agentmods.dev

agent-squad-python

A guide to the agent-squad Python package, which coordinates several AI assistants in Python programs. It explains when to use one assistant, automatic routing between specialists, fixed step-by-step pipelines, team supervision, and responses grounded in tool data.

In plain words
What is it for?
Use it to build Python applications with specialist assistants, route requests, chain processing steps, delegate work, or keep answers tied to retrieved data.
Why use it?
It helps choose a suitable coordination pattern instead of managing multiple assistants without a clear structure.

Skill for Claude CodeCodex

7.8k 4d ago A scan 113 tokens original Apache-2.0
View the source file 2FastLabs/agent-squad
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 skills/2fastlabs/agent-squad/python
Any agent
npx skills add 2FastLabs/agent-squad --skill python
Clone the repo
git clone --depth 1 https://github.com/2FastLabs/agent-squad

Made for: Claude Code, Codex.

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,697 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00113 $0.04697
Opus 5 $0.00056 $0.02348
Sonnet 5 $0.00023 $0.00939
Haiku 4.5 $0.00011 $0.00470

Measured yesterday against content hash c16cc751be30, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-squad-python 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 yesterday.

The scan reads SKILL.md. This mod also ships 53 executable files (setup.py, src/agent_squad/__init__.py, src/agent_squad/agent_overlap_analyzer.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

python/SKILL.md · 410 lines

How it starts

The opening of the file, as written. The whole thing — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-squad Python — assistant guide

Async-first, dependency-optional multi-agent orchestration framework (Python 3.11+). This is a guide and a map — not an API reference. Read exact signatures from the source (python/src/agent_squad/) and the docs site (docs/src/content/docs/); this file tells you what to use, when, and what to watch out for.

When to use what

  • One assistant — a single Agent subclass; no orchestrator needed, call process_request directly.
  • Several specialists — multiple agents + an AgentSquad orchestrator; the classifier routes each turn to the right agent automatically.
  • Answers must not drift from data (prices, balances, live stock) — GroundedAgent: a gatherer LLM calls tools and sees raw results but never speaks to the user; an isolated presenter LLM writes the reply grounded only on curated facts.
  • Fixed pipeline — ChainAgent: routes the output of one agent as the input to the next, sequentially.
  • Team coordination — SupervisorAgent: a lead BedrockLLMAgent or AnthropicAgent delegates to a team of sub-agents via an internal tool loop, maintaining shared context. Can itself be registered in an AgentSquad.
  • External tool servers — MCPToolProvider (requires agent-squad[mcp]) connects any number of MCP servers (stdio or SSE) and makes their tools available to any agent.

How to install

All third-party integrations are optional extras — never forced on users who don't need them.

pip install agent-squad                  # core only (no LLM runtime)
pip install "agent-squad[aws]"           # + boto3 — BedrockLLMAgent, BedrockClassifier, DynamoDbChatStorage, etc.
pip install "agent-squad[anthropic]"     # + anthropic SDK — AnthropicAgent, AnthropicClassifier
pip install "agent-squad[openai]"        # + openai SDK — OpenAIAgent, OpenAIClassifier
pip install "agent-squad[sql]"           # + libsql-client — SqlChatStorage (Turso/libSQL)
pip install "agent-squad[strands-agents]"# + strands-agents — StrandsAgent
pip install "agent-squad[dakera]"        # + dakera — DakeraRetriever
pip install "agent-squad[mcp]"           # + mcp — MCPToolProvider
pip install "agent-squad[all]"           # everything except strands-agents

Read the full file on GitHub · 410 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 410 lines · 113 tokens per session scan A c16cc751be30

Subscribe to this mod's changes

agent-squad-python is a skill published in the GitHub repository 2FastLabs/agent-squad (7,751 stars, last pushed 4d ago), licensed Apache-2.0. It adds 113 tokens to every session and 4,697 once invoked, about $0.0006 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.

Data and AIDevOps and cloudLanguagesanthropic-claudeawsaws-bedrockaws-cdkaws-lambdachatbot
Related

Other skills, from other repositories

verify-pr

Comprehensive PR readiness check before merge. Run quality checks, tests, CI, documentation, AWS resource cleanup, and code review.

go-to-k/cdkd · 29 tokens

nx-plugin-for-aws

Scaffold and build cloud-native applications on AWS using @aws/nx-plugin generators. Use when the user wants to create workspaces, generate projects, or scaffold infrastructure with the Nx Plugin for AWS.

awslabs/nx-plugin-for-aws · 46 tokens

run-integ

Run integration tests (deploy + destroy) against real AWS. Use when you need to verify cdkd works end-to-end with actual AWS resources.

go-to-k/cdkd · 34 tokens

review-pr

Recommend the right reviewer count for a PR based on size + bias factors. Outputs a concrete plan (inline spot-check / 1 reviewer / 3-axis parallel) plus ready-to-paste Agent dispatch prompts when reviewers are warranted.

go-to-k/cdkd · 49 tokens

cdkd

Install cdkd and use it safely from an AWS CDK project. Use when bootstrapping, synthesizing, diffing, deploying, inspecting, rolling back, migrating, or destroying dev/test stacks with cdkd.

go-to-k/cdkd · 49 tokens

cleanup

Detect and delete leftover AWS resources from cdkd integration tests. Only targets resources matching known cdkd stack name patterns.

go-to-k/cdkd · 27 tokens