AgentPlaybooks

Officialdeprecated17 toolsLive

by matebenyovszky · TypeScript

Manage portable AI agent playbooks, Agent Skills, MCP configurations, personas, and memory.

ai.agentplaybooks/agentplaybooks MCP Server

The ai.agentplaybooks/agentplaybooks server manages portable AI agent playbooks and related components. It supports organizing Agent Skills, MCP configurations, personas, and memory, enabling structured management of agent behavior and context across deployments.

🛠️ Key Features

Manage portable AI agent playbooks
Manage Agent Skills
Manage MCP configurations
Manage personas
Manage memory

🚀 Use Cases

Maintain portable playbooks for AI agents
Configure agent capabilities via Agent Skills
Store and manage MCP configuration sets for integrations
Apply personas to tailor agent behavior
Persist or organize agent memory information

⚡ Developer Benefits

Centralize playbooks, skills, MCP configuration, personas, and memory under one server
Keep agent setup components organized and portable

⚠️ Limitations

No additional operational details (e.g., specific tools, endpoints, or counts) are provided in the available source data.

Topics

agentaimcpmcp-servermcp-server-storemcp-servers-directoryplaybookplaybooksskillskills

Captured live from the server via tools/list.

list_playbooks

List all playbooks owned by the authenticated user. Returns playbooks with their counts of personas, skills, and MCP servers.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

create_playbook

Create a new playbook. A playbook is a container for personas (AI personalities), skills (capabilities), and memory (persistent storage).

Parameters4

name	string	required	Name of the playbook
description	string	optional	Description of what the playbook is for
visibility	string	optional	Visibility of the playbook
instructions	string	optional	Always-on project instructions (the AGENTS.md / CLAUDE.md content). Separate from the persona: the persona is who the agent is, these are the rules of this project.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Name of the playbook"
    },
    "description": {
      "type": "string",
      "description": "Description of what the playbook is for"
    },
    "visibility": {
      "type": "string",
      "enum": [
        "public",
        "private",
        "unlisted"
      ],
      "description": "Visibility of the playbook",
      "default": "private"
    },
    "instructions": {
      "type": "string",
      "description": "Always-on project instructions (the AGENTS.md / CLAUDE.md content). Separate from the persona: the persona is who the agent is, these are the rules of this project."
    }
  },
  "required": [
    "name"
  ]
}

get_playbook

Get detailed information about a specific playbook including all personas, skills, and MCP servers.

Parameters1

playbook_id

string

required

UUID of the playbook

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    }
  },
  "required": [
    "playbook_id"
  ]
}

update_playbook

Update a playbook's name, description, visibility, or project instructions.

Parameters5

playbook_id	string	required	UUID of the playbook
name	string	optional	New name
description	string	optional	New description
visibility	string	optional	New visibility
instructions	string	optional	New always-on project instructions (the AGENTS.md / CLAUDE.md content)

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    },
    "name": {
      "type": "string",
      "description": "New name"
    },
    "description": {
      "type": "string",
      "description": "New description"
    },
    "visibility": {
      "type": "string",
      "enum": [
        "public",
        "private",
        "unlisted"
      ],
      "description": "New visibility"
    },
    "instructions": {
      "type": "string",
      "description": "New always-on project instructions (the AGENTS.md / CLAUDE.md content)"
    }
  },
  "required": [
    "playbook_id"
  ]
}

delete_playbook

Delete a playbook and all its contents (personas, skills, memory, API keys). This action cannot be undone!

Parameters1

playbook_id

string

required

UUID of the playbook to delete

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook to delete"
    }
  },
  "required": [
    "playbook_id"
  ]
}

create_persona

Add a persona (AI personality with system prompt) to a playbook.

Parameters4

playbook_id	string	required	UUID of the playbook
name	string	required	Name of the persona
system_prompt	string	required	The system prompt that defines this persona's behavior
metadata	object	optional	Optional metadata

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    },
    "name": {
      "type": "string",
      "description": "Name of the persona"
    },
    "system_prompt": {
      "type": "string",
      "description": "The system prompt that defines this persona's behavior"
    },
    "metadata": {
      "type": "object",
      "description": "Optional metadata"
    }
  },
  "required": [
    "playbook_id",
    "name",
    "system_prompt"
  ]
}

update_persona

Update a persona's name, system prompt, or metadata.

Parameters5

playbook_id	string	required	UUID of the playbook
persona_id	string	required	UUID of the persona
name	string	optional	New name
system_prompt	string	optional	New system prompt
metadata	object	optional	New metadata

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    },
    "persona_id": {
      "type": "string",
      "description": "UUID of the persona"
    },
    "name": {
      "type": "string",
      "description": "New name"
    },
    "system_prompt": {
      "type": "string",
      "description": "New system prompt"
    },
    "metadata": {
      "type": "object",
      "description": "New metadata"
    }
  },
  "required": [
    "playbook_id",
    "persona_id"
  ]
}

delete_persona

Delete a persona from a playbook.

Parameters2

playbook_id	string	required	UUID of the playbook
persona_id	string	required	UUID of the persona to delete

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    },
    "persona_id": {
      "type": "string",
      "description": "UUID of the persona to delete"
    }
  },
  "required": [
    "playbook_id",
    "persona_id"
  ]
}

create_skill

Add a skill (capability/tool definition) to a playbook. Skills define what the AI can do with input/output schemas.

Parameters5

playbook_id	string	required	UUID of the playbook
name	string	required	Agent Skills-compatible name (lowercase kebab-case, e.g., 'code-review')
description	string	required	Description of what the skill does
content	string	optional	Full markdown content (SKILL.md body)
licence	string	optional	License information (e.g., MIT, Apache 2.0)

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    },
    "name": {
      "type": "string",
      "description": "Agent Skills-compatible name (lowercase kebab-case, e.g., 'code-review')"
    },
    "description": {
      "type": "string",
      "description": "Description of what the skill does"
    },
    "content": {
      "type": "string",
      "description": "Full markdown content (SKILL.md body)"
    },
    "licence": {
      "type": "string",
      "description": "License information (e.g., MIT, Apache 2.0)"
    }
  },
  "required": [
    "playbook_id",
    "name",
    "description"
  ]
}

update_skill

Update a skill's name, description, definition, or examples.

Parameters6

playbook_id	string	required	UUID of the playbook
skill_id	string	required	UUID of the skill
name	string	optional	New name
description	string	optional	New description
content	string	optional	New markdown content
licence	string	optional	New license

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    },
    "skill_id": {
      "type": "string",
      "description": "UUID of the skill"
    },
    "name": {
      "type": "string",
      "description": "New name"
    },
    "description": {
      "type": "string",
      "description": "New description"
    },
    "content": {
      "type": "string",
      "description": "New markdown content"
    },
    "licence": {
      "type": "string",
      "description": "New license"
    }
  },
  "required": [
    "playbook_id",
    "skill_id"
  ]
}

delete_skill

Delete a skill from a playbook.

Parameters2

playbook_id	string	required	UUID of the playbook
skill_id	string	required	UUID of the skill to delete

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    },
    "skill_id": {
      "type": "string",
      "description": "UUID of the skill to delete"
    }
  },
  "required": [
    "playbook_id",
    "skill_id"
  ]
}

list_skills

List all skills in a playbook. Skills define capabilities, rules, and how tasks should be solved.

Parameters1

playbook_id

string

required

UUID of the playbook

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    }
  },
  "required": [
    "playbook_id"
  ]
}

get_skill

Get detailed information about a specific skill including its definition and examples.

Parameters2

playbook_id	string	required	UUID of the playbook
skill_id	string	required	UUID of the skill

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    },
    "skill_id": {
      "type": "string",
      "description": "UUID of the skill"
    }
  },
  "required": [
    "playbook_id",
    "skill_id"
  ]
}

read_memory

Read a specific memory entry by key.

Parameters2

playbook_id	string	required	UUID of the playbook
key	string	required	Memory key to read

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    },
    "key": {
      "type": "string",
      "description": "Memory key to read"
    }
  },
  "required": [
    "playbook_id",
    "key"
  ]
}

search_memory

Search memories by text and/or tags. Returns all matching entries.

Parameters3

playbook_id	string	required	UUID of the playbook
search	string	optional	Search in keys and descriptions
tags	array	optional	Filter by tags (any match)

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    },
    "search": {
      "type": "string",
      "description": "Search in keys and descriptions"
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Filter by tags (any match)"
    }
  },
  "required": [
    "playbook_id"
  ]
}

write_memory

Write a memory entry with optional tags and description. Tags help organize and search memories.

Parameters5

playbook_id	string	required	UUID of the playbook
key	string	required	Memory key (unique identifier)
value	object	required	Value to store (any JSON object)
tags	array	optional	Tags for categorization and search
description	string	optional	Human-readable description of this memory

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    },
    "key": {
      "type": "string",
      "description": "Memory key (unique identifier)"
    },
    "value": {
      "type": "object",
      "description": "Value to store (any JSON object)"
    },
    "tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Tags for categorization and search"
    },
    "description": {
      "type": "string",
      "description": "Human-readable description of this memory"
    }
  },
  "required": [
    "playbook_id",
    "key",
    "value"
  ]
}

delete_memory

Delete a memory entry from a playbook.

Parameters2

playbook_id	string	required	UUID of the playbook
key	string	required	Memory key to delete

Raw schema

{
  "type": "object",
  "properties": {
    "playbook_id": {
      "type": "string",
      "description": "UUID of the playbook"
    },
    "key": {
      "type": "string",
      "description": "Memory key to delete"
    }
  },
  "required": [
    "playbook_id",
    "key"
  ]
}

README.md13 KBView on GitHub

AgentPlaybooks

Vendor-neutral, platform-independent home for AI agent skills, tools, and memory.

Keep your agents yours. AgentPlaybooks stores skills, personas, MCP servers, project instructions, and memory in one portable playbook, so you can switch platforms, use several at once, or self-host without vendor lock-in.

Your agent setup stays in sync across Claude, ChatGPT, Cursor, Codex, Gemini, local models, and future platforms. The playbook is the portable source of truth—not any single vendor or editor.

Highlights

Personas: 1 per playbook, stored directly on the playbook record
Skills: JSON schema definitions plus optional SKILL.md content
Skill attachments: secure file storage for code, prompts, and docs
MCP servers: tools and resources in Model Context Protocol format
Canvas: versioned markdown work documents for long-running agent workflows
Memory: key-value store with tags and descriptions
Export formats: JSON, OpenAPI, MCP, Anthropic, Markdown
API keys: Role-Based Access Control (Viewer, Coworker, Admin)
Team collaboration: one-time editor invites without sharing human credentials or agent API keys
Marketplace: Public and Unlisted playbooks, skills, MCP servers
Theme: System-aware Light and Dark modes

Tech Stack

Category	Technology	Purpose
Framework	Next.js 15 + React 19	App Router, SSR
Styling	Tailwind CSS 4	Utility-first CSS
Animation	Framer Motion	UI animations
Icons	Lucide React	Icon library
API	Hono	Edge API routing
Database	Supabase	Postgres + Auth + RLS
i18n	next-intl	Localization
Docs	MDX	Markdown + React
Hosting	Cloudflare Pages	Edge deployment
Adapter	@opennextjs/cloudflare	Next.js on Workers

Live Demo

Website: https://apbks.com
Docs: https://apbks.com/docs
GitHub: https://github.com/matebenyovszky/agentplaybooks

Getting Started

Prerequisites

Node.js 20+
npm or pnpm
Supabase account
Cloudflare account (optional for deployment)

Installation

bash

git clone https://github.com/matebenyovszky/agentplaybooks.git
cd agentplaybooks
npm install

Environment Variables

Create a .env.local file with:

env

NEXT_PUBLIC_SUPABASE_URL=https://your-project.supabase.co
NEXT_PUBLIC_SUPABASE_ANON_KEY=your_anon_key
SUPABASE_SERVICE_ROLE_KEY=your_service_role_key

Development

bash

npm run dev

Open http://localhost:3000

Cloudflare Deployment

bash

npm run build:worker
npm run preview
npx wrangler deploy

CLI and Claude Code Plugin (`packages/cli`)

agentplaybooks doctor <project> audits local agent configuration (instructions, Agent Skills, MCP servers, likely hard-coded secrets, drift) and agentplaybooks sync <project> creates the canonical agentplaybook.json plus the platform files missing from enabled targets: Claude Code (.claude/skills + .mcp.json), Cursor (.cursor/skills + .cursor/mcp.json), ChatGPT/Codex (.codex/skills + .codex/config.toml), Google Antigravity (.agents/skills), and Hermes Agent (~/.hermes/skills). login / playbooks / pull / push synchronize skills, MCP servers, and the manifest with a hosted playbook using a user API key; secret values never move, only the references the playbook declares in spec.secrets. All mutating commands are plan-only until --apply. See packages/cli/README.md.

The same package doubles as a Claude Code / Claude Cowork plugin (skill + slash commands). Install it from this repository:

text

/plugin marketplace add integrityauthority/agentplaybooks
/plugin install agentplaybooks@agentplaybooks

API Overview

Public and Unlisted playbook access

Public playbooks are visible to everyone. Unlisted playbooks are accessible via GUID but hidden from search.

code

GET /api/playbooks/:guid
GET /api/playbooks/:guid?format=openapi
GET /api/playbooks/:guid?format=mcp
GET /api/playbooks/:guid?format=anthropic
GET /api/playbooks/:guid?format=markdown

GET /api/playbooks/:id/personas
GET /api/playbooks/:id/skills
GET /api/playbooks/:guid/memory

Note: :id supports both UUID and GUID for personas and skills.

Authenticated playbook CRUD (session auth)

code

GET    /api/playbooks
POST   /api/playbooks
PUT    /api/playbooks/:id
DELETE /api/playbooks/:id

Personas (owner or editor)

code

POST   /api/playbooks/:id/personas
PUT    /api/playbooks/:id/personas/:pid
DELETE /api/playbooks/:id/personas/:pid

Skills (owner or editor)

code

POST   /api/playbooks/:id/skills
PUT    /api/playbooks/:id/skills/:sid
DELETE /api/playbooks/:id/skills/:sid

Memory writes (API key or owner)

code

PUT    /api/playbooks/:guid/memory/:key
DELETE /api/playbooks/:guid/memory/:key

Canvas work documents

Canvas documents belong to an isolated workflow run, so multiple teams can execute the same playbook without sharing work products. They are long-form markdown artifacts that agents can revise over time. Use memory for durable facts and structured state; use canvas for deliverables such as a PR review, research report, implementation plan, or draft that may be edited passage by passage.

http

GET    /api/playbooks/:guid/runs
POST   /api/playbooks/:guid/runs
GET    /api/playbooks/:guid/canvas?runId=:runId
POST   /api/playbooks/:guid/canvas
GET    /api/playbooks/:guid/canvas/:slug?runId=:runId
PUT    /api/playbooks/:guid/canvas/:slug?runId=:runId
PATCH  /api/playbooks/:guid/canvas/:slug?runId=:runId
DELETE /api/playbooks/:guid/canvas/:slug?runId=:runId

PUT replaces document fields and requires expectedVersion. PATCH performs an incremental append, prepend, or exact replace operation and also requires expectedVersion. A stale version returns HTTP 409, preventing two agents from silently overwriting each other's work.

bash

curl -X PATCH 'https://your-domain.com/api/playbooks/abc123/canvas/pr-review?runId=RUN_UUID' \
  -H "Authorization: Bearer apb_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "operation": "replace",
    "search": "## Security review\nPending.",
    "content": "## Security review\nNo blocking issues found.",
    "expectedVersion": 3
  }'

Playbook API keys (owner only)

code

GET    /api/playbooks/:id/api-keys
POST   /api/playbooks/:id/api-keys
DELETE /api/playbooks/:id/api-keys/:kid

Human collaboration (session auth; owner manages access)

Human editors are invited with a one-time link. They can edit playbook content, while ownership controls remain owner-only.

code

GET    /api/playbooks/:id/collaborators
POST   /api/playbooks/:id/collaborators
DELETE /api/playbooks/:id/collaborators/:collaboratorId

GET    /api/collaboration-invites/:token
POST   /api/collaboration-invites/:token

Invite links expire after 72 hours and can be accepted once. See Team Collaboration for the full permission model and security notes.

Playbook Secrets (owner or API key)

Secrets are encrypted using AES-256-GCM. Agents can use the use_secret MCP tool or proxy endpoint to use secrets in HTTP requests without ever reading the plaintext value.

code

GET    /api/playbooks/:guid/secrets          # List metadata only
POST   /api/playbooks/:guid/secrets          # Create encrypted secret
PUT    /api/playbooks/:guid/secrets/:name    # Update/rotate secret
DELETE /api/playbooks/:guid/secrets/:name    # Delete secret

# Dashboard only
GET    /api/playbooks/:guid/secrets/reveal/:name

# Proxy external requests using a secret
POST   /api/playbooks/:guid/secrets/proxy

User profile and user API keys (Management)

code

GET    /api/user/profile
PUT    /api/user/profile

GET    /api/user/api-keys
POST   /api/user/api-keys
DELETE /api/user/api-keys/:kid

Marketplace and stars

code

GET /api/public/playbooks
GET /api/public/skills
GET /api/public/skills/:id
GET /api/public/mcp
GET /api/public/mcp/:id

GET  /api/playbooks/:id/star
POST /api/playbooks/:id/star
GET  /api/user/starred

Memory write-back (playbook API key or owner)

code

GET    /api/playbooks/:guid/memory
PUT    /api/playbooks/:guid/memory/:key
DELETE /api/playbooks/:guid/memory/:key

MCP endpoints

code

GET  /api/mcp/:guid       # MCP manifest
POST /api/mcp/:guid       # MCP JSON-RPC

POST /api/mcp/manage      # MCP management server (user API key)

Management OpenAPI

code

GET /api/manage/openapi.json

Health

code

GET /api/health

API Key Usage

Playbook API keys let agents read/write memory for a single playbook.

bash

curl -X PUT https://your-domain.com/api/playbooks/abc123/memory/user_preferences \
  -H "Authorization: Bearer apb_live_xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{"value": {"theme": "dark"}}'

User API keys are used for management endpoints and the MCP management server:

bash

curl -X POST https://your-domain.com/api/mcp/manage \
  -H "Authorization: Bearer apb_live_xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"list_playbooks","params":{}}'

Project Structure

code

agentplaybooks/
  src/
    app/
      api/                 # Hono API + MCP endpoints
      dashboard/           # Authenticated UI
      enterprise/          # Enterprise landing page
      explore/             # Marketplace
      login/               # Auth pages
      page.tsx             # Marketing home
    components/
      playbook/            # Editor components
      ui/                  # UI primitives
    i18n/
      messages/            # Translation files
      config.ts            # i18n configuration
    lib/
      storage/             # Storage adapters
      supabase/            # Supabase client and types
      attachment-validator.ts
      utils.ts
  packages/
    cli/                   # AgentPlaybooks CLI + Claude Code plugin
  scripts/                 # Seed and build scripts
  supabase/
    migrations/            # Database migrations
  public/
  open-next.config.ts
  wrangler.jsonc

Database Schema

playbooks: core entity (includes visibility enum: private, public, unlisted; persona fields for agent identity and instructions for always-on project rules)
mcp_server_secrets: encrypted credentials for federated MCP/OpenAPI servers (service-role only)
mcp_proxy_audit_logs: owner-readable audit trail for federated calls
skills: skill definitions and optional SKILL.md content
skill_attachments: secure attachment storage for skills
mcp_servers: MCP tools and resources
playbook_runs: isolated executions of a reusable playbook
canvas: versioned markdown work documents
memories: key-value memory store
api_keys: playbook-scoped API keys with RBAC roles
user_api_keys: user-scoped API keys
playbook_collaborators: accepted human editor memberships and hashed one-time invites
profiles: public user profile data
playbook_stars: marketplace stars

A note on Row Level Security

RLS is enabled on the tables listed above, but it is not the primary authorization mechanism at runtime. Almost all API routes query with the service-role key, which bypasses RLS; authorization is enforced in application code (src/app/api/_shared/guards.ts).

RLS is load-bearing for the handful of endpoints that read public playbooks with the anon key — the MCP manifest (/api/mcp/:guid), its tool routes, and the public skills/MCP listings. Those depend on the anon SELECT policies in supabase/migrations/20260107_permissions_refactor.sql. Removing or disabling those policies breaks the endpoints rather than merely relaxing them.

Policies written against auth.uid() are currently inert, because no JWT-bearing client performs table queries — the browser talks only to /api/*, never to Postgres directly.

Contributing

Fork the repository
Create your feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

License

This project is licensed under the PolyForm Noncommercial License 1.0.0.

What this means:

You CAN:

Use the software for personal projects, learning, and experimentation
Use it internally within your organization for non-commercial purposes
Modify and adapt it for your own non-commercial use
Use it for research, education, and charitable purposes

You CANNOT (without permission):

Sell the software or offer it as a paid service
Use it to provide commercial services to others
Monetize the software or concept in any way

For commercial licensing, please contact the project maintainer.

See the LICENSE file for full details.

Install

Tools (17)

list_playbookscreate_playbookget_playbookupdate_playbookdelete_playbookcreate_personaupdate_personadelete_persona

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://agentplaybooks.ai/api/mcp/manage

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "agentplaybooks": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://agentplaybooks.ai/api/mcp/manage"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

ai.agentplaybooks/agentplaybooks MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

list_playbooks

create_playbook

get_playbook

update_playbook

delete_playbook

create_persona

update_persona

delete_persona

create_skill

update_skill

delete_skill

list_skills

get_skill

read_memory

search_memory

write_memory

delete_memory

AgentPlaybooks

Highlights

Tech Stack

Live Demo

Getting Started

Prerequisites

Installation

Environment Variables

Development

Cloudflare Deployment

CLI and Claude Code Plugin (packages/cli)

API Overview

Public and Unlisted playbook access

Authenticated playbook CRUD (session auth)

Personas (owner or editor)

Skills (owner or editor)

Memory writes (API key or owner)

Canvas work documents

Playbook API keys (owner only)

Human collaboration (session auth; owner manages access)

Playbook Secrets (owner or API key)

User profile and user API keys (Management)

Marketplace and stars

Memory write-back (playbook API key or owner)

MCP endpoints

Management OpenAPI

Health

API Key Usage

Project Structure

Database Schema

A note on Row Level Security

Contributing

License

What this means:

Install

Remote endpoint

CLI and Claude Code Plugin (`packages/cli`)