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/mlund01/squadron/claude-mdgit clone --depth 1 https://github.com/mlund01/squadronWrote 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/mlund01/squadron/claude-md)<a href="https://agentmods.dev/instructions/mlund01/squadron/claude-md"><img src="https://agentmods.dev/badge/instructions/mlund01/squadron/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 | $0.13350 | $0.13350 |
| Opus 5 | $0.06675 | $0.06675 |
| Sonnet 5 | $0.02670 | $0.02670 |
| Haiku 4.5 | $0.01335 | $0.01335 |
Grade C, and why
squadron CLAUDE.md scanned grade C 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
on subsequent loads. Force a reinstall by `rm -rf .squadron/mcp/<name>/<version>/`. How it starts
The opening of the file, as written. The whole thing — 1,246 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.
Build & Run Commands
go build -o squadron ./cmd/cli # Build the CLI
./squadron init # Initialize encrypted vault
./squadron verify <path> # Validate HCL config
./squadron chat -c <path> <agent_name> # Start chat with an agent
./squadron mission -c <path> <mission> # Run a mission
./squadron mission -c <path> -d <mission> # Run with debug logging
./squadron mission --resume <id> -c <path> <mission> # Resume a failed mission
./squadron vars set <name> <value> # Set a variable
./squadron vars get <name> # Get a variable
./squadron vars list # List all variables
./squadron serve -c <path> # Connect to command center (requires command_center block)
./squadron serve -c <path> -w # Launch local command center + connect
./squadron serve -c <path> -w --cc-port 9090 # Custom command center port
./squadron serve -c <path> -w --no-browser # Launch without opening browser
./squadron mcp status # Show OAuth status for configured MCP servers
./squadron mcp login <name> # Authorize an MCP server via OAuth
./squadron mcp logout <name> # Forget stored OAuth token for an MCP server
./squadron upgrade # Upgrade to latest release
./squadron upgrade --version v0.0.13 # Upgrade to specific version
./squadron version # Print current version
./squadron docs [output-dir] # Extract docs to local folder
./squadron plugin tools <path> # List plugin tools
./squadron plugin call <path> <tool> <json># Call a plugin tool
./squadron plugin info <path> <tool> # Get plugin tool info
./squadron plugin build <source> # Build a plugin from source
Architecture Overview
Squadron is a declarative framework for building and running AI agent workflows. LLM-powered agents, tools, plugins, and multi-step missions are defined entirely in HCL configuration files — no code required. Agents reason and act autonomously using a two-tier architecture: commanders orchestrate tasks while agents execute tool calls via native function calling.
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.
- 3d ago First seen · 1,246 lines · 13,350 tokens per session scan C 67ff90a0904d
squadron CLAUDE.md is an instructions file published in the GitHub repository mlund01/squadron (8 stars, last pushed 14d ago), licensed MIT. It adds 13,350 tokens to every session, about $0.0668 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
AgenticX AGENTS.md
Instructions for DemonDamon/AgenticX, covering agents.md, learned user preferences and learned workspace facts.
GPT-RAG release.instructions.md
Instructions for Azure/GPT-RAG, a project described as: Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
agentic-harness AGENTS.md
Instructions for frangelbarrera/agentic-harness, covering project context, architecture in 30 seconds, non-negotiable rules (from manifesto.md), coding standards and commit conventions.
initrunner CLAUDE.md
Instructions for vladkesler/initrunner, covering initrunner and project map.
dsh-codex-app-server AGENTS.md
Instructions for LyleMi/dsh-codex-app-server, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.