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

spec/V7_ROADMAP.md

View on GitHub
# DeepWorkPlan v7 — What Ships and What Follows (Planning Record)

> **Status: NON-NORMATIVE.** A planning record. The normative rules for
> everything that ships live in [`CONFIG.md`](CONFIG.md),
> [`ADDONS.md`](ADDONS.md), [`V7_ABILITIES.md`](V7_ABILITIES.md) and
> [`V7_CONTRACT.md`](V7_CONTRACT.md). Nothing here gates conformance.

## The rule v7 is built on

**The methodology works alone.** The `deepworkplan` skill needs no addon to
create, execute, verify or resume a plan. Every addon is optional and only
amplifies it; no addon gates conformance and no flow requires one
(`tests/standalone-methodology.bats` runs the whole lifecycle with no
configuration, every addon disabled, unknown keys and malformed configs, and
proves no addon file is opened).

The second rule follows from the first: a capability that is useful without
DWP is its **own product** (own repository, license, tags and interface
number), and the pack carries a **thin integrator** for it — never a copy.

## What v7 ships (7.0.0)

| Surface | What it is |
|---|---|
| **Addon registry** | `.dwp/config.json` / `~/.dwp/config.json` → `addons.<key>` (`enabled`, informative `version`); one stdlib reader shared with `benchmark`; per-key precedence; fail-closed with one warning; absent = not enabled ([`CONFIG.md`](CONFIG.md)). |
| **Addon descriptors** | `addons/<key>/addon.json` for every in-pack addon: pinned product (repo, exact tag, interface), read-only detect (argv without a shell, or paths), abilities, grants, transport ([`ADDONS.md`](ADDONS.md) §7). |
| **Addon-provided abilities** | effective abilities = host ∪ abilities of enabled, valid, detected, interface-compatible addons; computed per call, never persisted; an ability is never authority or consent ([`V7_ABILITIES.md`](V7_ABILITIES.md)). |
| **v7 contract generation** | `plan-contract/v7` (v6 + `parallel_safe`), `journal-event/v7` (v6 + `delegation`), `plan-manifest/v7`; default for new plans; v6 plans unchanged ([`V7_CONTRACT.md`](V7_CONTRACT.md)). |
| **Delegation** | `ledger.py delegate launch|observe|collect|cancel` behind a recorded gate (grant, marker, ability); `execute/delegation.md`; a delegate's result stays `asserted` until the plan's own gates observe it. |
| **Thin integrators** | `agentkit` → `coding-agents-kit@v1.0.1` (headless transport, `ak run`; autonomy by default with an always-winning opt-out since `v0.2.0`); `herdr` → `herdr-peers@v1.0.0` (interactive transport; stamp `[herdr-peers]`, protocol owned by herdr-peers); `devcontainer` → `devcontainer-kit@v1.0.1` (`dck init` and the `dck-dockerfile` skill, interface 2, per-repository Dockerfile, vendor-neutral); `vim` → `deepworkplan-vim@v1.0.0` (surface-driven editor offer). |
| **Pre-release channel** | `prerelease.yml` cuts `X.Y.Z-beta.N` on dispatch (never `latest`, with `SHA256SUMS`); stable releases ignore pre-release tags and graduate only on `[graduate]`. |
| **Standard** | DWP standard **7.0.0** (normative additions above); `6.0.0` declarations stay valid. |

Interfaces between the pieces are integers (`interface: 1` everywhere in v7.0; devcontainer-kit moved to `2` at `v0.2.0`);
tags pin what is installed. An unknown interface major is one warning and
"not available" — never an error.

## Release order

The 7.0.0 release history, not the current pins: each addon's
`addon.json` (`product.tag`) is the pin in force.

1. Product tags: `herdr-peers` `v0.1.0`, `coding-agents-kit` `v0.1.1`
   (supersedes `v0.1.0`, a security patch), `devcontainer-kit` `v0.1.4`
   (after the `v0.1.1` security release and an agents-layer fix),
   `deepworkplan-vim` `v0.4.2`.
2. `deepworkplan-skill` `v7.0.0-beta.1` — a GitHub **pre-release**.
3. A field test in real repositories.
4. `v7.0.0` — graduated from the beta by a `[graduate]` merge.

## Follow-ups (v7.x)

- **`deepworkplan.nvim`** — the editor's `lua/dwp/` modules as a plugin for
  people who keep their own Neovim config (v7.1). The vim addon names this
  route and never offers it before it ships.
- **A v7 benchmark record** — delivered in 7.1.5: `generation` accepts
  `"v6"` and `"v7"`. The record still carries a plain `X.Y.Z` pack version,
  so plans run by a pre-release pack are reported "not measured".
- **`addons.version` parity** — informative in 7.0.0; `verify` warns on a
  mismatch. A parity failure mode is a candidate once the field test shows
  how often versions drift.
- **devcontainer-kit workspaces** (satellites, port pools, a proxy) — in the
  kit's own roadmap, not the pack's.
- **Sender authentication between peers** — herdr-peers' `from=` is a claim;
  a scope allow-list (`HERDR_PEERS_SCOPE`) is the mitigation today.
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