What is squadrant CLAUDE.md?

Project instructions for Squadrant, a system that coordinates multiple coding agents and supports different agent tools. It describes the repository structure, shared packages, and rules for keeping features usable beyond Claude Code.

Use it when adding or changing agent runtimes, workspaces, notifications, command-line features, shared packages, or portable skills in Squadrant.

It helps agents follow the project’s architecture and ownership boundaries instead of adding changes tied to only one coding agent. This reduces conflicting edits and keeps the system portable.

How tu11aa/squadrant configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tu11aa/squadrant. 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/tu11aa/squadrant/develop/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tu11aa/squadrant

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tu11aa/squadrant/claude-md/github.svg)](https://agentmods.dev/instructions/tu11aa/squadrant/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tu11aa/squadrant/claude-md"><img src="https://agentmods.dev/badge/instructions/tu11aa/squadrant/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tu11aa/squadrant/claude-md"><img src="https://agentmods.dev/badge/instructions/tu11aa/squadrant/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,085 This file is loaded in full into every session.

When invoked 3,085 The same file — it is already loaded in full.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin 97% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.03085	$0.03085
Opus 5.5	$0.01234	$0.01234
Sonnet 5.5	$0.00617	$0.00617
Haiku 4.5	$0.00309	$0.00309

Measured 7d ago against content hash 890a8a29e137, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

squadrant CLAUDE.md scanned grade B with 1 finding 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

## Managed `~/.claude/settings.json` (#615)

Origin

This is a copy

97% identical to squadrant AGENTS.md — 1,486 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Direction: Multi-Agent

Squadrant is a multi-agent orchestration layer, not a Claude-Code-only tool. Claude Code is the reference implementation today; Codex, Cursor, and Gemini CLI are supported (or in progress) through the runtime driver abstraction and the upcoming cross-agent projection layer (issue #31).

When working on squadrant:

Prefer AGENTS.md as the canonical instruction format. CLAUDE.md is becoming a thin wrapper.
When adding agent-facing features, ask: "does this work for non-Claude agents too?" If not, file a follow-up issue to generalize it.
Don't add Claude-only surface area without a migration path. The three plugin slots (runtime / workspace / notifier) exist specifically to avoid this.
Skills in plugin/skills/ are portable markdown — Claude Code reads them via the Skill tool; other agents read them via AGENTS.md inclusion.

Full direction statement: docs/specs/2026-04-24-multi-agent-direction.md.

Repository layout

Six packages in a one-way DAG: shared ◄ core ◄ {agents, workspaces, web} ◄ cli

Package	Owns
`@squadrant/shared`	Config schema, types, constants — leaf, zero internal deps
`@squadrant/core`	Daemon, state-machine, protocol, `AgentDriver` interface
`@squadrant/agents`	AI driver seam: claude / codex / opencode / gemini
`@squadrant/workspaces`	Runtime (cmux), workspace (obsidian), notifier drivers
`@squadrant/web`	Observability dashboard (bundled HTML/JS)
`@squadrant/cli`	Commands, bin entry, daemon host — root package

Build outputs: dist/index.js (CLI bin) · dist/squadrantd.js (daemon). See architecture diagram.

Telegram (opt-in, #65)

Two-way Telegram lives in @squadrant/core (src/telegram/*: client/format/state/bridge/setup) and is wired into the daemon by the CLI host (squadrantd.ts) — a daemon-internal TelegramBridge, not a separate process. Outbound crew lifecycle events push to a per-project forum topic; inbound replies become a captain.message mailbox entry delivered to the captain pane. It is constructed only when config.telegram is present (zero behavior change otherwise) and uses plain fetch — no runtime SDK (@grammyjs/types is a dev-only type dep). Set up via squadrant telegram setup (interactive wizard) then squadrant telegram link <project> / squadrant telegram status; full guide + config block in docs/reference.md.

Read the full file on GitHub · 92 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.

7d ago Changed · +9 tokens per session 890a8a29e137
9d ago Changed · +1 lines · +89 tokens per session e52ee6d23a2d
17d ago Changed · +1 lines · +127 tokens per session 421f5b69ca57
29d ago Changed · +23 tokens per session 31385f491f38
1mo ago Changed · +36 tokens per session eecd6ea52341
2mo ago Changed · +157 tokens per session 0f3e937124d4
2mo ago First seen · 90 lines · 2,644 tokens per session scan B fbe9981943a4

Subscribe to this mod's changes

squadrant CLAUDE.md is an instructions file published in the GitHub repository tu11aa/squadrant (2 stars, last pushed yesterday), licensed MIT. It adds 3,085 tokens to every session, about $0.0123 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 97% identical to squadrant AGENTS.md, differing in 1,486 lines, and is treated as a copy.

Building agents

squadrant CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
squadrant CLAUDE.mdtu11aa/squadrant	Instructions file	2	yesterday	MIT	B	3,085	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

squadrant: Instructions file for Claude Code