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/agents-squads/squads-cli/agents-mdgit clone --depth 1 https://github.com/agents-squads/squads-cliWhat 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 | $0.01190 | $0.01190 |
| Opus 5 | $0.00595 | $0.00595 |
| Sonnet 5 | $0.00238 | $0.00238 |
| Haiku 4.5 | $0.00119 | $0.00119 |
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.
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 bedocs/agent-contract.md— the typed contract every agent runs underdocs/governance.md— permission and approval modeltemplates/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 |
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.
- 2d ago First seen · 113 lines · 1,190 tokens per session scan A d91c444e7135
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.
Other instructions, from other repositories
agent-framework copilot-instructions.md
Instructions for microsoft/agent-framework, covering github copilot instructions, repository structure and architectural decision records (adrs).
agent-framework python.instructions.md
Instructions for microsoft/agent-framework: See AGENTS.md for project structure and package documentation. Detailed conventions are in the agent skills under .github/skills/.
jido AGENTS.md
Instructions for agentjido/jido, covering agents.md - jido guide, intent, runtime baseline, commands and work management.
agent-starter-kit AGENTS.md
Instructions for ntorga/agent-starter-kit, covering agents.md, honesty and ambiguity, code shape, function extraction and duplication.
paperclip-plugin-company-wizard CLAUDE.md
Instructions for Yesterday-AI/paperclip-plugin-company-wizard, covering claude.md, what this is, commands, architecture and source layout.
paperclip-plugin-company-wizard AGENTS.md
Instructions for Yesterday-AI/paperclip-plugin-company-wizard, covering company wizard — project vision, what, why, core idea: gracefully optimistic architecture and design principles.