claude-code-plugin-ref…
Explain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins. Do not use for ops; use night-market-operations.
Orchestrates full project lifecycle by auto-detecting state and routing to the correct phase. Use when starting or resuming a project mid-workflow.
$ npx -y skills add athola/claude-night-market --skill mission-orchestrator --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/mission-orchestratorContext preview
The summary Claude sees to decide when to auto-load this skill.
Orchestrates full project lifecycle by auto-detecting state and routing to the correct phase. Use when starting or resuming a project mid-workflow.
name: mission-orchestrator description: Orchestrates full project lifecycle by auto-detecting state and routing to the correct phase. Use when starting or resuming a project mid-workflow. alwaysApply: false category: workflow-orchestration tags: - mission - orchestrator - lifecycle - full-cycle - automation dependencies: - attune:project-brainstorming - attune:project-specification - attune:project-planning - attune:project-execution - attune:war-room-checkpoint - attune:war-room - leyline:risk-classification - leyline:damage-control - leyline:additive-bias-defense - imbue:justify - imbue:vow-enforcement - abstract:friction-detector tools: [] provides: workflow: - mission-lifecycle - state-detection - phase-routing - session-recovery - reflexion-buffer - trust-tier - adaptive-constraints usage_patterns: - full-cycle-development - mission-resume - phase-routing complexity: advanced model_hint: deep estimated_tokens: 600 progressive_loading: true modules: - modules/mission-types.md - modules/state-detection.md - modules/phase-routing.md - modules/mission-state.md - modules/plan-review.md - modules/plan-versioner.md - modules/feedback-collector.md - modules/context-injector.md - modules/iteration-governor.md - modules/reflexion-buffer.md - modules/trust-tier.md - modules/adaptive-constraints.md references: - references/mission-charter.md - references/progress-report.md role: entrypoint
Wraps the entire attune development lifecycle (brainstorm → specify → plan → execute) into a single mission with automatic state detection, type selection, and phase routing. Follows the "persistent presence lens" pattern from `spec-kit:speckit-orchestrator`: delegates entirely to existing skills via `Skill()` calls, never re-implements phase logic.
1. State Detection
Scan for existing artifacts (project-brief.md, specification.md, etc.)
|
2. Mission Type Selection
Auto-detect type based on artifacts, or accept user override
|
3. Phase Routing Loop
For each phase in the mission type:
a. Pre-phase validation (check prerequisites)
b. Invoke Skill(attune:{phase-skill})
c. Post-phase artifact check (verify output exists)
d. Post-phase backlog triage (create GitHub issues
for out-of-scope items after brainstorm/specify)
e. Update mission state
f. User checkpoint (skippable with --auto)
g. Error handling via leyline:damage-control
|
4. Completion
All phases complete, final state saved| Type | Phases | Auto-detected When | |------|--------|--------------------| | `full` | brainstorm → specify → plan → execute | No artifacts exist | | `standard` | specify → plan → execute | `docs/project-brief.md` exists | | `tactical` | plan → execute | `docs/specification.md` exists | | `quickfix` | execute | `docs/implementation-plan.md` exists | | `review` | scope → investigate → verify → report | the request names existing software to audit, dogfood, or review |
`review` is the one type selected from request intent rather than from artifacts, because a tree of build artifacts looks the same whether the ask is "ship this" or "audit this". Its check runs first. It produces `reports/<topic>-<YYYY-MM-DD>.md` and never enters the war-room gate, which guards a plan-to-execute transition a review mission does not have.
See `modules/mission-types.md` for full type definitions and custom type support.
| Phase | Skill Invoked | Artifact Produced | |-------|--------------|-------------------| | brainstorm | `Skill(attune:project-brainstorming)` | `docs/project-brief.md` | | specify | `Skill(attune:project-specification)` | `docs/specification.md` | | plan | `Skill(attune:project-planning)` | `docs/implementation-plan.md` | | execute | `Skill(attune:project-execution)` | Implemented code and tests |
Review missions route to the existing review skills rather than to attune phase skills:
| Phase | Skill Invoked | Artifact Produced | |-------|--------------|-------------------| | scope | `Skill(pensive:tiered-audit)` | Tier selection and bounded scope | | investigate | `Skill(imbue:feature-review)` plus the `pensive:*` domain lenses | Raw findings | | verify | `Skill(imbue:proof-of-work)` | Evidence references per finding | | report | `Skill(imbue:structured-output)` | `reports/<topic>-<YYYY-MM-DD>.md` |
The orchestrator **never** re-implements phase logic. Each phase is a complete `Skill()` invocation that handles its own workflow.
Missions delegate execution by default. `Skill(conjure:delegation-core)` governs the decision, and its default posture is on: a phase that reaches execution work hands it to an external CLI without waiting to be asked.
| Phase | Delegates | Why | |-------|-----------|-----| | brainstorm | No | Reasoning; the Keep Local clause holds | | specify | No | Reasoning | | plan | No | Reasoning | | execute | Yes,
A plugin marketplace for Claude Code. Install only the plugins you need to run git workflows, code review, spec-driven development, and autonomous agents from inside your Claude Code session.
Explain plugin, skill, command, agent, and hook mechanics used here. Use when authoring or debugging plugins. Do not use for ops; use night-market-operations.
States load-bearing decisions, invariants, and weak points. Use when judging a design change. Do not use for gating; use night-market-change-control.
Rebuild the dev environment: uv, Python tiers, pins, traps. Use when onboarding or toolchain breaks. Do not use for daily commands; use night-market-operations.
Classify, gate, and review changes. Use when landing a PR, releasing, or amending rules. Do not use for failure triage; use night-market-debugging-playbook.
Search and record project memory (Discussions, journal, ADRs). Use before re-investigating anything. Do not use for settled battles; see failure-archaeology.
Bind loop 'done' to unfakeable gates. Use to harden egregore/herald loops or promote completion_integrity. Not for QA gates; use night-market-validation-and-qa.