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

examples/V6_PLAN_EXAMPLE.md

View on GitHub
# A v6 Plan — Minimal Worked Example

A v6 plan is **two authored artifacts + one guarded sequence**. Allocate the
folder with `shared/plan_paths.py` before authoring; this example uses the
first ID in a new repository. This
example shows the smallest honest shape; the normative rules live in
[`../spec/V6_CONTRACT.md`](../spec/V6_CONTRACT.md) (contract + journal)
and [`../spec/V6_LIFECYCLE.md`](../spec/V6_LIFECYCLE.md) (detection,
materialization, activation, amendments, coexistence).

```
.dwp/plans/PLAN_001_ship_feature_x/
├── README.md          # the human plan (what the approval digests)
├── 1.task_implement.md
├── 2.task_final_review.md
├── manifest.json      # WRITTEN BY materialize — contract pointer
├── contract.json      # WRITTEN BY materialize — stamped, content-addressed
├── journal.ndjson     # first event: the approval
└── ...                # state.json / views/ / gates/ are generated later
```

## 1. The markdown (authored)

`README.md` carries the goal, the task list and the execution rules — the
recorded create flow's shape, unchanged. Task files declare their
objective, `Touched Surface`, `Read Before Starting`, `Acceptance Criteria`
with `AC-*` ids, and `Validation` gates. The last task is the Final Review.

## 2. The contract draft (authored, outside the plan folder)

```json
{
  "schema": "https://deepworkplan.com/schema/plan-contract/v6.json",
  "spec_version": "6.0.0",
  "plan": "PLAN_001_ship_feature_x",
  "revision": 1,
  "created_at": "2026-09-26T12:00:00Z",
  "title": "Ship feature X under the v6 contract",
  "outcome": {
    "statement": "Feature X ships with verified behavior.",
    "success_definition": "Both acceptance criteria hold on observed evidence.",
    "out_of_scope": ["publicity", "release tagging"]
  },
  "acceptance": {
    "criteria": [
      { "id": "AC-tests-pass", "statement": "The suite passes.",
        "observable_check": "the repo's test command exits 0",
        "accepted_evidence": ["observed"] },
      { "id": "AC-human-review", "statement": "A human reviewed the diff.",
        "observable_check": "review sign-off recorded",
        "accepted_evidence": ["asserted"] }
    ]
  },
  "tasks": [
    { "id": "T-implement", "title": "Implement feature X",
      "prerequisites": [], "touched_surface": ["src/feature_x.py"],
      "gate_intent": [
        { "criterion": "AC-tests-pass", "check": "pytest -q" }] },
    { "id": "T-final-review", "title": "Final Review",
      "prerequisites": ["T-implement"], "touched_surface": ["src/", "tests/"],
      "gate_intent": [
        { "criterion": "AC-human-review",
          "check": "a human reviews the diff (recorded by ledger.py signoff, not executed)" }] }
  ],
  "invariants": [
    { "id": "INV-no-publication",
      "statement": "No pushes, tags or publication during this plan." }],
  "scope": {
    "allowed_paths": ["src/", "tests/"],
    "allowed_command_classes": ["python3", "pytest"],
    "forbidden_operations": ["publish", "force-push"] },
  "resource_envelope": {
    "limits": [
      { "id": "spend_usd", "unit": "USD", "limit": 40,
        "enforcement": "enforced",
        "metering_source": "host adapter: usage.total_cost_usd" },
      { "id": "wall_clock_h", "unit": "hours", "limit": 6,
        "enforcement": "advisory" } ] },
  "scheduling": {
    "max_retries_per_gate": 1, "max_adaptations_per_task": 2,
    "starvation_threshold_events": 24,
    "handoff": { "fresh_context": "context pressure at 60%",
                 "cross_host_resume": "custodian seal broken" } },
  "permissions": {
    "granted": ["gate_command_exec", "fs_write_repo_scope", "git_operations"],
    "not_granted": ["network_access", "agent_delegation"] },
  "authorization": {
    "authority": "the developer who asked for the plan",
    "mechanism": "plan_authorship",
    "boundaries": "This contract governs feature X only.",
    "consent_checkpoints": ["GO before the release commit"],
    "timestamp": "2026-09-26T12:00:00Z" },
  "dependencies": [
    { "kind": "pinned_input", "name": "python3", "detail": ">= 3.9" } ]
}
```

Validate it before proposing:
`python3 ../shared/contract_v6.py validate-contract draft.json`.

## 3. Materialization (guarded — the helper writes, never your hands)

```bash
python3 ../shared/ledger.py --plan .dwp/plans/PLAN_001_ship_feature_x \
  materialize --contract draft.json --authority sergio \
  --mechanism plan_authorship
# OK: materialized PLAN_001_ship_feature_x contract <cid> (manifest, contract,
#     approval seq 1)
```

`AC-human-review` accepts only `asserted`, so no gate closes it: once
`T-final-review` has started and the human has reviewed the diff and
written their note, record their sign-off (the intent's `check` describes
the human check; it is never executed):

```bash
python3 ../shared/ledger.py --plan .dwp/plans/PLAN_001_ship_feature_x \
  signoff --criterion AC-human-review \
  --evidence-path analysis_results/REVIEW_NOTE.md --authority sergio
# OK: signoff AC-human-review by sergio at seq <n> (asserted: a human claim,
#     never executed)
```

From here the v6 execute loop runs the plan:
`ready` selects, `start` opens the attempt and records the fingerprint,
`gate` mints observed evidence, `complete` is refused until every
criterion holds, `project` + `views.py render` regenerate the
projections, `receipt` recomputes the outcome from the records.

**What never happens:** the contract edited in place after approval (a
change is a revision under `contracts/` with fresh authority — refine),
a manifest pointer rewritten, a v5 plan migrated silently, or a task
closed on narrative.
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