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/schema/context-manifest-v6.schema.json

View on GitHub
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://deepworkplan.com/schema/context-manifest/v6.json",
  "title": "DWP v6 per-task context manifest",
  "description": "The derived, read-only context selection for ONE task of a v6 plan, produced by shared/context_manifest.py (spec/V6_CONTEXT.md): the cheap re-anchoring surface an executing agent loads instead of history. Never hand-edited and never a source of truth - every value is recomputed from the contract and the journal, so two derivations over the same records are identical (deterministic under replay; as_of carries the records' position and timestamp, not a wall clock). Context pruning can never hide the acceptance or authorization boundary: the three mandatory sections (authorization, repository_rules, acceptance) are unconditional, and a --sections request that would drop one is refused.",
  "type": "object",
  "additionalProperties": false,
  "required": [
    "schema",
    "derived_by",
    "plan",
    "contract_id",
    "contract_revision",
    "task",
    "as_of",
    "authorization",
    "repository_rules",
    "touched_surface",
    "acceptance",
    "evidence",
    "next_action",
    "dead_ends",
    "freshness"
  ],
  "properties": {
    "schema": {
      "const": "https://deepworkplan.com/schema/context-manifest/v6.json"
    },
    "derived_by": {
      "const": "dwp context_manifest.py",
      "description": "The shipped helper identity that produced this derivation; a document produced by any other path must not wear this schema."
    },
    "plan": {
      "type": "string",
      "pattern": "^PLAN_[A-Za-z0-9_-]+$",
      "description": "The plan folder name, mirrored from the contract."
    },
    "contract_id": {
      "type": "string",
      "pattern": "^[a-f0-9]{64}$",
      "description": "The live contract's content-addressed identity this derivation was computed against."
    },
    "contract_revision": {
      "type": "integer",
      "minimum": 1,
      "description": "The live contract's revision; after an amendment this is the highest revision under contracts/."
    },
    "task": {
      "type": "string",
      "minLength": 1,
      "description": "The task id this manifest selects context for."
    },
    "as_of": {
      "type": "object",
      "additionalProperties": false,
      "required": ["last_seq", "event_ts"],
      "properties": {
        "last_seq": {
          "type": "integer",
          "minimum": 0,
          "description": "The journal sequence of the last event included; the manifest is stale by definition once the journal grows past it."
        },
        "event_ts": {
          "type": "string",
          "description": "The timestamp of that last event (the scheduler's clock, A11)."
        }
      }
    },
    "authorization": {
      "type": "object",
      "additionalProperties": false,
      "required": ["approvals", "contract_authorization", "permissions"],
      "properties": {
        "approvals": {
          "type": "array",
          "description": "Approval events citing the live contract id - the running authority (task_start is refused without one).",
          "items": {
            "type": "object",
            "additionalProperties": false,
            "required": ["authority", "mechanism", "ts", "seq"],
            "properties": {
              "authority": {"type": ["string", "null"]},
              "mechanism": {
                "type": "string",
                "description": "How authority was granted (plan_authorship or pre_authorization); the mechanism is recorded honestly and both gate identically (A2/A3)."
              },
              "ts": {"type": ["string", "null"]},
              "seq": {"type": "integer", "minimum": 1}
            }
          }
        },
        "contract_authorization": {
          "description": "The contract's authorization block verbatim; its shape is governed by plan-contract/v6.json, not restated here.",
          "type": ["object", "null"]
        },
        "permissions": {
          "description": "The contract's permissions block verbatim (granted / not_granted); its shape is governed by plan-contract/v6.json, not restated here.",
          "type": ["object", "null"]
        }
      }
    },
    "repository_rules": {
      "type": "object",
      "additionalProperties": false,
      "required": ["scope", "invariants", "dependencies"],
      "properties": {
        "scope": {
          "description": "The contract's scope block verbatim (allowed_paths, allowed_command_classes, forbidden_operations); governed by plan-contract/v6.json.",
          "type": ["object", "null"]
        },
        "invariants": {
          "type": "array",
          "description": "Per declared invariant: the statement, plus the latest grammar-matching observation's state (pass / fail / stale / unevaluated).",
          "items": {
            "type": "object",
            "additionalProperties": false,
            "required": ["id", "statement", "state", "seq"],
            "properties": {
              "id": {"type": "string", "minLength": 1},
              "statement": {"type": "string"},
              "state": {
                "enum": ["pass", "fail", "stale", "unevaluated"]
              },
              "seq": {
                "type": ["integer", "null"],
                "description": "The seq of the observation that produced the state, or null when unevaluated."
              },
              "detail": {
                "type": "string",
                "description": "The fail/stale detail when the state carries one."
              }
            }
          }
        },
        "dependencies": {
          "type": "array",
          "description": "The contract's dependencies block verbatim (pinned inputs, external systems); governed by plan-contract/v6.json.",
          "items": {"type": "object"}
        }
      }
    },
    "touched_surface": {
      "type": "object",
      "additionalProperties": false,
      "required": ["files", "widen_discovery", "widen_reasons"],
      "properties": {
        "files": {
          "type": "object",
          "description": "Repo-relative path to its sha256 content digest; a null value means the entry is missing on disk.",
          "additionalProperties": {
            "type": ["string", "null"],
            "pattern": "^[a-f0-9]{64}$"
          }
        },
        "widen_discovery": {
          "type": "boolean",
          "description": "True when discovery must widen this cycle: a touched-surface entry is missing on disk, or the surface's impact is unmapped (no in-window accepted evidence yet)."
        },
        "widen_reasons": {
          "type": "array",
          "items": {"type": "string"}
        }
      }
    },
    "acceptance": {
      "type": "array",
      "description": "This task's criteria with their closure decisions, recomputed by outcomes.py closure - a projection, never a declaration.",
      "items": {
        "type": "object",
        "additionalProperties": false,
        "required": ["criterion", "task", "control_kind", "satisfied", "mechanism"],
        "properties": {
          "criterion": {"type": "string", "minLength": 1},
          "task": {"type": "string"},
          "control_kind": {
            "enum": ["regression", "discrimination", "none"],
            "description": "none for evidence-closed criteria; regression/discrimination require an executed, in-window, discriminating control pair."
          },
          "satisfied": {"type": "boolean"},
          "mechanism": {
            "type": "string",
            "description": "How it closes or why it is still open: control_pair, evidence, reconciled, or an open/blocked explanation string."
          },
          "via_seq": {
            "type": ["integer", "null"],
            "description": "The journal seq of the closing record when one exists."
          },
          "verdict": {
            "enum": ["discriminating"],
            "description": "The control verdict that closed a controlled criterion."
          },
          "trust": {
            "enum": ["observed", "asserted"],
            "description": "The trust label of the closing evidence; observed means a shipped helper itself executed the check (A1)."
          },
          "evidence_path": {
            "type": "string",
            "description": "Pointer to the recorded evidence artifact under the plan."
          },
          "authority": {
            "type": "string",
            "description": "The amendment authority behind a reconciled closure (A4/D2-4)."
          }
        }
      }
    },
    "evidence": {
      "type": "array",
      "description": "In-window accepted evidence for this task's satisfied criteria, with pointers that are re-checked against disk at derivation time.",
      "items": {
        "type": "object",
        "additionalProperties": false,
        "required": ["criterion", "seq", "trust", "evidence_path", "pointer_resolves"],
        "properties": {
          "criterion": {"type": "string", "minLength": 1},
          "seq": {"type": "integer", "minimum": 1},
          "trust": {"enum": ["observed", "asserted"]},
          "evidence_path": {"type": "string"},
          "pointer_resolves": {
            "type": "boolean",
            "description": "Whether the evidence artifact exists on disk at derivation time; a dangling pointer is surfaced, never hidden."
          }
        }
      }
    },
    "next_action": {
      "type": "object",
      "additionalProperties": false,
      "required": ["step", "action"],
      "properties": {
        "step": {
          "enum": ["approval", "start", "authority", "control", "evidence", "complete"],
          "description": "The deterministic ladder's first match, in order: approval -> start -> authority -> control -> evidence -> complete."
        },
        "action": {
          "type": "string",
          "description": "The concrete command or authority act the ladder prescribes."
        },
        "criteria": {
          "type": "array",
          "items": {"type": "string", "minLength": 1},
          "description": "The criteria the step addresses, when it addresses specific ones."
        }
      }
    },
    "dead_ends": {
      "type": "array",
      "description": "The U4 digest: recorded dead approaches (failed gates, refusals, refused adaptations, non-discriminating controls), retention-biased - an entry leaves only on a proven record fact, never on a mere surface change.",
      "items": {
        "type": "object",
        "additionalProperties": false,
        "required": ["kind", "seq", "ts"],
        "properties": {
          "kind": {
            "enum": ["failed_gate", "refusal", "refused_adaptation", "non_discriminating_control"]
          },
          "seq": {"type": "integer", "minimum": 1},
          "ts": {"type": ["string", "null"]},
          "task": {"type": "string"},
          "criterion": {"type": "string"},
          "command": {"type": "string"},
          "exit_code": {"type": "integer"},
          "cause": {"type": "string"},
          "run_fingerprint": {
            "type": "string",
            "pattern": "^[a-f0-9]{64}$"
          },
          "subject": {"type": "string"},
          "stage": {"type": "string"},
          "reason": {"type": "string"},
          "verdict": {"type": "string"},
          "recorded_contract_id": {
            "type": "string",
            "pattern": "^[a-f0-9]{64}$"
          },
          "aged_out": {
            "type": "string",
            "description": "Why the entry no longer gates discovery (e.g. a superseded contract revision)."
          }
        }
      }
    },
    "freshness": {
      "type": "object",
      "additionalProperties": false,
      "required": ["inputs_fingerprint", "rule"],
      "properties": {
        "inputs_fingerprint": {
          "type": "string",
          "pattern": "^[a-f0-9]{64}$",
          "description": "Digest over the contract id and the current touched-surface digests; a stored fingerprint different from the current one invalidates the summary that carries it."
        },
        "rule": {
          "type": "string",
          "description": "The freshness rule in words, restated with every derivation."
        }
      }
    },
    "history_triggers": {
      "type": "array",
      "description": "Optional section: the ONLY declared triggers under which history beyond this manifest loads (none, a handoff, an amendment affecting this task).",
      "items": {
        "type": "object",
        "additionalProperties": false,
        "required": ["trigger", "loads"],
        "properties": {
          "trigger": {"type": "string", "minLength": 1},
          "loads": {"type": "string", "minLength": 1}
        }
      }
    }
  }
}
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