DeepWorkPlan — Methodology Skill (Router)
Models matter; context matters more. The DeepWorkPlan skill turns any
repository into a structured environment — context, guardrails, and a durable
plan — where any coding agent executes reliably on long-horizon work. It makes
the repository "AI-first" — AGENTS.md + docs/ + per-module docs + .agents/
(with the .claude → .agents and .cursor → .agents symlinks) — and runs structured Deep Work
Plans: multi-task plans an AI agent drafts, refines, executes task-by-task,
and resumes. All plan and draft outputs land in a gitignored .dwp/ directory
at the repo root (.dwp/plans/, .dwp/drafts/).
Source of truth: https://deepworkplan.com. License: MIT.
Start here (first run)
This skill is a self-sufficient entry point: whether a developer arrives from
https://deepworkplan.com/init.md or simply installs this skill, the setup plan
is the same — and it lives here, so no network is required.
If the repository is not yet AI-first — there is no root AGENTS.md and no
.agents/ directory — the recommended first action is to onboard it, even if
the developer's request was vague ("set this up", "make this repo AI-first", or a
plain install). Before routing anywhere else:
- Read the standard locally. Read
spec/ (five RFC-2119
documents) and shared/adaptation.md. The overriding
rule is REASON, do not copy-paste: this skill is the reusable engine; what
you produce must be adapted to this repository, never templated.
- Run onboarding. Read
onboard/SKILL.md and execute it.
It is non-destructive: detect existing AGENTS.md, docs/, .agents/, or
CLAUDE.md, reconcile rather than overwrite, and ask the developer before
replacing anything. The result: AGENTS.md + CLAUDE.md symlink, a reasoned
docs/ tree, per-module docs, a .agents/ kit, and a gitignored .dwp/ — the
repository becomes the agent harness.
- Verify conformance. Read
verify/SKILL.md and run it to
confirm, objectively, that the repository now meets the standard (AGENTS.md with
real commands, the .agents/ catalog, the gitignored .dwp/, and so on).
- Then plan and execute. With the harness in place, create and execute Deep
Work Plans (below) — long-horizon, gated, resumable work an agent can run
autonomously for hours.
If the repository is already AI-first, skip onboarding and route by intent
silently — do not announce the detection or the routing decision (no "the repo
is already AI-first" / "routing to the create sub-skill" preamble). Just begin the
matched sub-skill's flow directly.
What it does
This is the router. It does not run any flow itself — it maps the
developer's intent to the right sub-skill and tells the agent to read that
sub-skill's SKILL.md and execute it there.
Trust boundary (write scope)
allowed-tools includes write-capable Edit, Write, and Bash because the
sub-skills this router delegates to need them; the router itself only reads
(the repo tree, the local spec/, shared/, and sub-skill files). Writes happen
inside the delegated sub-skill, each of which declares its own trust boundary:
- Onboard writes
AGENTS.md, docs/, per-module docs, .agents/, and
appends to .gitignore — reconciling with, never clobbering, what exists,
and asking before replacing anything.
- Create / refine write plan artifacts under the gitignored
.dwp/
directory only.
- Execute / resume write task outputs, progress, and per-task commits —
gated by each task's validation, never committing secrets, never pushing
without the developer's instruction.
- Addons install or configure anything only after the developer explicitly
accepts the offer, always via pinned, verified install paths.
It MUST NOT: make network calls in the core flow, read or commit credentials,
run installers unprompted, or write anywhere outside the surfaces above. The
full guarantees and a runnable self-audit live in
TRUST.md.
For the agent — routing rules
When the developer wants to plan, execute, or manage structured work, or make a
repo AI-agent-ready, match the intent below and read that sub-skill's
SKILL.md to execute it. Do not answer directly — each sub-skill carries the
full step-by-step flow.
| Developer says… |
Route to |
| "create a plan", "new deep work plan", "/dwp-create" |
Create → read create/SKILL.md |
| "execute the plan", "run the plan", "/dwp-execute" |
Execute → read execute/SKILL.md |
| "refine the draft", "modify the plan", "/dwp-refine" |
Refine → read refine/SKILL.md |
| "resume", "continue the interrupted plan", "/dwp-resume" |
Resume → read resume/SKILL.md |
| "plan status", "what's left", "/dwp-status" |
Status → read status/SKILL.md |
| "verify", "is this repo AI-first?", "check conformance", "/dwp-verify" |
Verify → read verify/SKILL.md |
| "make this repo AI-first", "onboard this repo", "set up AGENTS.md + docs + .agents" |
Onboard → read onboard/SKILL.md |
| "create/update a skill or agent", "evolve the kit", "/skill-create", "/agent-create" |
Author → read author/SKILL.md |
If the intent is ambiguous between planning and managing existing work, ask the
developer which they mean before routing.
Normative specification (ships with the skill)
The methodology's authoritative standard lives at spec/ —
five RFC-2119 documents (DOCUMENTATION_STANDARD, DWP_SPECIFICATION,
AGENT_PROTOCOL, ARCHETYPES, ADDONS). It ships inside the skill so an agent
reads the standard locally — no network needed. The onboard flow and
shared/adaptation.md reference it as the standard to produce. The public,
rendered version lives at https://deepworkplan.com/spec.
Shared resources used by every sub-skill
shared/context.sh — detect repo root, branch, and agent
tool; resolve the .dwp/ output location.
shared/dwp-paths.md — the .dwp/plans/ +
.dwp/drafts/ output convention and how to override it.
shared/adaptation.md — the reasoning-over-copy-paste
principle and the two repository archetypes (individual repo vs orchestrator
hub).
Opt-in addons
The addons/ area holds opt-in capabilities the
onboard flow can layer onto a repo. Addons are never part of the AI-first
baseline — a repo is fully conformant with zero addons. The first addon is
devcontainer support.
1---2name: deepworkplan-43description: DeepWorkPlan — turn any repo AI-first and run Deep Work Plans. Routes to create, execute, refine, resume, status, verify, and repo-onboarding sub-skills based on intent. Use when the developer wants to plan, execute, manage, or verify structured multi-task work, or make a repository AI-agent-ready.4version: "2.17.0"5documentation_url: https://deepworkplan.com6user-invocable: true7allowed-tools: Bash, Read, Grep, Glob, Edit, Write8metadata:9 source: https://skillmd.com/skills/dailybothq/deepworkplan-410 openclaw:11 emoji: 🧠12 homepage: https://deepworkplan.com13 requires:14 anyBins:15 - git16 - bash17---1819# DeepWorkPlan — Methodology Skill (Router)2021Models matter; context matters more. The **DeepWorkPlan** skill turns any22repository into a structured environment — context, guardrails, and a durable23plan — where any coding agent executes reliably on long-horizon work. It makes24the repository "AI-first" — `AGENTS.md` + `docs/` + per-module docs + `.agents/`25(with the `.claude → .agents` and `.cursor → .agents` symlinks) — and runs structured **Deep Work26Plans**: multi-task plans an AI agent drafts, refines, executes task-by-task,27and resumes. All plan and draft outputs land in a gitignored `.dwp/` directory28at the repo root (`.dwp/plans/`, `.dwp/drafts/`).2930Source of truth: <https://deepworkplan.com>. License: MIT.3132## Start here (first run)3334This skill is a self-sufficient entry point: whether a developer arrives from35<https://deepworkplan.com/init.md> or simply installs this skill, the setup plan36is the same — and it lives here, so no network is required.3738**If the repository is not yet AI-first** — there is no root `AGENTS.md` and no39`.agents/` directory — the recommended first action is to **onboard it**, even if40the developer's request was vague ("set this up", "make this repo AI-first", or a41plain install). Before routing anywhere else:42431. **Read the standard locally.** Read [`spec/`](spec/README.md) (five RFC-211944 documents) and [`shared/adaptation.md`](shared/adaptation.md). The overriding45 rule is **REASON, do not copy-paste**: this skill is the reusable engine; what46 you produce must be adapted to *this* repository, never templated.472. **Run onboarding.** Read [`onboard/SKILL.md`](onboard/SKILL.md) and execute it.48 It is **non-destructive**: detect existing `AGENTS.md`, `docs/`, `.agents/`, or49 `CLAUDE.md`, reconcile rather than overwrite, and ask the developer before50 replacing anything. The result: `AGENTS.md` + `CLAUDE.md` symlink, a reasoned51 `docs/` tree, per-module docs, a `.agents/` kit, and a gitignored `.dwp/` — the52 repository becomes the agent harness.533. **Verify conformance.** Read [`verify/SKILL.md`](verify/SKILL.md) and run it to54 confirm, objectively, that the repository now meets the standard (AGENTS.md with55 real commands, the `.agents/` catalog, the gitignored `.dwp/`, and so on).564. **Then plan and execute.** With the harness in place, create and execute Deep57 Work Plans (below) — long-horizon, gated, resumable work an agent can run58 autonomously for hours.5960**If the repository is already AI-first**, skip onboarding and route by intent61**silently** — do not announce the detection or the routing decision (no "the repo62is already AI-first" / "routing to the create sub-skill" preamble). Just begin the63matched sub-skill's flow directly.6465## What it does6667This is the **router**. It does not run any flow itself — it maps the68developer's intent to the right sub-skill and tells the agent to read that69sub-skill's `SKILL.md` and execute it there.7071## Trust boundary (write scope)7273`allowed-tools` includes write-capable `Edit`, `Write`, and `Bash` because the74sub-skills this router delegates to need them; the router itself only **reads**75(the repo tree, the local `spec/`, `shared/`, and sub-skill files). Writes happen76inside the delegated sub-skill, each of which declares its own trust boundary:7778- **Onboard** writes `AGENTS.md`, `docs/`, per-module docs, `.agents/`, and79 appends to `.gitignore` — reconciling with, never clobbering, what exists,80 and asking before replacing anything.81- **Create / refine** write plan artifacts under the gitignored `.dwp/`82 directory only.83- **Execute / resume** write task outputs, progress, and per-task commits —84 gated by each task's validation, never committing secrets, never pushing85 without the developer's instruction.86- **Addons** install or configure anything only after the developer explicitly87 accepts the offer, always via pinned, verified install paths.8889It MUST NOT: make network calls in the core flow, read or commit credentials,90run installers unprompted, or write anywhere outside the surfaces above. The91full guarantees and a runnable self-audit live in92[`TRUST.md`](TRUST.md).9394---9596## For the agent — routing rules9798When the developer wants to plan, execute, or manage structured work, or make a99repo AI-agent-ready, match the intent below and **read that sub-skill's100`SKILL.md` to execute it**. Do not answer directly — each sub-skill carries the101full step-by-step flow.102103| Developer says… | Route to |104|------------------|----------|105| "create a plan", "new deep work plan", "/dwp-create" | **Create** → read [`create/SKILL.md`](create/SKILL.md) |106| "execute the plan", "run the plan", "/dwp-execute" | **Execute** → read [`execute/SKILL.md`](execute/SKILL.md) |107| "refine the draft", "modify the plan", "/dwp-refine" | **Refine** → read [`refine/SKILL.md`](refine/SKILL.md) |108| "resume", "continue the interrupted plan", "/dwp-resume" | **Resume** → read [`resume/SKILL.md`](resume/SKILL.md) |109| "plan status", "what's left", "/dwp-status" | **Status** → read [`status/SKILL.md`](status/SKILL.md) |110| "verify", "is this repo AI-first?", "check conformance", "/dwp-verify" | **Verify** → read [`verify/SKILL.md`](verify/SKILL.md) |111| "make this repo AI-first", "onboard this repo", "set up AGENTS.md + docs + .agents" | **Onboard** → read [`onboard/SKILL.md`](onboard/SKILL.md) |112| "create/update a skill or agent", "evolve the kit", "/skill-create", "/agent-create" | **Author** → read [`author/SKILL.md`](author/SKILL.md) |113114If the intent is ambiguous between planning and managing existing work, ask the115developer which they mean before routing.116117### Normative specification (ships with the skill)118119The methodology's authoritative standard lives at [`spec/`](spec/README.md) —120five RFC-2119 documents (`DOCUMENTATION_STANDARD`, `DWP_SPECIFICATION`,121`AGENT_PROTOCOL`, `ARCHETYPES`, `ADDONS`). It ships inside the skill so an agent122reads the standard **locally** — no network needed. The `onboard` flow and123`shared/adaptation.md` reference it as the standard to produce. The public,124rendered version lives at https://deepworkplan.com/spec.125126### Shared resources used by every sub-skill127128- [`shared/context.sh`](shared/context.sh) — detect repo root, branch, and agent129 tool; resolve the `.dwp/` output location.130- [`shared/dwp-paths.md`](shared/dwp-paths.md) — the `.dwp/plans/` +131 `.dwp/drafts/` output convention and how to override it.132- [`shared/adaptation.md`](shared/adaptation.md) — the reasoning-over-copy-paste133 principle and the two repository archetypes (individual repo vs orchestrator134 hub).135136### Opt-in addons137138The [`addons/`](addons/README.md) area holds **opt-in** capabilities the139`onboard` flow can layer onto a repo. Addons are never part of the AI-first140baseline — a repo is fully conformant with zero addons. The first addon is141devcontainer support.