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/V6_RESOURCES.md

View on GitHub
# V6 Resources — Envelope Reserves, Exhaustion and Host Capability Negotiation

> **Status: v6 line.** This document defines the v6 resource contract: the
> **host capability negotiation**, the **counter-source split**
> (journal-observable vs host-only), the **reserve** representation, the
> **exhaustion** grammar and dispatch hold, the **cancellation
> settlement**, and the **routing posture**. The design source is
> `docs/evaluations/v6/ARCHITECTURE_RFC.md` §8 (draft-4); the shipped
> implementation is `shared/resources.py` (Python 3.9+ stdlib, composing
> the envelope accounting of `shared/scheduler.py` and the record
> discipline of `shared/ledger.py` — it never duplicates either). The v5
> standard is untouched: these rules bind **v6 new plans only**.

All documents in this spec use RFC-2119 language. A limit the host cannot
meter is **advisory, not enforced**: enforcement parity across hosts is
never claimed.

## 1. Host capability negotiation

* The runtime host states its **abilities** as a closed set:
  `stop_agent`, `meter_spend`, `meter_tokens`, `meter_wall_clock`,
  `cancel_children`, `model_routing`, `subagents`, `telemetry`. Abilities
  are distinct from the contract's permission **grants** (§3.2 of the
  contract spec): a grant is authority, an ability is what the host can
  actually do.
* An unknown ability key MUST be refused — a capability is never invented.
* An unstated ability is `false`. The **minimal host** (no model
  switching, no subagents, no telemetry, no stop) is a supported degraded
  posture, never an error; every limit that needs the missing ability
  degrades to advisory with the missing ability named.
* From the 7.0.0 line, enabled and detected addons MAY contribute
  abilities at runtime on top of this declaration — never persisted, never
  invented — per [`V7_ABILITIES.md`](V7_ABILITIES.md); this section is
  otherwise unchanged.

## 2. Counter sources

* **Journal-observable counters** (wall-clock span, gate retries,
  dispatch calls) are computed from the plan's own records; no host
  ability is required to enforce them.
* **Host-only counters** (spend, provider tokens) require the matching
  `meter_*` ability and an **observed** `resource_sample` from a host
  adapter (A1: only a host_adapter actor reading a real meter mints
  observed samples). A metered host with no sample on record enforces
  the **pending side only** — a missing counter is not free usage.
* A unit outside every known family MUST degrade to advisory with the
  unit named; a meter is never invented.

## 3. Reserves

* A limit MAY declare `reserve` (a number, `0 <= reserve <= limit`). The
  dispatchable ceiling is `limit - reserve`; a refusal fires when
  `spent + pending > limit - reserve`. Reserves exist so verification,
  retry and resume cannot be starved by ordinary work.
* The ceiling comparison is **runtime semantics** (it depends on the
  sibling `limit` value, which JSON Schema cannot express); both halves
  still reject a malformed (non-numeric, negative) reserve.

## 4. Exhaustion

* Hitting a limit MUST persist an **incomplete checkpoint** — the journal
  and snapshot already are that checkpoint — and stop dispatch. The stop
  is recorded as an observation with the grammar
  `LIMIT: exhausted <limit-id>: <detail>`; only a declared limit may be
  exhausted (an undeclared counter is never recorded).
* An exhaustion observation **can never satisfy an acceptance criterion**
  (the ledger counts only `gate_run` events); exhaustion structurally
  cannot mint completed evidence.
* Dispatch stays held until an explicit `LIMIT: recovered <id>` record;
  recovery is never silent.
* Advisory limits surface, never hold.

## 5. Cancellation settlement

* An in-flight reservation (an authorized adaptation's declared impact)
  settles **exactly once**: `RESERVATION: <key>: released` (the cancelled
  child never consumed the budget) or `RESERVATION: <key>: committed`.
* Identical replay is idempotent (content-keyed dedup). A second
  settlement with a **different** disposition is the double-charge
  ambiguity and MUST be refused, never arbitrated.
* Pending accounting subtracts released reservations; with zero
  settlements it equals the envelope core's pending exactly (drift-guarded
  by tests).

## 6. Routing posture

* The default posture is **fixed-model**. Model-tier switching requires
  BOTH the contract grant `model_routing` AND the host ability of the
  same name; each refusal names the missing side(s).
* Parallel dispatch requires the `agent_delegation` grant AND the host
  `subagents` ability; otherwise the posture is sequential-only.
* A routing posture is a permission statement, **never an efficacy
  claim**: switching being authorized says nothing about whether
  switching helps.
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