Agent Squad is a framework that routes each user request to an appropriate specialized AI agent while preserving conversation context. It is used to build multi-agent applications in Python, TypeScript, or Swift, with support for custom agents and pre-built integrations.
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 skills add 2FastLabs/agent-squad --skill typescriptgit clone --depth 1 https://github.com/2FastLabs/agent-squadWrote 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/skills/2fastlabs/agent-squad/typescript)<a href="https://agentmods.dev/skills/2fastlabs/agent-squad/typescript"><img src="https://agentmods.dev/badge/skills/2fastlabs/agent-squad/typescript/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.
<a href="https://agentmods.dev/skills/2fastlabs/agent-squad/typescript"><img src="https://agentmods.dev/badge/skills/2fastlabs/agent-squad/typescript.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00087 | $0.04310 |
| Opus 5.5 | $0.00035 | $0.01724 |
| Sonnet 5.5 | $0.00017 | $0.00862 |
| Haiku 4.5 | $0.00009 | $0.00431 |
Grade A, and why
agent-squad-typescript 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 1mo 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-squad TypeScript — assistant guide
Node.js / TypeScript multi-agent orchestration framework (npm package agent-squad). All public
symbols are exported from a single barrel typescript/src/index.ts. This file is guidance and a
map — not an API reference. Read exact signatures from
typescript/src/ and worked recipes from 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
Agentsubclass +AgentSquadwith no routing. Or skip the orchestrator entirely and callagent.processRequest(...)directly. - Several specialists → multiple agents registered with
orchestrator.addAgent(agent), a classifier routes each turn. - Answers must not drift from data (prices, balances, live lookups) →
GroundedAgent: a gatherer LLM calls tools, an isolated presenter LLM speaks only from the curated results. - Fixed pipeline →
ChainAgent: each agent's output is the next agent's input. - One lead LLM coordinating a team →
SupervisorAgent: the lead calls sub-agents as tools. - External tools via MCP →
MCPToolProvider(async factory pattern, optional peer dep). - RAG context → attach a
Retrieverto any agent that supportsretriever?in its options.
How to install
npm install agent-squad
Optional peer dependencies — install only what you use:
| Package | Used by |
|---|---|
@aws-sdk/client-bedrock-runtime |
BedrockLLMAgent, BedrockClassifier (already a hard dep in current releases) |
@anthropic-ai/sdk |
AnthropicAgent, AnthropicClassifier (already a hard dep) |
openai |
OpenAIAgent, OpenAIClassifier (already a hard dep) |
@modelcontextprotocol/sdk |
MCPToolProvider — lazy await import() at connect time |
@dakera-ai/dakera |
DakeraRetriever — lazy require() at construction time |
@modelcontextprotocol/sdk and @dakera-ai/dakera are the only two true optional peer deps;
everything else ships as a hard dependency at the moment.
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.
- .npmignore 659 B
- eslint.config.mjs 949 B runs code
- jest.config.js 200 B runs code
- package-lock.json 275 KB
- package.json 2.3 KB
- README.md 9.9 KB
- src/agentOverlapAnalyzer.ts 4.9 KB runs code
- src/agents/agent.ts 9.5 KB runs code
- src/agents/amazonBedrockAgent.ts 5.4 KB runs code
- src/agents/anthropicAgent.ts 17 KB runs code
- src/agents/bedrockFlowsAgent.ts 4.4 KB runs code
- src/agents/bedrockInlineAgent.ts 14 KB runs code
- src/agents/bedrockLLMAgent.ts 18 KB runs code
- src/agents/bedrockTranslatorAgent.ts 5.3 KB runs code
- src/agents/chainAgent.ts 4.0 KB runs code
- src/agents/comprehendFilterAgent.ts 9.6 KB runs code
- src/agents/groundedAgent.ts 12 KB runs code
- src/agents/lambdaAgent.ts 2.7 KB runs code
- src/agents/lexBotAgent.ts 3.4 KB runs code
- src/agents/openAIAgent.ts 7.1 KB runs code
- src/agents/supervisorAgent.ts 11 KB runs code
- src/classifiers/anthropicClassifier.ts 4.4 KB runs code
- src/classifiers/bedrockClassifier.ts 6.6 KB runs code
- src/classifiers/classifier.ts 11 KB runs code
- src/classifiers/jevClassifier.ts 12 KB runs code
- src/classifiers/openAIClassifier.ts 4.6 KB runs code
- src/common/src/awsSdkUtils.ts 3.7 KB runs code
- src/common/src/types/awsSdk.ts 553 B runs code
- src/common/src/version.ts 84 B runs code
- src/index.ts 3.1 KB runs code
- src/orchestrator.ts 19 KB runs code
- src/retrievers/AmazonKBRetriever.ts 4.9 KB runs code
- src/retrievers/DakeraRetriever.ts 4.5 KB runs code
- src/retrievers/retriever.ts 1.8 KB runs code
- src/storage/chatStorage.ts 1.2 KB runs code
- src/storage/dynamoDbChatStorage.ts 4.9 KB runs code
- src/storage/memoryChatStorage.ts 2.8 KB runs code
- src/storage/sqlChatStorage.ts 6.0 KB runs code
- src/storage/summarizingChatStorage.ts 4.2 KB runs code
- src/tools/mcpToolProvider.ts 19 KB runs code
- src/types/index.ts 1.8 KB runs code
- src/utils/chatUtils.ts 816 B runs code
- src/utils/helpers.ts 2.0 KB runs code
- src/utils/logger.ts 3.4 KB runs code
- src/utils/tool.ts 7.6 KB runs code
- src/utils/ui.ts 1.4 KB runs code
- tests/agents/Agents.test.ts 3.5 KB runs code
- tests/agents/groundedAgent.test.ts 16 KB runs code
- tests/agents/LambdaAgent.test.ts 6.8 KB runs code
- tests/agents/OpenAi.test.ts 4.0 KB runs code
- tests/classifiers/AnthropicClassifier.test.ts 4.7 KB runs code
- tests/classifiers/BedrockClassifier.test.ts 3.9 KB runs code
- tests/classifiers/Classifier.test.ts 7.8 KB runs code
- tests/classifiers/JevClassifier.test.ts 16 KB runs code
- tests/classifiers/OpenAIClassifier.test.ts 6.3 KB runs code
- tests/mcpToolProvider.test.ts 26 KB runs code
- tests/mcpToolProviderV2.test.ts 6.3 KB runs code
- tests/mcpToolProviderV2Partial.test.ts 1.5 KB runs code
- tests/mock/mockAgent.ts 1.4 KB runs code
- tests/Orchestrator.test.ts 9.2 KB runs code
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.
- 1mo ago First seen · 355 lines · 87 tokens per session scan A 3e19394a998a
agent-squad-typescript is a skill published in the GitHub repository 2FastLabs/agent-squad (7,789 stars, last pushed 9d ago), licensed Apache-2.0. It adds 87 tokens to every session and 4,310 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
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.
sandy
Run TypeScript scripts in sandboxed microVMs or Docker containers with AWS SDK access via IMDS. Use when investigating AWS resources, running read-only queries, or executing TypeScript automation that needs AWS credentials.
aws-integration-testing
Generate comprehensive integration tests for AWS Python Lambda functions, Batch jobs, and services that interact with S3, DynamoDB, RDS/PostgreSQL, SQS, SNS, EventBridge, Kinesis, and other AWS services. Uses moto for in-process AWS mocking and testcontainers for real database testing. Reads the handler source code to…
wraps-workflows
Build email and SMS automation workflows using the @wraps.dev/client TypeScript DSL. Covers triggers, steps, branching, cascades, and the full defineWorkflow API.
typescript-patterns
TypeScript patterns and conventions for safer, more maintainable code. Covers narrowing, discriminated unions, satisfies, unknown vs any, type guards, and when to keep types simple.
aws-cdk-builder
AWS CDK infrastructure builder using TypeScript with L2/L3 constructs and Well-Architected patterns. Activate on: AWS CDK, CDK construct, CDK stack, CDK pipeline, AWS infrastructure as code TypeScript, L2 construct, CDK patterns. NOT for: Terraform IaC (use terraform-module-builder), Kubernetes manifests (use…