{
  "markdown": "# Planwright\n\n**Control plane for autonomous software labor.**\n\nPlanwright is the objective-native planning board for agent-led software development. Humans define outcomes at the Objective layer; coding agents (Claude Code, Cursor, Codex, and others) claim work, decompose tasks, execute, and report back via native MCP—with every state change captured in a hash-chained, Ed25519-signed audit trail.\n\n[![Documentation](https://img.shields.io/badge/docs-planwright.tools-blue)](https://planwright.tools/docs)\n[![MCP](https://img.shields.io/badge/MCP-compatible-green)](https://modelcontextprotocol.io)\n\n---\n\n## Quick Start\n\n### Claude Code (recommended)\n\n```bash\nclaude mcp add planwright https://mcp.planwright.tools/mcp\n```\n\nYour browser opens for GitHub login. That's it.\n\n### Other Agents\n\nSee the [full agent setup guides](https://planwright.tools/docs/agents) for Cursor, Codex, Claude Desktop, and generic MCP clients.\n\n---\n\n## How It Works\n\n```\n┌─────────────────────────────────────────────────────────────────┐\n│                                                                 │\n│   PLANNING (Humans)                 EXECUTION (Agents)          │\n│                                                                 │\n│   \"Add OAuth login\" ───────┐                                    │\n│                            │                                    │\n│   create_objective() ──────┤                                    │\n│                            ▼                                    │\n│                     ┌──────────────┐                            │\n│                     │   BACKLOG    │                            │\n│                     └──────┬───────┘                            │\n│                            │                                    │\n│   schedule_objective() ────┤                                    │\n│                            ▼                                    │\n│                     ┌──────────────┐                            │\n│                     │  SCHEDULED   │◀── list_objectives()       │\n│                     └──────┬───────┘                            │\n│                            │                                    │\n│                            │── claim_objective() ──────────────▶│\n│                            ▼                                    │\n│                     ┌──────────────┐                            │\n│                     │ IN PROGRESS  │◀── append_plan()           │\n│                     │              │◀── record_diff()           │\n│                     └──────┬───────┘                            │\n│                            │                                    │\n│                            │── request_acceptance() ───────────▶│\n│                            ▼                                    │\n│                     ┌──────────────┐                            │\n│                     │  ACCEPTANCE  │                            │\n│                     └──────┬───────┘                            │\n│                            │                                    │\n│   Human reviews ───────────┤                                    │\n│   (web UI)                 │                                    │\n│                     ┌──────┴───────┐                            │\n│                     │     DONE     │                            │\n│                     └──────────────┘                            │\n│                                                                 │\n│   Every step: hash-chained + Ed25519 signed audit trail         │\n│                                                                 │\n└─────────────────────────────────────────────────────────────────┘\n```\n\n---\n\n## Key Features\n\n**Objective-Native, Not Task-Based**\nNo story points. No velocity charts. No capacity planning. Agents decompose objectives into tasks themselves—you manage outcomes, not effort.\n\n**Immutable Audit Trail**\nEvery state change produces a hash-chained, Ed25519-signed audit record. Know exactly what the agent planned, what it changed, and when.\n\n**Native MCP Integration**\nAgents connect via the Model Context Protocol—no custom API clients needed. Works with any MCP-compatible agent.\n\n**Multi-Agent Support**\nClaude Code, Cursor, Codex, Factory, Amp—if it speaks MCP, it can work from your Planwright board.\n\n**Context Files**\nPush CLAUDE.md, architecture docs, and specs to Planwright. Agents read them before starting work.\n\n---\n\n## Documentation\n\n- [Getting Started](https://planwright.tools/docs/getting-started)\n- [Agent Setup Guides](https://planwright.tools/docs/agents)\n- [Writing Better Objectives](https://planwright.tools/docs/best-practices)\n- [API Reference](https://planwright.tools/docs/reference)\n\n---\n\n## Examples\n\nSee the [`examples/`](./examples) directory for:\n\n- Sample `CLAUDE.md` files for different project types\n- Example objective structures\n- Context file templates\n\n---\n\n## MCP Server\n\nPlanwright's MCP server is hosted and managed—no self-hosting required.\n\n| Endpoint | Protocol |\n|----------|----------|\n| `https://mcp.planwright.tools/mcp` | Streamable HTTP |\n\nAuthentication is handled via OAuth 2.1 with Dynamic Client Registration (RFC 7591). Your agent opens a browser for GitHub login on first connection.\n\nFor CI/CD and headless environments, generate a static token in **Settings → MCP Tokens**.\n\n---\n\n## Available Tools\n\nPlanwright exposes 30 MCP tools for agent orchestration:\n\n### Setup & Context\n| Tool | Description |\n|------|-------------|\n| `planwright_set_repo` | Set active project for the session (by GitHub repo or project ID) |\n| `planwright_list_workspaces` | List workspaces you have access to |\n| `planwright_list_projects` | List projects with IDs and linked GitHub repos |\n| `planwright_list_context_files` | List CLAUDE.md, specs, architecture docs for the project |\n| `planwright_get_context_file` | Read a specific context file |\n| `planwright_push_context_file` | Upload or update a context file |\n| `planwright_get_doc_suggestions` | Get pending documentation gap suggestions |\n| `planwright_dismiss_doc_suggestion` | Dismiss a doc suggestion |\n| `planwright_get_board_url` | Get the Planwright board URL |\n\n### Initiatives\n| Tool | Description |\n|------|-------------|\n| `planwright_list_initiatives` | List initiatives (milestones) for the workspace |\n| `planwright_create_initiative` | Create a new initiative |\n| `planwright_update_initiative` | Update initiative metadata |\n| `planwright_delete_initiative` | Delete an initiative |\n\n### Objectives\n| Tool | Description |\n|------|-------------|\n| `planwright_list_objectives` | List objectives by lane (backlog, scheduled, in_progress, acceptance, done) |\n| `planwright_get_objective` | Get full objective details including agent run history |\n| `planwright_create_objective` | Create a new objective with acceptance criteria |\n| `planwright_update_objective` | Update objective metadata |\n| `planwright_schedule_objective` | Move objective from backlog to scheduled |\n\n### Agent Workflow\n| Tool | Description |\n|------|-------------|\n| `planwright_claim_objective` | Claim a scheduled objective and start an agent run |\n| `planwright_append_plan` | Post the agent's decomposition plan |\n| `planwright_check_alignment` | Verify work aligns with claimed objective (drift detection) |\n| `planwright_record_diff` | Record diff summary and test results |\n| `planwright_submit_test_run` | Submit acceptance criteria verification results |\n| `planwright_request_acceptance` | Move objective to acceptance lane for human review |\n| `planwright_append_note` | Record task completion in the agent run log |\n| `planwright_flag_clarity` | Flag objective as having clarity concerns |\n| `planwright_override_clarity` | Human override for clarity flags |\n\n### Enrichment & Classification\n| Tool | Description |\n|------|-------------|\n| `planwright_list_unenriched` | List objectives/initiatives missing intent summaries |\n| `planwright_list_unclassified` | List objectives missing strategic classification |\n| `planwright_list_my_bugs` | List bugs for this project |\n\n---\n\n## Support\n\n- [Documentation](https://planwright.tools/docs)\n- [GitHub Discussions](https://github.com/Planwright/planwright/discussions)\n- [Report a Bug](https://github.com/Planwright/planwright/issues/new?template=bug_report.md)\n\n---\n\n## License\n\nPlanwright is a commercial product. The MCP integration examples in this repository are provided under the MIT License.\n\nSee [LICENSE](./LICENSE) for details.\n",
  "bytes": 8482,
  "sha": "24fde2f3f181339c4b9f028b70c32012673d2ada77b67074d3d99f0d51dc171c",
  "repo_slug": "planwright/planwright",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_tools_planwright_planwright_ab0fe095/readme"
}