cli-dispatch: Instructions file for Claude Code

CLAUDE.md

cli-dispatch CLAUDE.md is an instructions file for Claude Code from rbinar/cli-dispatch. It costs 7,566 tokens per session, scanned A, original, MIT.

Project instructions for cli-dispatch, a Claude Code plugin that delegates tasks to other coding-agent command-line tools. They explain the repository, its commands, hooks, skills, and testing practices.

In plain words
What is it for?
Use them when modifying cli-dispatch, running individual tests, checking shell scripts, or understanding how its external worker commands are organised.
Why use it?
They give coding agents the project-specific context needed to work safely in a repository without a package build step.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is rbinar/cli-dispatch's own configuration. It tells Claude Code how to work on cli-dispatch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cli-dispatch configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to rbinar/cli-dispatch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rbinar/cli-dispatch/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rbinar/cli-dispatch

Made for: Claude Code.

Wrote 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.

agentmods badge for cli-dispatch CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rbinar/cli-dispatch/claude-md/github.svg)](https://agentmods.dev/instructions/rbinar/cli-dispatch/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rbinar/cli-dispatch/claude-md"><img src="https://agentmods.dev/badge/instructions/rbinar/cli-dispatch/claude-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.

agentmods 80×15 button for cli-dispatch CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rbinar/cli-dispatch/claude-md"><img src="https://agentmods.dev/badge/instructions/rbinar/cli-dispatch/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,566 This file is loaded in full into every session.
When invoked 7,566 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.07566 $0.07566
Opus 5.5 $0.03026 $0.03026
Sonnet 5.5 $0.01513 $0.01513
Haiku 4.5 $0.00757 $0.00757

Measured today against content hash f0f2d86eb3b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cli-dispatch CLAUDE.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 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.

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.

CLAUDE.md · 379 lines

How it starts

The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this repo is

cli-dispatch is a Claude Code plugin (not an npm package — there is no package.json, no build step, no bundler; the demo video source under assets/demo-src/ is gitignored, local only). It ships slash commands, a SessionStart hook, a skill, and standalone CLI scripts that let Claude Code delegate work to six external "worker" backends — DeepSeek (via claude pointed at DeepSeek's API), Antigravity/Gemini (agy), OpenAI Codex (codex), OpenCode (opencode, via OpenRouter), GitHub Copilot (copilot), and Ollama (ol: the same claude pointed at a local Ollama, selected by CLAUDE_DS_BACKEND=ollama inside the DeepSeek pipeline; ol-agent is a shim over ds-agent) — since Claude Code's built-in subagent tool only supports Anthropic models. It ships one thin subagent, agents/runner.md (cli-dispatch:runner, haiku, Bash-only — a forwarder, see "The deterministic runner + escalation path" below); the five agents/*-runner.md LLM babysitters were deleted in 4.0.0.

Everything the plugin installs lives under plugins/cli-dispatch/:

  • commands/*.md — slash commands (/cli-dispatch:*). Each is markdown with a fenced bash (and sometimes PowerShell) block that Claude Code executes directly — there is no compiled command layer. Read-only commands should instead pre-execute an extracted script via a leading !`bash "${CLAUDE_PLUGIN_ROOT}/scripts/<name>.sh"` line: embedded shell is paid twice (once as the markdown's input tokens, again as output when the model re-emits it verbatim as a Bash tool call), while a ! line runs before the model sees anything and injects only the output. doctor, sessions and help are converted; balance was too until 6.1.5 and now runs its script from one fenced call (see "Non-obvious constraints"); clean is a thin call to the installed cli-dispatch-clean binary (not pre-executed — it mutates); the rest are not yet. Two traps: ${CLAUDE_PLUGIN_ROOT} is interpolated into the ! command string but not exported into the subprocess, so a script that needs it must take it as an argument (this silently killed doctor's staleness check in 4.9.0); and a mutating command must never pre-execute its mutation — clean --schedule must not pre-execute install/uninstall either; those stay a deliberate call.
  • scripts/ — the actual installed CLIs. Per-backend: ds-agent, ag-agent, cx-agent, oc-agent, cp-agent + their *-stream siblings and *-worktree-run.sh runners. Backend-agnostic: cli-dispatch-run (the deterministic runner — the delegation path), cli-dispatch-wait, cli-dispatch-clean, cli-dispatch-gain, cli-dispatch-run-summary.sh (the compact verdict summary shared by /cli-dispatch:run and a detached run's summary.txt; unlike the pre-execution scripts below, install.sh DOES copy it — to ~/.local/share/cli-dispatch/, not PATH — because the installed runner needs it), and cli-dispatch-statusline.sh (the [CD] statusline fragment — bash-only by design, glob-loaded from the plugin cache rather than installed to ~/.local/bin). The pre-execution scripts (cli-dispatch-doctor.sh, cli-dispatch-sessions.sh, cli-dispatch-balance.sh, cli-dispatch-help.sh, cli-dispatch-clean-schedule.sh + its .ps1 twin; cli-dispatch-status.ps1 stays only as doctor's native-Windows fallback) likewise run from the plugin cache and are not installed, so they can never go stale relative to the plugin — do not add them to install.sh. setup-form.mjs (the one-shot browser form for keys and model names) follows the same rule — install.sh/install.ps1/setup.md run it from the plugin dir — and being node it has no .ps1 twin; cli-dispatch-pane-read.mjs (the /cli-dispatch-runs pane's byte-range file reader, run by the mod) follows it too. Bash/PowerShell wrappers around Node engines (*-stream-parse.mjs parsers, verdict-writer.mjs, gain-report.mjs, drift-report.mjs, cli-dispatch-clean.mjs). install.sh/install.ps1 copy these into ~/.local/bin (wrappers) and ~/.local/share/cli-dispatch/ (engines + shared libs).
  • hooks/hooks.json — the SessionStart hook registration. Wires scripts/policy-inject.mjs to all five matchers (startup/resume/clear/compact/fork); compact and fork matter because compaction drops the injected policy from a long session's context (#118).
  • hooks/cli-dispatch-mod.tsx — the plugin's mod (Claude Code 2.1.287+), named under modules in the same hooks.json: a band above the prompt with this session's workers; a tool.call guard that refuses Edit/Write into a repo while a worktree run for it is live (the leak check would blame the worker); and the mcp__cli-dispatch__dispatch tool (6.3.0), which runs cli-dispatch-run --detach + cli-dispatch-wait --run itself in one tool call — the runner agent's job with no LLM turns. It is not registered inside a worker (CLI_DISPATCH_WORKER=1). Its state contract is types/index.d.ts (named as types in plugin.json); its tests are tests/mod.test.ts. /cli-dispatch-runs is its run monitor pane (this session's runs, one chronological Flow built from transcript.jsonl in its own frame, which the pane's ui.scroll hook scrolls, masked); the band's liveness test is isRunAlive. It reads session dirs with the same root resolution and 90 s liveness window as cli-dispatch-statusline.sh.
  • skills/ds-delegate/SKILL.md — the ds-delegate skill.

Read the full file on GitHub · 379 lines

Changes

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.

  1. today Changed · +2 lines · +74 tokens per session f0f2d86eb3b7
  2. yesterday Changed · +20 lines · +526 tokens per session 497d098563f2
  3. 8d ago Changed · +22 lines · +504 tokens per session 160ab204a6e9
  4. 9d ago Changed · +6 lines · +133 tokens per session 67e6d937628a
  5. 12d ago Changed · +9 lines · +236 tokens per session 43dd33f4d8f0
  6. 13d ago Changed · +23 lines · +606 tokens per session 2f2f32f02ceb
  7. 15d ago Changed · +25 lines · +546 tokens per session 0c8bc58fbd1c
  8. 1mo ago First seen · 272 lines · 4,941 tokens per session scan A 7acfb584b690

Subscribe to this mod's changes

cli-dispatch CLAUDE.md is an instructions file published in the GitHub repository rbinar/cli-dispatch (10 stars, last pushed today), licensed MIT. It adds 7,566 tokens to every session, about $0.0303 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 2026-08-31.

Related

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).

microsoft/vscode · 9,649 tokens

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.

vercel/next.js · 7,257 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

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.

deepseek-ai/deepseek-harness · 4,159 tokens