AgentPlaybooks

One playbook, every agent. A portable operating environment for AI agents — persona, skills, MCP servers, project instructions, and memory in one source of truth.

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.

It is not another skill store or MCP registry. Skills and MCP connections are parts of a playbook; the playbook is the whole job. That holds for agents with a body too: a skill can carry demonstrations, recordings of the task in the order a robot performs them.

Highlights

What a playbook holds

• Persona: 1 per playbook, stored directly on the playbook record
• Instructions: always-on project rules — the AGENTS.md / CLAUDE.md content
• Skills: SKILL.md documents in the Agent Skills format, frontmatter preserved across every client
• Skill attachments: bundled scripts, references, and templates, round-tripped by the CLI
• Demonstrations: recordings of a skill being performed — YouTube, a pinned URL, or a LeRobot dataset — with timestamped segments, for agents that learn by watching
• MCP servers: tools and resources in Model Context Protocol format
• Memory: key-value store with tags and descriptions, with a native Hermes memory provider
• Hermes Tools plugin: connect playbook skills, MCP/OpenAPI tools, and credentials
• Canvas: versioned markdown work documents, scoped to a playbook run, so several teams can execute the same playbook without sharing work products

Credentials, without handing them over

• Secrets vault: AES-256-GCM, per-user derived keys. Agents reference a secret by name and the platform injects it server-side (use_secret), so the value never enters an agent's context. Optional per-secret host allow-lists, and an expiry that is enforced: an expired secret is refused by every path that would use it.
• Federation: other MCP servers and OpenAPI services become tools on your playbook, with their credentials resolved from that same vault by name
• Audit trail: every federated call and every vault operation, refusals included
• Audit evidence from the CLI: export JSONL/CSV, verify the per-playbook hash chain, and explicitly confirm retention purges with apb audit.

Getting it into your tools

• Claude: one plugin brings every playbook in your account into claude.ai, Claude Desktop, Cowork, Claude Code, and mobile, signing in with OAuth — no API key. Or add a single playbook as a custom connector. See AgentPlaybooks in Claude.
• Cursor and VS Code: one-click install links for the account or a single playbook — on each playbook's Integrations tab, and in MCP Integration.
• CLI + portable Agent Plugin: audit your local agent config, then sync one playbook to Claude Code, Cursor, ChatGPT/Codex, Google Antigravity, Grok Bot and Hermes
• Agent Plugins 1.0: install the project plugin or export a single playbook as plugin.json, mcp.json, and complete Agent Skills directories. Compatible MCP hosts can also discover hosted playbook skills through the MCP Skills extension.
• Private, versioned central backups are separate from installable plugin exports; packages contain no vault secret values.
• Publishing: a public playbook's skills are served as plain markdown over HTTP at /.well-known/skills/ — installable from a URL, no registry, no sign-up
• Export formats: Agent Plugin ZIP, JSON, OpenAPI, MCP, Anthropic, Markdown

Working with other people

• API keys: role-based access control (Viewer, Coworker, Admin)
• Team collaboration: one-time editor invites without sharing human credentials or agent API keys
• Explore: practical use cases, setup guidance, and curated AgentPlaybooks starters
• Sharing: public or unlisted playbooks; keep project context in private copies
• Theme: system-aware Light and Dark modes

Tech Stack

Category	Technology	Purpose
Framework	Next.js 16 + 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 (en, hu, de, es)
Docs	Plain markdown in public/docs	Fetched and rendered client-side
Hosting	Cloudflare Workers	Edge deployment
Adapter	@opennextjs/cloudflare	Next.js on Workers

Live Demo

• Website: https://agentplaybooks.ai — the canonical host; https://apbks.com is a short domain for links
• Docs: https://agentplaybooks.ai/docs
• Release distribution checklist: npm, MCP registry, plugin stores, skill discovery, Hermes memory, and verification
• GitHub: https://github.com/matebenyovszky/agentplaybooks

Getting Started

Prerequisites

• Node.js 22+ (engines in package.json; CI runs 22)
• npm 11+ — npm 10 writes a lockfile npm ci then rejects
• Supabase project
• Cloudflare account (optional for deployment)

Installation

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

Starters

Portable playbooks under examples/ — persona, instructions, skills, MCP, memory, and vault in a tree you control. Small MIT examples you can clone or cp -R. Not a marketplace.

Starter	One-liner
coding-agent-baseline	Coding-agent playbook: instructions, two skills, safe MCP stub
doctor-drift-demo	Review playbook with host-folder drift; the portable store stays canonical
skills-only-starter	Smallest playbook: three skills + instructions; no MCP
cursor-hermes-starter	Playbook with persona, instructions, and skills for Cursor and Hermes hosts

Install into a host (optional doctor check, then sync):

npx @agentplaybooks/cli@latest doctor examples/coding-agent-baseline
npx @agentplaybooks/cli@latest sync examples/coding-agent-baseline --target=claude,cursor --apply

See examples/README.md, the CLI docs, and the Agent Plugins spec.

Environment Variables

Create a .env.local file with:

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

# Required for the secrets vault. 32 bytes as 64 hex characters:
#   node -e "console.log(require('crypto').randomBytes(32).toString('hex'))"
# Losing it means losing every stored secret — no vault operation can decrypt
# without it, and rotating it invalidates everything already encrypted.
SECRETS_ENCRYPTION_KEY=

Optional:

Variable	Effect
NEXT_PUBLIC_APP_URL	The canonical origin used for canonical tags, the sitemap and robots. Defaults to https://agentplaybooks.ai.
ALLOWED_ORIGINS	Comma-separated CORS allow-list. Replaces the hosted defaults entirely — set it on a self-hosted instance so the project's own domains are not trusted there.
SECRETS_REQUIRE_ALLOWED_HOSTS	true makes a secret's host allow-list mandatory: an unpinned secret cannot be used for outbound requests at all.

Development

npm run dev

Open http://localhost:3000

Cloudflare Deployment

npm run build:worker
npm run preview
npx wrangler deploy

CLI, ChatGPT/Codex Plugin, and Claude Code Plugin (packages/cli)

agentplaybooks doctor <project> audits local agent configuration (instructions, Agent Skills, custom agents, 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, Cursor, ChatGPT/Codex, GitHub Copilot, Gemini CLI, Google Antigravity (.agents/skills), Grok Bot (.agents/skills, which it discovers natively alongside AGENTS.md), and Hermes Agent (.agents/skills registered in ~/.hermes/config.yaml, plus that file's mcp_servers: and SOUL.md). agentplaybooks plugin export|import round-trips Agent Plugins 1.0 packages; the only manifest extension carries secret references and bindings, never secret values. login / playbooks / pull / push synchronize skills, MCP servers, and the manifest with a hosted playbook using a user API key. push also creates a private, versioned cross-platform AI agent configuration backup, including complete Agent Skills folders and portable custom agents. backups lists revisions; pull --snapshot can recover an earlier one. Secret values never move, only references declared in spec.secrets. Mutating commands show a plan first and require --apply, --yes, or interactive confirmation where supported. See packages/cli/README.md and the backup and migration guide.

The same package is a ChatGPT/Codex and Cursor plugin (skill + account MCP). Exact API-key setup and installation commands are in packages/cli/README.md.

The Claude plugin is a separate, lean folder, plugins/agentplaybooks: the account MCP connector (OAuth, no key), a playbooks skill that works in chat and Cowork, and doctor / sync commands that run the published CLI through a pinned npx. It has no bin/ directory, because claude.ai and Cowork refuse a plugin that has one. Add it on claude.ai under Customize → Plugins → Add marketplace with matebenyovszky/agentplaybooks, or in Claude Code:

/plugin marketplace add matebenyovszky/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.

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)

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

Personas (owner or editor)

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

Skills (owner or editor)

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

Memory writes (API key or owner)

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.

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.

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)

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.

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.

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

# Audit trail — shared with federated MCP calls
GET    /api/playbooks/:guid/audit?operation=secret.

Every vault operation is recorded, refusals included: what was done, to which secret, by the owner or by which API key prefix, and for secret.use the destination host. An entry never holds a secret value, a full outbound URL, or a key. Owner access only — a playbook API key performs vault operations but cannot read the record of them.

User profile and user API keys (Management)

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

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

Public discovery and saved favorites

These APIs support public reads, dashboard skill/MCP discovery, and existing favorites. Explore is a server-rendered use-case guide with curated first-party starter links; it does not load these catalogs or automatically feature public playbooks.

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)

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

MCP endpoints

For clients that require a local stdio process, see the local MCP transport. It uses the same account tools and authorization handlers; protocol discovery starts without credentials, while data operations require your instance configuration.

GET  /api/mcp/:guid                    # MCP manifest
POST /api/mcp/:guid                    # MCP JSON-RPC
POST /api/mcp/:guid/tools/:tool        # Call one tool over plain HTTP

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

GET    /api/mcp/config/:serverId       # Federated server config (owner)
POST   /api/mcp/config/:serverId
PUT    /api/mcp/config/:serverId
DELETE /api/mcp/config/:serverId
POST   /api/mcp/config/:serverId/test  # Try the connection before saving it

GET  /api/mcp-registry/search          # Search the public MCP registry
GET  /.well-known/mcp-registry-auth    # Registry ownership verification

Every tool a playbook exposes is also reachable as a plain HTTP call, so a client that cannot speak MCP is not shut out:

POST /api/playbooks/:guid/operations/:operation
POST /api/control/:operation           # Account-level operations

Publishing skills over HTTP

Skills are served as plain markdown — an index plus one SKILL.md per skill, no credential, open CORS. Any client can install from a base URL with no registry and no sign-up. Only public playbooks are served; unlisted and private ones stay reachable through apb pull.

GET /.well-known/skills/                    # Site-wide: every public playbook's skills
GET /playbooks/:guid/.well-known/skills/    # One playbook

hermes skills install well-known:https://agentplaybooks.ai/.well-known/skills/<name>

Connection catalogue

GET /api/connections

Curated templates for wiring up a federated MCP server or OpenAPI service. Public, because a template is not a credential: every entry references the secrets it needs by name only, to be resolved from the playbook's vault.

Management

GET  /api/manage/openapi.json
GET  /api/manage/playbooks
POST /api/manage/playbooks

Health

GET /api/health

API Key Usage

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

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:

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

agentplaybooks/
  src/
    app/
      .well-known/skills/  # Public skill publishing (site-wide)
      api/
        _shared/           # auth.ts, guards.ts — where authorization lives
        [[...route]]/      # Hono catch-all for most endpoints
        mcp/               # MCP manifest, JSON-RPC, federation config
        playbooks/         # Per-playbook routes (secrets, canvas, audit, …)
      dashboard/           # Authenticated UI
      enterprise/          # Self-hosting landing page
      explore/             # Use cases, setup guidance, curated starters
      login/               # Auth pages
      page.tsx             # Marketing home
    components/
      playbook/            # Editor components
      ui/                  # UI primitives
    i18n/
      messages/            # Translation files (en, hu, de, es)
      request.ts           # Server-side locale resolution
    lib/
      mcp/                 # Federation, secret references
      storage/             # Storage adapters
      supabase/            # Supabase client and types
      crypto.ts            # Secrets vault encryption
  packages/
    cli/                   # AgentPlaybooks CLI + Codex/Cursor plugin
  plugins/
    agentplaybooks/        # Claude plugin (claude.ai, Cowork, Claude Code)
  .claude-plugin/          # Plugin marketplace manifest
  docs/                    # Contributor-facing notes
    security/              # Supplier-assessment pack (HU + EN)
  examples/                # Starter playbooks (fork/clone/sync)
  public/
    blog/  docs/           # Markdown served to the client
  schemas/                 # JSON schemas (agentplaybook.json, …)
  scripts/                 # Seed and build scripts
  supabase/
    migrations/            # Database migrations
  tests/                   # Vitest suites
  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)
• secrets: the vault — AES-256-GCM ciphertext, per-secret host allow-list, reveal flag, rotation and usage accounting
• audit_logs: owner-readable audit trail for federated MCP calls and secrets vault operations (secret.*); never holds values, full URLs or keys. Renamed from mcp_proxy_audit_logs.
• 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: saved playbook favorites

There is deliberately no second credential store. Federated MCP and OpenAPI servers used to keep their own encrypted secrets in mcp_server_secrets; that table was dropped (supabase/migrations/20260820_drop_mcp_server_secrets.sql) because a second store meant the credentials most worth stealing sat in the weaker box, without the rotation, expiry, usage accounting and audit trail the vault already had. transport_config.auth.token_secret now names a vault entry instead.

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.

Security

Report vulnerabilities privately — see SECURITY.md. Do not open a public issue for a security defect.

Self-hosted operators assembling a NIS2 / 418/2024. 77. § filing can start from the incident runbook (HU). Release SBOMs and cosign verify are in docs/security/supply-chain.md.

Contributing

1. Fork the repository

2. Create your feature branch (git checkout -b feature/amazing-feature)

3. Run the same checks CI runs, in the same order:

   npm run lint                        # eslint
   npm run test:all                    # vitest + the CLI suite
   npm run prebuild && npx tsc --noEmit
   npm run audit:production
   npm run build
   

4. Commit your changes and open a Pull Request

Two things worth knowing before your first PR:

• Write the lockfile with npm 11. npm 10 produces a package-lock.json that npm ci then rejects outright, so CI fails on install before it reaches your change. npx npm@11 install works on Node 20 as well.
• Warnings are tolerated, errors are not. npm run lint currently reports a known set of react-hooks and navigation warnings, tracked in the issues — a clean run means zero errors, not zero output.

License

MIT — see LICENSE.

Use it for anything, including commercially. Keep the copyright notice and the permission notice in copies or substantial portions.