Skip to content

j-mauro-r/SAT-Dengue-V2 / .agents/skills/deepworkplan

deepworkplan

Verified

DeepWorkPlan — turn any repo AI-first and run Deep Work Plans. Routes to create, execute, refine, resume, status, verify, upgrade, 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.

FileKindSize
SKILL.mdskill md12.0 KB
TRUST.mdmarkdown16.1 KB
addons/README.mdmarkdown11.7 KB
addons/machine-installs.mdmarkdown2.9 KB
examples/CREATE_PLAN.mdmarkdown6.9 KB
examples/ORCHESTRATOR_TASK_TEMPLATE_create_child_dwp.mdmarkdown15.0 KB
examples/ORCHESTRATOR_TASK_TEMPLATE_execute_child_dwp.mdmarkdown16.7 KB
examples/ORCHESTRATOR_TASK_TEMPLATE_integration_checkpoint.mdmarkdown9.0 KB
examples/PROMPTS_TEMPLATE.mdmarkdown4.0 KB
examples/TEAM_AGENTS_TASK_TEMPLATE.mdmarkdown5.1 KB
examples/V6_PLAN_EXAMPLE.mdmarkdown5.5 KB
guide/GUIDE.mdmarkdown8.0 KB
guide/authoring.mdmarkdown28.5 KB
guide/execution.mdmarkdown21.0 KB
guide/large-repo-onboarding.mdmarkdown3.3 KB
guide/orchestration-at-scale.mdmarkdown11.4 KB
guide/orchestrator.mdmarkdown37.9 KB
guide/prompts.mdmarkdown10.1 KB
guide/skills-integration.mdmarkdown6.5 KB
guide/structure.mdmarkdown6.2 KB
guide/swarm.mdmarkdown21.2 KB
guide/team-agents.mdmarkdown12.3 KB
shared/adaptation.mdmarkdown2.7 KB
shared/addon_sync.pyscript17.7 KB
shared/benchmark.pyscript97.6 KB
shared/config.pyscript41.5 KB
shared/context.shscript4.2 KB
shared/context_manifest.pyscript40.8 KB
shared/contract_v6.pyscript82.7 KB
shared/delegators.pyscript3.0 KB
shared/dwp-paths.mdmarkdown5.8 KB
shared/finalize_plan.pyscript7.2 KB
shared/install-verification.mdmarkdown1.8 KB
shared/ledger.pyscript141.5 KB
shared/migrate_v6.pyscript46.5 KB
shared/outcomes.pyscript27.2 KB
shared/plan_paths.pyscript4.8 KB
shared/resources.pyscript49.0 KB
shared/scheduler.pyscript41.6 KB
shared/state_contract.pyscript9.8 KB
shared/swarm.pyscript27.3 KB
shared/troubleshooting.mdmarkdown7.4 KB
shared/update-state.pyscript12.5 KB
shared/views.pyscript21.0 KB
shared/working-principles.mdmarkdown7.1 KB
spec/ADDONS.mdmarkdown27.4 KB
spec/AGENT_PROTOCOL.mdmarkdown28.0 KB
spec/ARCHETYPES.mdmarkdown10.6 KB
spec/BENCHMARK.mdmarkdown20.3 KB
spec/CONFIG.mdmarkdown8.7 KB
spec/DOCUMENTATION_STANDARD.mdmarkdown40.7 KB
spec/DWP_SPECIFICATION.mdmarkdown65.1 KB
spec/LITE_PLANS.mdmarkdown4.0 KB
spec/PLAN_STATE.mdmarkdown34.9 KB
spec/README.mdmarkdown11.5 KB
spec/V6_CONTEXT.mdmarkdown6.4 KB
spec/V6_CONTRACT.mdmarkdown12.3 KB
spec/V6_LIFECYCLE.mdmarkdown13.5 KB
spec/V6_RESOURCES.mdmarkdown4.7 KB
spec/V7_ABILITIES.mdmarkdown4.9 KB
spec/V7_CONTRACT.mdmarkdown6.4 KB
spec/V7_ROADMAP.mdmarkdown4.6 KB
spec/schema/addon-descriptor-v1.schema.jsonconfig5.5 KB
spec/schema/benchmark-record.schema.jsonconfig14.0 KB
spec/schema/context-manifest-v6.schema.jsonconfig12.5 KB
spec/schema/dwp-config-v1.schema.jsonconfig3.5 KB
spec/schema/dwp-handoff-v1.schema.jsonconfig3.0 KB
spec/schema/journal-event-v6.schema.jsonconfig22.3 KB
spec/schema/journal-event-v7.schema.jsonconfig24.9 KB
spec/schema/learnings-record.schema.jsonconfig6.0 KB
spec/schema/plan-contract-v6.schema.jsonconfig16.4 KB
spec/schema/plan-contract-v7.schema.jsonconfig16.6 KB
spec/schema/plan-manifest-v2.schema.jsonconfig1.0 KB
spec/schema/plan-manifest-v5.schema.jsonconfig1.3 KB
spec/schema/plan-manifest-v6.schema.jsonconfig2.0 KB
spec/schema/plan-manifest-v7.schema.jsonconfig1.7 KB
spec/schema/plan-manifest.schema.jsonconfig1.8 KB
spec/schema/plan-snapshot-v6.schema.jsonconfig7.8 KB
spec/schema/plan-state-v2.schema.jsonconfig6.4 KB
spec/schema/plan-state-v5.schema.jsonconfig6.7 KB
spec/schema/plan-state.schema.jsonconfig3.7 KB

guide/GUIDE.md

View on GitHub
# DeepWorkPlan — Methodology Guide (GUIDE.md)

### How to Create Deep-Work Task Execution Plans (outputs under `.dwp/`)

This guide defines the **official structure and workflow** for creating _agent deep work plans_.

These plans are designed so that an AI agent (Cursor, Claude, etc.) can:

- Work for **many hours** (including overnight)
- Focus on **one task at a time**
- Follow a **clear, ordered execution plan**
- Keep everything **modular, auditable and disposable**

Use this document whenever you need to generate a new deep-work plan.

---

> **Addressing a section: by its number, not by a heading level.** "Read
> §6.1" means the section numbered 6.1 at whatever level the file uses
> (`## 6.1.` sits beside `## 6.`). Extracting `### 6.1` would match nothing,
> exit **zero**, and read **empty** — a silent no-read. If a section
> extraction comes back empty, that is a defect to report, never a blank
> section.

This file is the **routing index** of the methodology guide. The guide's content
is unchanged; it is split into flow-scoped files so an agent loads only what its
current flow needs (`spec/DWP_SPECIFICATION.md` §5). The design rationale lives
in the contributor-only repository ADR.
Nothing here is compressed — every section that existed in
the single-file guide exists verbatim in exactly one file below.

## How to read this guide (by flow)

| Your flow | Read (essential) | Read only when triggered |
|-----------|------------------|--------------------------|
| **Create** a plan | [`authoring.md`](./authoring.md) (README + task-file templates, test & security discipline), [`structure.md`](./structure.md) (folders, naming, lifecycle) | [`orchestrator.md`](./orchestrator.md) if the plan spans sub-repositories; [`team-agents.md`](./team-agents.md) if parallel groups were detected; [`prompts.md`](./prompts.md) when writing `PROMPTS.md`; [`skills-integration.md`](./skills-integration.md) when referencing skills/agents in tasks; the flow file `../create/v6.md` + `../spec/V6_CONTRACT.md` when creating a new plan |
| **Execute** / **resume** a plan | [`execution.md`](./execution.md) (agent rules, per-task commits, completion tracking, final review) | [`orchestrator.md`](./orchestrator.md) for orchestrator plans; [`team-agents.md`](./team-agents.md) for parallel groups; [`orchestration-at-scale.md`](./orchestration-at-scale.md) for a lead running agents in panes across accounts; [`swarm.md`](./swarm.md) for capacity checks, handoff packets and lead succession; [`prompts.md`](./prompts.md) §9 for resume scenarios; the flow file `../execute/v6.md` when the plan folder is v6 by its artifacts (`../spec/V6_LIFECYCLE.md` is normative); a v6 resume loads `../resume/v6.md`; v5 → v6 migration is refine 3.2a (`../shared/migrate_v6.py`) |
| **Refine** a plan | [`authoring.md`](./authoring.md), [`structure.md`](./structure.md) | as for Create |
| **Onboard** a repository | [`structure.md`](./structure.md) | [`large-repo-onboarding.md`](./large-repo-onboarding.md) when the repository is large enough to be its own plan; `../onboard/v6.md` (bounded-autonomy records) for v6 plans — `../spec/V6_LIFECYCLE.md` §10 is normative |
| **Verify** / **status** | [`structure.md`](./structure.md) §1–§2 | — |
| **Upgrade** the installed skill | [`structure.md`](./structure.md) §1–§2 (what lives where) | the `upgrade` sub-skill itself (`../upgrade/SKILL.md`) — check is read-only, download needs explicit acceptance, `.dwp/` is never migrated |
| **Author** skills/agents | [`skills-integration.md`](./skills-integration.md) | — |

Do not read every file by default. Each sub-skill's "Shared resources" section
names its essential files and its conditional triggers.

## Section map (every section of the original guide, in original order)

| Section | Now in |
|---------|--------|
| ## 1. Top-Level Folder Structure | [`structure.md`](./structure.md) |
| ## 2. Naming Conventions | [`structure.md`](./structure.md) |
| ## 3. Purpose of This System | [`structure.md`](./structure.md) |
| ## 4. Plan-Level README Structure (`{PLAN_NAME}/README.md`) | [`authoring.md`](./authoring.md) |
| ## 5. Task File Structure (`N.task_{task_title}.md`) | [`authoring.md`](./authoring.md) |
| ## 6. Agent Execution Rules (Critical Behavior) | [`execution.md`](./execution.md) |
| ## 6.1. Mandatory Final Tasks → now **6.1. Final Review, Task-Local Skills and the Optional Report** (spec 2.3.0 lifecycle) | [`execution.md`](./execution.md) |
| ## 6.1. Final Review, Task-Local Skills and the Optional Report | [`execution.md`](./execution.md) |
| ## 🔄 Multi-Project Commit Workflow | [`execution.md`](./execution.md) |
| ## ⚠️ CRITICAL: Task Completion Tracking (MANDATORY) | [`execution.md`](./execution.md) |
| ## 7. How to Instruct an Agent to Generate a New Plan | [`prompts.md`](./prompts.md) |
| ## 8. How to Instruct an Agent to Execute a Plan | [`prompts.md`](./prompts.md) |
| ## 9. How to Resume an Interrupted Plan (CRITICAL) | [`prompts.md`](./prompts.md) |
| ## 10. Cleanup and Lifecycle | [`structure.md`](./structure.md) |
| ## 11. Skills & Agents Integration (MANDATORY) | [`skills-integration.md`](./skills-integration.md) |
| ## 13. Orchestrator Plans (Core Hub Only) | [`orchestrator.md`](./orchestrator.md) |
| ## 14. Team Agents Execution Mode (Claude Code Only) | [`team-agents.md`](./team-agents.md) |
| ## 15. Onboarding a Large Repo as Its Own Deep Work Plan | [`large-repo-onboarding.md`](./large-repo-onboarding.md) |
| ## 16. Orchestration at Scale | [`orchestration-at-scale.md`](./orchestration-at-scale.md) |
| ## 17. Swarm Autonomy | [`swarm.md`](./swarm.md) |
| ## 12. Summary | this file (below) |

Section numbers and headings are preserved inside each file, so a reference such
as "GUIDE §5.3" still means "section 5.3" — now found in [`authoring.md`](./authoring.md).
A reference of the form `guide/GUIDE.md §N` from an earlier version resolves
through this table.

---

## 12. Summary

This guide defines how an agent should:

- Create plans under `.dwp/plans/{PLAN_NAME}/`; `plan_paths.py` allocates
  numbered names. Existing unnumbered plans keep their names.
- Split work into ordered, single-focus task files
- Execute tasks sequentially, with strong validation and logging
- Resume interrupted plans without duplicating work
- Keep everything temporary and isolated from the main repository
- Leverage existing skills and agents for higher-quality, more consistent plans (see section 11)
- Onboard a large repo as its own Deep Work Plan — documenting docs/, per-module docs, and the `.agents/` kit task-by-task with gates and resumability (see section 15)
- Create orchestrator plans that generate child DWP plans in sub-repositories for complex multi-repo features (see section 13)
- Propagate global context to child DWPs via the Orchestrator Context Manifest (see section 13.8)
- Pass outputs between child DWPs using the inter-child output passing protocol (see section 13.9)
- **Hand off** child DWPs for execution by separate agent sessions inside each target repo (orchestrator agents never execute children inline — see §13.0) with dependency-aware execution modes and readiness gates (see section 13.10)
- Optionally enable parallel task execution via team agents as a progressive enhancement for Claude Code (see section 14)
- Run many agents at once — lanes in panes, on chosen accounts and vendors (see section 16)
- Keep a swarm running past one account's limit — capacity checks, handoff packets, lead succession (see section 17)
- Generate task files in parallel via team agents (see section 14.8)

Use this as the **authoritative specification** whenever an agent is asked to:

- Generate a new plan
- Prepare detailed per-task prompts
- Run long, focused, multi-task deep-work sessions
- Resume interrupted execution safely and efficiently
- Create orchestrator plans that coordinate child DWPs across repositories
- Hand off child DWPs for execution with dependency checking and predecessor output handoff (orchestrator never runs children inline — §13.0)
- Create team-agent-aware plans with parallel task groups (Claude Code only)
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall