Individual skill
agent-squad-typescript
Use when building or modifying a Node.js / TypeScript app that uses the agent-squad npm package — multi-agent orchestration: orchestrator, agents (all built-in types + GroundedAgent), classifier routing (Bedrock / Anthropic / OpenAI), storage (in-memory / DynamoDB / SQL), retrievers (Amazon KB / Dakera), and tools (AgentTools + MCPToolProvider).
typescript/SKILL.md
Source commit 729d5f52869c8280f599a9fa5cf27fc1df445602
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 2, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 7,800
- Repository last updated
- Oct 8, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- aws Repository topic
- aws-bedrock Repository topic
- anthropic-claude Repository topic
- aws-cdk Repository topic
- aws-lambda Repository topic
- chatbot Repository topic
- generative-ai Repository topic
- machine-learning Repository topic
- openai Repository topic
- serverless Repository topic
- data Derived category
- data-databases Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
.npmignoreasset · 659 bytesREADME.mddoc · 10,168 bytesSKILL.mdcore · 17,088 bytesSKILL.mdcore · 17,088 byteseslint.config.mjsruns · 949 bytesjest.config.jsruns · 200 bytespackage-lock.jsonasset · 281,673 bytespackage.jsonruns · 2,362 bytessrc/agentOverlapAnalyzer.tsruns · 5,044 bytessrc/agents/agent.tsruns · 9,752 bytessrc/agents/amazonBedrockAgent.tsruns · 5,540 bytessrc/agents/anthropicAgent.tsruns · 17,894 bytessrc/agents/bedrockFlowsAgent.tsruns · 4,487 bytessrc/agents/bedrockInlineAgent.tsruns · 14,445 bytessrc/agents/bedrockLLMAgent.tsruns · 18,602 bytessrc/agents/bedrockTranslatorAgent.tsruns · 5,474 bytessrc/agents/chainAgent.tsruns · 4,090 bytessrc/agents/comprehendFilterAgent.tsruns · 9,832 bytessrc/agents/groundedAgent.tsruns · 12,332 bytessrc/agents/lambdaAgent.tsruns · 2,719 bytessrc/agents/lexBotAgent.tsruns · 3,500 bytessrc/agents/openAIAgent.tsruns · 7,279 bytessrc/agents/supervisorAgent.tsruns · 10,988 bytessrc/classifiers/anthropicClassifier.tsruns · 4,506 bytessrc/classifiers/bedrockClassifier.tsruns · 6,793 bytessrc/classifiers/classifier.tsruns · 11,317 bytessrc/classifiers/jevClassifier.tsruns · 12,245 bytessrc/classifiers/openAIClassifier.tsruns · 4,694 bytessrc/common/src/awsSdkUtils.tsruns · 3,800 bytessrc/common/src/types/awsSdk.tsruns · 553 bytessrc/common/src/version.tsruns · 84 bytessrc/index.tsruns · 3,183 bytessrc/orchestrator.tsruns · 19,070 bytessrc/retrievers/AmazonKBRetriever.tsruns · 4,981 bytessrc/retrievers/DakeraRetriever.tsruns · 4,594 bytessrc/retrievers/retriever.tsruns · 1,815 bytessrc/storage/chatStorage.tsruns · 1,226 bytessrc/storage/dynamoDbChatStorage.tsruns · 4,981 bytessrc/storage/memoryChatStorage.tsruns · 2,860 bytessrc/storage/sqlChatStorage.tsruns · 6,190 bytessrc/storage/summarizingChatStorage.tsruns · 4,288 bytessrc/tools/mcpToolProvider.tsruns · 19,786 bytessrc/types/index.tsruns · 1,879 bytessrc/utils/chatUtils.tsruns · 816 bytessrc/utils/helpers.tsruns · 2,085 bytessrc/utils/logger.tsruns · 3,516 bytessrc/utils/tool.tsruns · 7,769 bytessrc/utils/ui.tsruns · 1,471 bytestests/Orchestrator.test.tsruns · 9,412 bytestests/agents/Agents.test.tsruns · 3,538 bytestests/agents/LambdaAgent.test.tsruns · 6,955 bytestests/agents/OpenAi.test.tsruns · 4,140 bytestests/agents/groundedAgent.test.tsruns · 16,420 bytestests/classifiers/AnthropicClassifier.test.tsruns · 4,835 bytestests/classifiers/BedrockClassifier.test.tsruns · 3,985 bytestests/classifiers/Classifier.test.tsruns · 7,978 bytestests/classifiers/JevClassifier.test.tsruns · 16,327 bytestests/classifiers/OpenAIClassifier.test.tsruns · 6,429 bytestests/mcpToolProvider.test.tsruns · 26,351 bytestests/mcpToolProviderV2.test.tsruns · 6,489 bytestests/mcpToolProviderV2Partial.test.tsruns · 1,538 bytestests/mock/mockAgent.tsruns · 1,409 bytestests/retrievers/DakeraRetriever.test.tsruns · 2,808 bytestests/retrievers/Retriever.test.tsruns · 3,242 bytestests/storage/ChatStorage.test.tsruns · 16,698 bytestests/storage/SummarizingChatStorage.test.tsruns · 7,422 bytestests/utils/Utils.test.tsruns · 4,957 bytestests/utils/helpers.test.tsruns · 2,133 bytestests/utils/tool.test.tsruns · 2,000 bytestsconfig.jsonasset · 721 bytes
Read excerpt
# 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 `Agent` subclass + `AgentSquad` with no routing. Or skip the
orchestrator entirely and call `agent.processRequest(...)` directly.
- **Several specialists** → multiple agents registered with `orchestrator.addAgent(agent)`, a
classifier routes each turn.