squads-cli AGENTS.md

Repository instructions for agents working on squads-cli, a command-line tool that organizes autonomous AI agents into teams called squads. They explain the project structure, specifications, testing expectations, and permission rules.

In plain words
What is it for?
Use them when changing squads-cli, especially to read the relevant architecture, philosophy, agent contract, governance, and scaffolded-project instructions before coding.
Why use it?
They give coding agents one source of truth before making non-trivial changes. This reduces the chance of implementing code that conflicts with the product’s documented design or governance.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/agents-squads/squads-cli/agents-md
Clone the repo
git clone --depth 1 https://github.com/agents-squads/squads-cli

Made for: Codex, OpenCode.

Per session 1,190 This file is loaded in full into every session.
When invoked 1,190 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01190 $0.01190
Opus 5 $0.00595 $0.00595
Sonnet 5 $0.00238 $0.00238
Haiku 4.5 $0.00119 $0.00119

Measured 2d ago against content hash d91c444e7135, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

squads-cli 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.

AGENTS.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Guidance for AI coding agents working on this repository. This is the single source of truth — CLAUDE.md imports it.

Specs — read before non-trivial changes

The product is spec'd; changes that contradict a spec need a founder-visible issue first, not code. Canonical set:

  • docs/architecture.md — how squads works under the hood (files, context cascade, roles, feedback loop)
  • docs/philosophy.md — what this product is and refuses to be
  • docs/agent-contract.md — the typed contract every agent runs under
  • docs/governance.md — permission and approval model
  • templates/seed/skills/squads-cli/SKILL.md — the operating loop as taught to every scaffolded project

What This Is

squads-cli is a CLI orchestrator for autonomous AI agent teams. It organizes agents into squads (domain-aligned teams), manages their context and memory, and dispatches them via native AI CLIs (claude, gemini, etc.).

The CLI is open source. Agents are the primary consumers — after squads run dispatches an agent, it calls CLI commands to read context, persist memory, and coordinate with other agents.

Repository Structure

src/
├── cli.ts              # All command registrations (Commander.js, lazy imports)
├── commands/            # One file per command — start here for any command change
├── lib/                 # Shared logic (parsing, context, memory, git, providers)
templates/               # Files generated by `squads init`
test/                    # Unit + E2E tests (vitest)

Key files by concern:

Concern File
Squad/agent discovery src/lib/squad-parser.ts
Context injection src/lib/run-context.ts
Agent execution src/commands/run.ts, src/lib/execution-engine.ts
Multi-agent conversation src/lib/conversation.ts, src/lib/workflow.ts
Provider CLIs src/lib/llm-clis.ts (integration), src/lib/providers.ts (registry + pricing)
Memory read/write src/lib/memory.ts
Git / GitHub src/lib/git.ts, src/lib/github.ts (gh CLI + bot identity)
Observability src/lib/observability.ts, src/lib/telemetry.ts
Terminal output src/lib/terminal.ts
Command registration src/cli.ts

Read the full file on GitHub · 113 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. 2d ago First seen · 113 lines · 1,190 tokens per session scan A d91c444e7135

Subscribe to this mod's changes

squads-cli AGENTS.md is an instructions file published in the GitHub repository agents-squads/squads-cli (51 stars, last pushed 18d ago), licensed MIT. It adds 1,190 tokens to every session, about $0.0060 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.