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/enderfga/claw-orchestrator/claude-mdgit clone --depth 1 https://github.com/Enderfga/claw-orchestratorWrote 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/enderfga/claw-orchestrator/claude-md)<a href="https://agentmods.dev/instructions/enderfga/claw-orchestrator/claude-md"><img src="https://agentmods.dev/badge/instructions/enderfga/claw-orchestrator/claude-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 5.1 | $0.03331 | $0.03331 |
| Opus 5 | $0.01665 | $0.01665 |
| Sonnet 5 | $0.00666 | $0.00666 |
| Haiku 4.5 | $0.00333 | $0.00333 |
Grade C, and why
claw-orchestrator CLAUDE.md scanned grade C with 2 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 today.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
The `build` script must clean `dist/` first (it does: `rm -rf dist && tsc && ...`). Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Plugin installation requires `--dangerously-force-unsafe-install` (child_process usage) How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — claw-orchestrator
This file provides context for Claude Code when working on this project.
Architecture
Claw Orchestrator wraps coding CLIs (Claude Code, Codex, Antigravity, Grok Build, plus arbitrary custom CLIs) into a managed, programmable session layer for claw-style agent systems. Runs as a standalone CLI/server, with first-class OpenClaw plugin support. Key source files:
| File | Purpose |
|---|---|
src/index.ts |
Plugin entry — registers all 77 canonical tools |
src/session-manager.ts |
Core orchestrator — session lifecycle, council, ultraplan/ultrareview |
src/base-oneshot-session.ts |
Abstract base class for one-shot (process-per-send) engines |
src/persistent-session.ts |
Claude Code CLI wrapper (spawn, JSON protocol, stream parsing) |
src/persistent-codex-session.ts |
Codex CLI wrapper (codex exec --full-auto) |
src/persistent-gemini-session.ts |
Gemini CLI wrapper — legacy: Gemini CLI is sunset, superseded by Antigravity (agy). Kept working for existing callers; not documented as an option and not version-tracked. |
src/persistent-agy-session.ts |
Google Antigravity CLI wrapper (agy -p, plain text, log-harvested conversation resume) |
src/persistent-cursor-session.ts |
Cursor Agent CLI wrapper — legacy: superseded in this lineup by Grok Build (grok). Kept working for existing callers; not documented as an option and not version-tracked. Binary is cursor-agent, never the contested agent name. |
src/persistent-grok-session.ts |
Grok Build CLI wrapper (grok -p --output-format json) — engine-reported cost, resumable session id |
src/persistent-opencode-session.ts |
sst/opencode CLI wrapper (opencode run --format json) |
src/persistent-custom-session.ts |
Custom engine — any CLI via user-provided CustomEngineConfig |
src/council.ts |
Multi-agent collaboration engine with git worktree isolation and post-processing |
src/consensus.ts |
Consensus voting parser for council |
src/kernel/types.ts |
One state vocabulary — RunState, RunOutcome, WorkflowSpec, node specs |
src/kernel/engine.ts |
The run kernel — checkpointed execution, resume, retry, timeout, cancel, steer |
src/kernel/store.ts |
Durable run store (~/.claw-orchestrator/wf/<runId>/) — guards, leases, and the one storage transaction |
src/kernel/file-lock.ts |
The one exclusive file lock, shared by the run store and the ultraapp build queue |
src/kernel/exec.ts |
The single child-process wrapper — non-throwing, timeout kills the process group, output capped |
src/kernel/agent-step.ts |
The single start→send→stop lifecycle; success reads turnsSucceeded |
src/kernel/nodes/ |
One executor per node kind; thin wrappers over the existing engines |
src/kernel/templates/ |
Built-in workflows (solve, council, fanout, ultraapp) |
src/verify/contract.ts |
AcceptanceContract + CheckSpec, and the normalizer that keeps agent-authored contracts out |
src/verify/runner.ts |
Runs the checks — the generalisation of ultraapp's fix-on-failure |
src/verify/baseline.ts |
Base-commit capture and change sets that include created files |
src/verify/evidence.ts |
Evidence bundles — verdict, per-check logs, patch, screenshots |
src/run-ledger.ts |
Durable per-turn record (~/.claw-orchestrator/runs/*.jsonl) — append, query, summarize, verdict join |
src/budget.ts |
Runtime-enforced maxBudgetUsd spend cap (all engines, not just Claude Code) |
src/models.ts |
Centralized model registry — pricing, aliases, engine/provider mapping |
src/engine-presets.ts |
Community engine presets — tiering, provenance validation, customEngine id resolution |
src/types.ts |
Shared types, interfaces; re-exports from models.ts |
src/logger.ts |
Structured Logger interface + console implementation |
src/circuit-breaker.ts |
Engine failure tracking with exponential backoff |
src/inbox-manager.ts |
Cross-session messaging (inbox) manager |
src/embedded-server.ts |
HTTP server for standalone/CLI usage |
src/openai-compat.ts |
OpenAI-compatible /v1/chat/completions endpoint |
src/acp-server.ts |
Agent Client Protocol adapter — runs the orchestrator as an ACP agent |
src/proxy/ |
Multi-model proxy (Gemini, GPT via Anthropic format translation) |
bin/cli.ts |
CLI entry point (commander-based) |
bin/acp-server.ts |
ACP stdio entry (clawo-acp / clawo acp) |
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.
- today Changed · +2 lines · +37 tokens per session feafdfc2d271
- yesterday Changed · +13 lines · +187 tokens per session e14cefe982e7
- 5d ago Changed · +27 tokens per session ffd6a816f008
- 6d ago First seen · 217 lines · 3,080 tokens per session scan C 7beb9fd1a680
claw-orchestrator CLAUDE.md is an instructions file published in the GitHub repository Enderfga/claw-orchestrator (565 stars, last pushed yesterday), licensed MIT. It adds 3,331 tokens to every session, about $0.0167 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
Codewhale AGENTS.md
AGENTS.md instructions for Hmbown/Codewhale, covering codewhale agent guidance, the ponytail method, working rules, landing other people's work and merging under a gate.
Codewhale CLAUDE.md
Claude Code instructions for Hmbown/Codewhale, a project described as: Open-source coding agent for your terminal, built in Rust and on a journey of continuous community improvement. Issues and PRs welcome.
mission-control CLAUDE.md
Claude Code instructions for builderz-labs/mission-control, covering mission control, prerequisites, setup, run and docker.
alook AGENTS.md
AGENTS.md instructions for alookai/alook, covering alook, navigation, must, release — unified version bump and e2e ui (browser tests).
alook CLAUDE.md
Claude Code instructions for alookai/alook, a project described as: Rooms for people and agents.
flow CLAUDE.md
Claude Code instructions for AixleHQ/flow, covering claude.md, documentation index, before pushing a branch or opening/updating a pr, docker is required and test parallelization.