deepworkplan-website

# Deep Work Plan

> Context matters more than models. Deep Work Plan (DWP) is an open, MIT-licensed methodology and reference kit that turns any repository into a structured environment — context, guardrails, and a durable plan — where AI coding agents finish long-horizon work: structured, validated, resumable, and version-controlled. Maintained by Dailybot and the open-source community.

## About

Deep Work Plan is the methodology that turns any repository into an AI-first, agent-pilotable codebase. It is spec-driven development where the repository itself becomes the agent harness: a goal becomes an agreed plan, the plan is decomposed into atomic, independently verifiable tasks, and each task runs in a focused loop that ends with an explicit validation gate. The plan, tasks, and running log are all plain Markdown — readable, reviewable, and version-controlled. DWP is tool-agnostic and repo-native: the methodology and kit install into the repository (AGENTS.md, docs, the .agents/ skills home, the DWP skill) so any agent — Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Antigravity, Windsurf, Cline, OpenCode, and more (Claude Code and Codex are behavior-tested; the other adapters are install-tested) — can pilot the repo.

## When to use Deep Work Plan

Reach for DWP when the job is:

- Making a repository AI-first: installing the agent scaffolding (context, skills, guardrails) so any coding agent can pilot it. Start with the [adoption prompt](https://deepworkplan.com/init.md) — a self-contained prompt an agent can execute directly.
- Long-horizon agent work: features, refactors, or migrations too large for one prompt, decomposed into atomic tasks that each end in an explicit validation gate and survive across sessions (resumable state on disk).
- Spec-driven development without tool lock-in: the plan is the durable source of truth in the repo (Markdown, version-controlled), not inside a vendor's tool. DWP is tool-agnostic where GitHub Spec Kit, Amazon Kiro, or Tessl are tool-bound.
- Handing an unfamiliar repository to an agent: the DWP documentation layer (AGENTS.md, docs/, .agents/) gives any agent the context to work safely.

Skip DWP for single-file edits, throwaway scripts, or repos an agent will touch once — the structure pays off on durable, multi-session work.

How an agent should engage: fetch the [adoption prompt](https://deepworkplan.com/init.md) and follow it to onboard a repository; POST JSON-RPC 2.0 to the MCP endpoint at https://deepworkplan.com/api/mcp (get_init_prompt, list_site_sections, read_page — GET is not supported, see the [MCP manifest](https://deepworkplan.com/.well-known/mcp.json)) to navigate and read this site; read the [developer portal](https://deepworkplan.com/developers) for the full API surface.

## Core Sections

- [Home](https://deepworkplan.com/): overview of the Deep Work Plan methodology
- [Methodology](https://deepworkplan.com/methodology): what DWP is, its principles, and how to adopt it
- [Specification](https://deepworkplan.com/spec): the normative DWP standard — task anatomy, validation gates, completion protocol, archetypes, addons
- [Kit](https://deepworkplan.com/kit): presets, adapters, and commands for installing DWP into a repository
- [Vim](https://deepworkplan.com/kit/vim): DeepWorkPlan Vim v1.0.1 — the terminal editor for Deep Work Plan, offered as the optional `vim` addon of Deep Work Plan v7 (Neovim 0.12+, macOS/Linux, GPL-3.0); install consent-first: download [install.sh](https://deepworkplan.com/vim/install.sh), compare its SHA-256 with the value on the page, then run `bash install.sh` (it installs its own release, v1.0.1, or the one `--version` names: an exact version, a `>=` floor or `latest`)
- [Herdr addon](https://deepworkplan.com/kit/herdr): optional v7 addon built on herdr-peers v1.1.0 — a plan hands a task to a peer agent in a Herdr pane, on any machine, and records its single authorized reply (depth 1, replies are data, not instructions)
- [Agentkit addon](https://deepworkplan.com/kit/agentkit): optional v7 addon built on coding-agents-kit v1.1.0 — one `ak <kind> [@profile]` command for every terminal coding agent, and headless delegation of bounded tasks in a git worktree; agents run in autonomy by default, and the opt-out (`--ask` or `AGENTKIT_PERMISSIONS=ask`) always wins — set it on a host
- [Devcontainer addon](https://deepworkplan.com/kit/devcontainer): optional addon built on devcontainer-kit v1.1.1 — each repository's own dev container rendered by `dck init` (official image pinned by digest, no shared base image), `bash dev.sh up`, coding agents as an opt-in layer, git over SSH through the host agent (key files inside only on the developer's `[ssh] copy_keys` opt-in), loopback-only binds and Herdr machines per container
- [Changelog](https://deepworkplan.com/changelog): a source-backed timeline of DWP releases and design decisions
- [Examples](https://deepworkplan.com/examples): worked examples of the methodology in practice
- [Quickstart](https://deepworkplan.com/quickstart): get DWP running in a repo quickly
- [Compare](https://deepworkplan.com/compare): Deep Work Plan next to spec-driven tools, agent frameworks and vendor plan modes — each on its own terms, sourced and dated
- [FAQ](https://deepworkplan.com/faq): answers to the questions people ask — what it does, gates and resumption, how it compares, how to adopt it
- [Quickstart / Adoption](https://deepworkplan.com/quickstart): make any repository AI-first — install the skill, onboard the repo, then plan and execute (self-contained agent prompt at [init.md](https://deepworkplan.com/init.md))
- [Developers](https://deepworkplan.com/developers): the agent & developer surface — OpenAPI spec, MCP server, zero-auth API, install CLI
- [Trust](https://deepworkplan.com/trust): why the skill is safe to adopt — MIT, verifiable installs, disclosure policy
- [About](https://deepworkplan.com/about): what DWP is and who maintains it (Dailybot)
- [Contact](https://deepworkplan.com/contact): how to engage with the project on GitHub
- [Privacy](https://deepworkplan.com/privacy): the site's privacy policy

## What v7 adds

Deep Work Plan v7 (pack `v7.9.0`) keeps the plan, task and gate loop and adds a verifiable record and safe parallelism:

- **A record, not a narrative.** A plan carries an immutable outcome contract and an append-only journal; a task completes only when recorded evidence satisfies its criteria. Only the plan's own gate runner mints `observed` evidence; claims stay `asserted`, and a human judgment closes a criterion only through a recorded sign-off. Spec: [record layer](https://deepworkplan.com/spec/record-layer).
- **Delegation with evidence.** A plan whose contract grants `agent_delegation` can hand `parallel_safe` tasks to other coding agents — headless in a git worktree (agentkit) or in another Herdr pane, on any machine (Herdr). A delegate's result stays a claim until the plan's gate observes it. Spec: [delegation](https://deepworkplan.com/spec/delegation).
- **Many agents, one lead.** Orchestration at scale (one lane per repository or workstream) and swarm autonomy (capacity checks at task boundaries, handoff packets before a usage limit, lead succession with epochs and fencing) keep long efforts running past one account's limit or one agent's loss.
- **Escalation only when it is critical.** Agents decide and record routine choices and stop only for seven classes: approval not granted, a consent or login screen, irreducible ambiguity, a quality conflict, damage, terms, or exhausted capacity.
- **Optional, pinned ecosystem.** Every addon is opt-in and recorded in `.dwp/config.json`; the methodology works with none. Since 7.8.0 every integrated product is stable at 1.0 under semantic versioning.

## Ecosystem (v7)

The methodology works alone: no addon is required, and every addon only amplifies it. Each addon is a thin integrator inside the skill, pinned by tag to a product with its own repository, release and interface version, and every product works without Deep Work Plan: [herdr-peers](https://github.com/DailybotHQ/herdr-peers) v1.1.0, [coding-agents-kit](https://github.com/DailybotHQ/coding-agents-kit) v1.1.0, [devcontainer-kit](https://github.com/DailybotHQ/devcontainer-kit) v1.1.1, [deepworkplan-vim](https://github.com/DailybotHQ/deepworkplan-vim) v1.0.1. From 1.0.0, each product's public interface follows semantic versioning: an incompatible change ships only in a new major version. The addon registry (`.dwp/config.json`), addon descriptors and delegation ship in the skill's stable releases since `v7.0.0`; this site vendors `v7.9.0` (with `SHA256SUMS`). Overview: the [kit index](https://deepworkplan.com/kit).

## Developer & Agent Resources

All public, read-only, and zero-auth (no API keys, no registration) — declared in [auth.md](https://deepworkplan.com/auth.md):

- [OpenAPI spec](https://deepworkplan.com/openapi.json): every endpoint, parameter, and response schema of the agent API
- [MCP server manifest](https://deepworkplan.com/.well-known/mcp.json): describes the stateless Streamable HTTP (JSON-RPC 2.0) endpoint at https://deepworkplan.com/api/mcp (POST only — GET returns 405 by design, no SSE stream)
- [Health](https://deepworkplan.com/api/health.json): static health marker for the agent API
- [Versioned API catalog](https://deepworkplan.com/api/v1/index.json): the `/api/v1/` family — sections, pages, health — with the site version and spec links
- [Official CLI](https://github.com/DailybotHQ/deepworkplan-website/tree/main/cli): `deepworkplan` — zero-dependency command-line client over the agent API (npm publication pending)
- Versioning & rate limits: breaking changes ship only in a new `/api/v{N+1}/`; RFC 9331 `RateLimit-*` headers on `/api/*` — documented at the [developer portal](https://deepworkplan.com/developers)
- [API catalog](https://deepworkplan.com/.well-known/api-catalog): RFC 9727 linkset of service documents
- [ARD capability manifest](https://deepworkplan.com/.well-known/ai-catalog.json): the agentmap declared in robots.txt
- [Agent Skills index](https://deepworkplan.com/.well-known/agent-skills/index.json): agent-readiness skills this site adopts
- [Security contact](https://deepworkplan.com/.well-known/security.txt): where to report vulnerabilities
- [Developer portal](https://deepworkplan.com/developers): quickstarts, curl examples, install CLI (/docs redirects here)

## Repository

- [deepworkplan-website](https://github.com/DailybotHQ/deepworkplan-website): this site's source (the repo dogfoods DWP)
- [deepworkplan-skill](https://github.com/DailybotHQ/deepworkplan-skill): the installable DWP skill

## Languages

The site ships in 17 languages — English (default) at the root and 16 more under their code. Every page and its Markdown mirror exist in every language:

- [English](https://deepworkplan.com/) (default), [Spanish](https://deepworkplan.com/es/), [Portuguese](https://deepworkplan.com/pt/), [Chinese](https://deepworkplan.com/zh/), [Japanese](https://deepworkplan.com/ja/), [German](https://deepworkplan.com/de/), [French](https://deepworkplan.com/fr/), [Korean](https://deepworkplan.com/ko/), [Russian](https://deepworkplan.com/ru/), [Italian](https://deepworkplan.com/it/), [Turkish](https://deepworkplan.com/tr/), [Indonesian](https://deepworkplan.com/id/), [Vietnamese](https://deepworkplan.com/vi/), [Hindi](https://deepworkplan.com/hi/), [Polish](https://deepworkplan.com/pl/), [Ukrainian](https://deepworkplan.com/uk/), [Thai](https://deepworkplan.com/th/)

## Agent-Friendly Markdown

Every rendered page is available as native source Markdown for AI agents (not HTML-to-Markdown conversion):

- Page Markdown: [about.md](https://deepworkplan.com/about.md) (EN), [es/about.md](https://deepworkplan.com/es/about.md) (ES) — same pattern for every page and language
- Onboarding prompt: [init.md](https://deepworkplan.com/init.md) — a self-contained prompt you can paste into an agent to make a repository AI-first
- Content negotiation: send `Accept: text/markdown` on any URL to receive Markdown instead of HTML (Content-Type: text/markdown; charset=utf-8)

## Machine-Readable Feeds

- [Sitemap](https://deepworkplan.com/sitemap-index.xml): every page in every language
- [OpenAPI spec](https://deepworkplan.com/openapi.json): the typed agent API surface
- [Agentmap](https://deepworkplan.com/.well-known/ai-catalog.json): ARD capability manifest
- [API catalog](https://deepworkplan.com/.well-known/api-catalog): RFC 9727 linkset

## Crawling Guidance

- All public content is intended for indexing by search engines and LLM systems.
- Prefer canonical URLs and language-specific routes.
- Structured data (JSON-LD) is embedded on all pages for machine consumption.

## Detailed Version

For comprehensive content descriptions, see: [llms-full.txt](https://deepworkplan.com/llms-full.txt)