The request asks what to use to shape an AI agent's behaviour, with no platform named. The most direct fit is Sanity, whose indexed action 'shape-your-agent' crafts a system prompt for an agent powered by the Sanity Context MCP server 111. GitHub's agent-related skills and LangChain's agent platform are also relevant for building and governing agents 2124.
- 1
Sanitysanity.ioverified and signed
Its indexed 'shape-your-agent' action runs an interactive session to craft a system prompt for an AI agent powered by the Sanity Context MCP server 11.
+6 community tools built for it
for agents: shape-your-agent · create-agent-with-sanity-context · dial-your-context
- 2
LangChainlangchain.comverified and signed
An open agent engineering platform for building agents with proven patterns, own harness, context, memory and model choice, per its page 4.
+160 community tools built for it
for agents: skill-creator · deep-agents-memory · deep-agents-orchestration
- 3
GitHubgithub.comverified and signed
Its indexed 'agent-governance' skill gives patterns for adding governance, safety and trust controls to AI agent systems 12.
official:CLI · github-mcp-serverskill · add-community-extensionskill · git-commitskill · acquire-codebase-knowledge+2,563 community tools built for it
for agents: typespec-create-agent · finalize-agent-prompt · agent-governance
Sources
- 1The Content Operating System for the AI era | Sanitysanity.io · read 2026-10-29
- 2GitHub · Change is constant. GitHub keeps you ahead. · GitHub · GitHubgithub.com · read 2026-10-29
- 4LangChain: the open agent platform to own your intelligencelangchain.com · read 2026-10-29
- 11shape-your-agent: declares "shape-your-agent" (the record we read and signed)unfragile.ai · read 2026-10-24
- 12typespec-create-agent: declares "typespec-create-agent" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
shape-your-agent · shape-your-agent verified and signed
Interactive session to craft a system prompt for an AI agent powered by the Sanity Context MCP server. Use this skill when users want to define agent personality, set tone/voice, establish boundaries and guardrails, configure refusal behaviors, or control how their agent communicates. Trigger when u
typespec-create-agent · typespec-create-agent verified and signed
Generate a complete TypeSpec declarative agent with instructions, capabilities, and conversation starters for Microsoft 365 Copilot
· Pathmode website read, tools not yet checked
Shape your product without running the coding agent. Review proposed changes in your browser, bring your customer and product knowledge, and decide what needs to change. Pathmode carries those decisions and their reasoning into your developer’s coding agent.
· Langchain Google website read, tools not yet checked
LangChain enables every company to own their intelligence. Control, govern, and compound intelligence with an open agent engineering platform.
skill-creator · skill-creator verified and signed
Guide for creating effective skills that extend agent capabilities with specialized knowledge, workflows, or tool integrations. Use this skill when the user asks to: (1) create a new skill, (2) make a skill, (3) build a skill, (4) set up a skill, (5) initialize a skill, (6) scaffold a skill, (7) upd
notion · @notionhq/client verified and signed
· Langchain Openai website read, tools not yet checked
LangChain enables every company to own their intelligence. Control, govern, and compound intelligence with an open agent engineering platform.
· Langchain Anthropic website read, tools not yet checked
LangChain enables every company to own their intelligence. Control, govern, and compound intelligence with an open agent engineering platform.
figma-use-figjam · figma-use-figjam verified and signed
This skill helps agents use Figma's use_figma MCP tool in the FigJam context. Can be used alongside figma-use which has foundational context for using the use_figma tool.
· Langchain Protocol website read, tools not yet checked
LangChain enables every company to own their intelligence. Control, govern, and compound intelligence with an open agent engineering platform.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.