloads):
src/gateway/protocol/schema/protocol-schemas.ts
In this repo these are inlined into packages/claw-client/src/lib/gateway/types.ts with a comment pointing back to the source.
How plugin detection works
The Claw client appends :openclaw-os to its session key (e.g. agent:main:main:openclaw-os). The plugin's before_prompt_build hook checks for this suffix and, when present, prepends the OpenUI Lang system prompt. The agent then streams back component markup which the client renders in real time. Sessions from other clients are unaffected.
Agents → Sessions → Threads mental model
Agent — a named AI persona defined in the OpenClaw gateway config (e.g. main, helper). Returned by agents.list. Agents are fixed; you cannot create or delete them from a client.
Session — a persistent conversation channel addressed by a structured key:
agent:<agentId>:<channel>:<senderId?>
<channel>is typicallymainfor the operator's direct channel<senderId>is an optional suffix that scopes the session further (e.g. per-user, per-client)- The gateway stores message history under this key
- Multiple clients can share a session (same key = same history) or have isolated sessions (different key = separate history)
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.
- 2d ago First seen · 59 lines · 777 tokens per session scan A 889ecca7a607
openclaw-os AGENTS.md is an instructions file published in the GitHub repository thesysdev/openclaw-os (322 stars, last pushed 3mo ago), licensed MIT. It adds 777 tokens to every session, about $0.0039 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
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
spring-ai-agentcore AGENTS.md
Instructions for spring-ai-community/spring-ai-agentcore, covering agents.md, project overview, architecture, key components and artifact store classes.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
agentoscope AGENTS.md
Instructions for rafaelcg/agentoscope, covering agentoscope — agent instructions, what this is, layout, commands and conventions.