@cleocode/skills 2.0.0

package/skills/ct-cleo/references/orchestrator-constraints.md

@@ -0,0 +1,55 @@
+# Orchestrator Constraints (Detailed)
+
+## ORC Rules
+
+| ID | Rule | Enforcement |
+|----|------|-------------|
+| ORC-001 | Stay high-level | NO implementation details |
+| ORC-002 | Delegate ALL work | Use Task tool for everything |
+| ORC-003 | No full file reads | Manifest summaries ONLY |
+| ORC-004 | Dependency order | Sequential spawning per wave |
+| ORC-005 | Context budget | Stay under 10K tokens |
+| ORC-006 | Max 3 files per agent | Scope limit per spawn |
+| ORC-007 | All work traced to Epic | No orphaned work |
+| ORC-008 | Zero architectural decisions | Must be pre-decided by HITL |
+
+## Spawn Pipeline
+
+### MCP Spawn Operations
+
+```
+# Analyze dependency waves
+query({ domain: "orchestrate", operation: "analyze", params: { epicId: "T001" }})
+
+# Get ready tasks
+query({ domain: "orchestrate", operation: "ready", params: { epicId: "T001" }})
+
+# Get next task suggestion
+query({ domain: "orchestrate", operation: "next", params: { epicId: "T001" }})
+```
+
+### CLI Spawn Operations
+
+```bash
+cleo orchestrator start --epic T001
+cleo orchestrator analyze T001
+cleo orchestrator ready --epic T001
+cleo orchestrator next --epic T001
+cleo orchestrator spawn T002
+```
+
+### Spawn Workflow
+
+1. Select skill protocol for task (auto-dispatch or explicit)
+2. Prepare spawn context (resolve ALL tokens)
+3. Verify `tokenResolution.fullyResolved == true`
+4. Spawn `cleo-subagent` with resolved prompt via Task tool
+
+### Token Pre-Resolution
+
+**CRITICAL**: Orchestrator MUST resolve ALL tokens before spawn. Verify:
+- All `@` references resolved
+- All `{{TOKEN}}` placeholders substituted
+- `tokenResolution.fullyResolved == true`
+- Task exists (`cleo exists T####`)
+- Output directory exists

package/skills/ct-cleo/references/session-protocol.md

@@ -0,0 +1,162 @@
+# Session Protocol (Detailed)
+
+Sessions track work context across agent interactions.
+
+## Multi-Session Requirements
+
+**CRITICAL: Multi-session requires BOTH flags:**
+
+```bash
+ct session start --scope epic:T001 --auto-focus --name "Name"
+#                ^^^^^^^^^^^^^^^^^ REQUIRED     ^^^^^^^^^^^^^ REQUIRED
+```
+
+## MCP Session Operations
+
+```
+mutate({ domain: "session", operation: "start",
+  params: { scope: "epic:T001", name: "Work", autoStart: true }})
+query({ domain: "session", operation: "status" })
+mutate({ domain: "session", operation: "end", params: { note: "Progress" }})
+```
+
+## CLI Session Protocol
+
+### START (ALWAYS first)
+
+```bash
+ct session list                # Check existing sessions
+ct session status              # Current session
+ct session resume <id>         # Resume existing
+# OR (only if no suitable session):
+ct session start --scope epic:T001 --auto-focus --name "Work"
+```
+
+### WORK
+
+```bash
+ct current                     # Show active task
+ct next                        # Task suggestion
+ct add "Task" --depends T005   # Add related
+ct complete T005               # Complete task
+ct start T006                  # Start next task
+```
+
+### END (ALWAYS when stopping)
+
+```bash
+ct complete <id>               # Complete current
+ct archive                     # Clean up done tasks
+ct session end --note "Progress"
+```
+
+## Research & Manifest Operations
+
+### Output Requirements
+
+Subagent output files follow this structure:
+
+```markdown
+# <Title>
+
+**Task**: T####
+**Epic**: T####
+**Date**: YYYY-MM-DD
+**Status**: complete | partial | blocked
+
+---
+
+## Summary
+<2-3 sentence executive summary>
+
+## Content
+<main deliverable>
+```
+
+### Manifest Entry (MANIFEST.jsonl)
+
+Append ONE line (no pretty-printing):
+
+```json
+{"id":"T####-slug","file":"path","title":"...","date":"YYYY-MM-DD","status":"complete","agent_type":"research","topics":[],"key_findings":[],"actionable":true,"needs_followup":[],"linked_tasks":["T####"]}
+```
+
+### Status Classification
+
+| Status | Condition | Action |
+|--------|-----------|--------|
+| `complete` | All objectives achieved | Complete normally |
+| `partial` | Some objectives achieved | Populate `needs_followup` |
+| `blocked` | Cannot proceed | Document blocker |
+
+## Token System
+
+Orchestrators resolve ALL tokens before spawning subagents. Subagents CANNOT resolve `@` references or `{{TOKEN}}` patterns.
+
+### Standard Tokens
+
+| Token | Description |
+|-------|-------------|
+| `{{TASK_ID}}` | Current task identifier |
+| `{{EPIC_ID}}` | Parent epic identifier |
+| `{{DATE}}` | Current date (ISO) |
+| `{{TOPIC_SLUG}}` | URL-safe topic name |
+| `{{OUTPUT_DIR}}` | Output directory |
+| `{{MANIFEST_PATH}}` | Manifest file path |
+| `{{TASK_TITLE}}` | Task title |
+| `{{TASK_DESCRIPTION}}` | Task description |
+
+### Command Tokens
+
+| Token | Default |
+|-------|---------|
+| `{{TASK_SHOW_CMD}}` | `cleo show` |
+| `{{TASK_START_CMD}}` | `cleo start` |
+| `{{TASK_COMPLETE_CMD}}` | `cleo complete` |
+| `{{TASK_LINK_CMD}}` | `cleo research link` |
+
+## Skill Ecosystem
+
+Skills are **context injections, NOT agents**. The orchestrator selects and injects skill content into `cleo-subagent`.
+
+### Discovery
+
+```
+query({ domain: "skills", operation: "list" })
+query({ domain: "skills", operation: "show", params: { name: "ct-orchestrator" }})
+```
+
+### Key Skills
+
+| Skill | Category | Use Case |
+|-------|----------|----------|
+| `ct-orchestrator` | orchestration | Multi-agent coordination |
+| `ct-epic-architect` | planning | Epic decomposition |
+| `ct-task-executor` | execution | General task execution |
+| `ct-research-agent` | research | Information gathering |
+| `ct-spec-writer` | specification | Document creation |
+| `ct-validator` | validation | Quality checks |
+| `ct-documentor` | documentation | Documentation generation |
+| `ct-test-writer-bats` | testing | BATS test creation |
+
+### Dispatch Priority
+
+1. **Label-based**: Task labels match skill tags
+2. **Catalog-based**: CAAMP dispatch matrix
+3. **Type-based**: Task type maps to protocol
+4. **Keyword-based**: Title/description matches triggers
+5. **Fallback**: `ct-task-executor`
+
+## Release Workflow
+
+**CRITICAL**: `release ship` only commits version metadata. All code changes MUST be committed BEFORE running `release ship`.
+
+```bash
+git add <files> && git commit -m "feat(T####): description"
+cleo release create v1.0.0
+cleo release ship v1.0.0 --bump-version --create-tag --push
+```
+
+## Project Context
+
+When available, project-specific configuration is loaded from `.cleo/project-context.json` (generated by `cleo init --detect`). Contains detected project type, testing framework, and LLM hints.

package/skills/ct-codebase-mapper/SKILL.md

@@ -0,0 +1,82 @@
+---
+name: ct-codebase-mapper
+version: 1.0.0
+description: Codebase analysis and mapping for autonomous agent understanding. Builds structured maps of project stack, architecture, conventions, testing, integrations, and concerns.
+category: recommended
+tier: 1
+protocol: null
+dependencies: []
+compatibility:
+  - claude-code
+  - cursor
+  - windsurf
+  - gemini-cli
+triggers:
+  - codebase map
+  - analyze codebase
+  - understand project
+  - brownfield analysis
+  - project structure
+---
+
+# Codebase Mapper
+
+Structured codebase analysis for autonomous agent understanding.
+
+## Quick Start
+
+| Goal | Command | Cost |
+|------|---------|------|
+| Quick analysis | `query admin map` | ~500 tokens |
+| Deep analysis + store | `mutate admin map` | ~800 tokens |
+| Focus on one area | `query admin map {focus: "concerns"}` | ~300 tokens |
+| CLI | `cleo map` / `cleo map --store` | — |
+
+## Progressive Disclosure
+
+### Tier 0: Quick Analysis
+
+```
+query admin map
+```
+
+Returns structured `CodebaseMapResult` with stack, architecture, structure, conventions, testing, integrations, and concerns.
+
+### Tier 1: Store to Brain
+
+```
+mutate admin map
+```
+
+Same analysis, but stores patterns, learnings, and observations to brain.db. Tagged with `source: 'codebase-map'` for filtering.
+
+### Tier 2: Focused Analysis
+
+```
+query admin map {focus: "concerns"}
+```
+
+Focus areas: `stack`, `architecture`, `structure`, `conventions`, `testing`, `integrations`, `concerns`.
+
+## When to Use
+
+- **New project onboarding**: Run `mutate admin map` to build brain.db context
+- **Brownfield init**: `cleo init --map-codebase` runs analysis during initialization
+- **Before epic planning**: Understand project structure before decomposing work
+- **Tech debt assessment**: `query admin map {focus: "concerns"}` for TODOs and large files
+
+## Output Structure
+
+```typescript
+{
+  projectContext: ProjectContext,  // From detectProjectType()
+  stack: StackAnalysis,           // Languages, frameworks, deps
+  architecture: ArchAnalysis,     // Layers, entry points, patterns
+  structure: StructureAnalysis,   // Directory tree with annotations
+  conventions: ConventionAnalysis,// Naming, linting, formatting
+  testing: TestingAnalysis,       // Framework, patterns, coverage
+  integrations: IntegrationAnalysis, // APIs, DBs, CI/CD
+  concerns: ConcernAnalysis,      // TODOs, large files, complexity
+  analyzedAt: string
+}
+```