agileflow 3.1.0 → 3.2.1

package/src/core/experts/documentation/expertise.yaml

@@ -1,6 +1,6 @@
 domain: documentation
-last_updated: 2026-02-03
-version: 1.3
+last_updated: 2026-02-14
+version: 1.4
 
 # AgileFlow-specific documentation structure (learned from actual codebase)
 files:
@@ -153,7 +153,7 @@ learnings:
 
   - date: 2026-01-09
     context: "Created IDE Integrations documentation for AgileFlow"
-    insight: "IDE handler system supports 4 IDEs (Claude Code, Cursor, Windsurf, Codex CLI) through plugin architecture. Each IDE has custom config directory (.claude/, .cursor/, .windsurf/, .codex/) and different installation models. Claude Code most advanced (damage control, spawnable agents), Codex CLI unique (per-repo skills, user-level prompts, AGENTS.md instructions)"
+    insight: "IDE handler system supports 4 IDEs (Claude Code, Cursor, Windsurf, OpenAI Codex) through plugin architecture. Each IDE has custom config directory (.claude/, .cursor/, .windsurf/, .codex/) and different installation models. Claude Code most advanced (damage control, spawnable agents), OpenAI Codex unique (per-repo skills, user-level prompts, AGENTS.md instructions)"
     created_files:
       - "apps/docs/content/docs/features/ide-integrations.mdx (700+ lines)"
       - "apps/docs/content/docs/features/index.mdx (updated with IDE section)"
@@ -168,7 +168,7 @@ learnings:
       - "Claude Code subagent spawning, damage control hooks"
       - "Cursor unique features, differences from Claude Code"
       - "Windsurf workflow management, VSCode integration"
-      - "Codex CLI dual installation model (per-repo skills, user-level prompts, AGENTS.md)"
+      - "OpenAI Codex dual installation model (per-repo skills, user-level prompts, AGENTS.md)"
       - "Dynamic IDE handler system, extensibility guide"
       - "Content injection system explanation"
       - "Troubleshooting guide for common issues"
@@ -235,3 +235,25 @@ learnings:
       - "Formatting consistent (tables, code blocks, bullets) ✓"
     source: "packages/cli/src/core/commands/*.md vs apps/docs/content/docs/commands/*.mdx"
     notes: "Used systematic comparison approach: extracted descriptions, parameters, and features from 50 source commands against documentation. Prioritized commands with most feature additions: babysit (Smart Detection, Story Claiming, Logic Audit), configure (profiles, hierarchical menus). All changes preserve source accuracy while making docs more discoverable and comprehensive."
+
+  - date: 2026-02-14
+    context: "Audited README files for v3.0.2 - IDE config locations and badge accuracy"
+    insight: "Found and fixed 2 discrepancies between root and npm README files: (1) Cursor IDE config was .cursor/rules/ instead of .cursor/commands/ (verified against cursor.js installer), (2) OpenAI Codex location was incomplete - missing ~/.codex/prompts/ directory for user-level prompts. Both files now synchronized and identical."
+    fixed_issues:
+      - "packages/cli/README.md line 42: Updated Cursor from .cursor/rules/agileflow/ to .cursor/commands/agileflow/"
+      - "packages/cli/README.md line 44: Updated Codex from .codex/skills/ to .codex/skills/ and ~/.codex/prompts/"
+    verified:
+      - "Badge counts: 93 commands (correct), 45 agents (correct), dynamic skills (correct)"
+      - "All 11 referenced documentation files exist"
+      - "All 6 example commands/agents exist in source"
+      - "External links functional: npm (HTTP 200), GitHub (HTTP 200), docs site (HTTP 200)"
+      - "README files now identical (diff shows no differences)"
+    quality_gates:
+      - "Documentation current with v3.0.2 code ✓"
+      - "Counts verified against actual source files ✓"
+      - "IDE config verified against installers ✓"
+      - "All example commands/agents exist ✓"
+      - "No deprecated information remains ✓"
+      - "Two README files synchronized ✓"
+    source: "README.md, packages/cli/README.md, packages/cli/tools/cli/installers/ide/*.js"
+    notes: "Learned that IDE config locations can drift from documentation. Always verify against actual installer code (cursor.js, codex.js, etc.) not assumptions. OpenAI Codex has dual installation model (per-repo .codex/skills/ + user-level ~/.codex/prompts/) - this must be documented completely."

package/src/core/profiles/COMPARISON.md

@@ -0,0 +1,170 @@
+# IDE Capability Comparison Matrix
+
+Complete comparison of all supported IDEs. Profiles at `/packages/cli/src/core/profiles/`.
+
+## Core Capabilities
+
+| Capability | Claude Code | Cursor | Windsurf | Codex |
+|---|---|---|---|---|
+| **File Operations** | ✅ Native tools | ✅ read_file, edit_file | ✅ Native | ⚠️ Via skills |
+| **Shell Execution** | ✅ Bash tool | ✅ run_terminal_cmd | ✅ run_command | ⚠️ Via sandbox |
+| **File Search** | ✅ Glob, Grep | ✅ codebase_search, grep_search | ✅ search_files, search_codebase | ⚠️ Via sandbox |
+| **Interactive Input** | ✅ Structured (AskUserQuestion) | ⚠️ Conversational | ⚠️ Conversational | ⚠️ Text-only |
+| **Sub-Agents** | ✅ Task tool | ✅ Async native agents | ⚠️ Cascades + chaining | ❌ Cannot nest |
+| **Nested Sub-Agents** | ✅ Full nesting | ✅ Full nesting | ❌ Parallel only | ❌ None |
+
+## Planning & Execution
+
+| Capability | Claude Code | Cursor | Windsurf | Codex |
+|---|---|---|---|---|
+| **Plan Mode** | ✅ EnterPlanMode/ExitPlanMode | ✅ Native | ✅ Native + "megaplan" | ❌ None |
+| **Plan Editing** | ✅ User can edit | ✅ User can edit | ✅ User can edit | N/A |
+| **Persistent Plans** | ✅ Yes | ✅ Yes | ✅ ~/.windsurf/plans/ | N/A |
+
+## Lifecycle & Hooks
+
+| Hook Event | Claude Code | Cursor | Windsurf | Codex |
+|---|---|---|---|---|
+| **SessionStart** | ✅ | ❌ | ❌ | ❌ |
+| **PreToolUse** | ✅ | ❌ | ❌ | ❌ |
+| **PostToolUse** | ✅ | ❌ | ❌ | ❌ |
+| **beforeSubmitPrompt** | ❌ | ✅ | ❌ | ❌ |
+| **beforeShellExecution** | ❌ | ✅ | ❌ | ❌ |
+| **beforeMCPExecution** | ❌ | ✅ | ❌ | ❌ |
+| **beforeReadFile** | ❌ | ✅ | ❌ | ❌ |
+| **afterFileEdit** | ❌ | ✅ | ❌ | ❌ |
+| **pre_read_code** | ❌ | ❌ | ✅ | ❌ |
+| **post_read_code** | ❌ | ❌ | ✅ | ❌ |
+| **pre_write_code** | ❌ | ❌ | ✅ | ❌ |
+| **post_write_code** | ❌ | ❌ | ✅ | ❌ |
+| **pre_run_command** | ❌ | ❌ | ✅ | ❌ |
+| **post_run_command** | ❌ | ❌ | ✅ | ❌ |
+| **pre_mcp_tool_use** | ❌ | ❌ | ✅ | ❌ |
+| **post_mcp_tool_use** | ❌ | ❌ | ✅ | ❌ |
+| **pre_user_prompt** | ❌ | ❌ | ✅ | ❌ |
+| **post_cascade_response** | ❌ | ❌ | ✅ | ❌ |
+| **post_setup_worktree** | ❌ | ❌ | ✅ | ❌ |
+| **Total Hook Events** | 5 | 6 | 11 | 0 |
+
+**Status**: SessionStart, PreToolUse, PostToolUse (Claude Code); beforeSubmitPrompt, beforeShellExecution, beforeMCPExecution, beforeReadFile, afterFileEdit (Cursor); stop hook (all IDEs)
+
+## External Integration
+
+| Capability | Claude Code | Cursor | Windsurf | Codex |
+|---|---|---|---|---|
+| **Web Search** | ✅ WebSearch | ✅ web_search + @web | ✅ web_search | ❌ |
+| **Web Fetch** | ✅ WebFetch | ✅ @web + MCP | ✅ url_read, view_chunk | ❌ |
+| **MCP Support** | ✅ Full | ✅ Full | ✅ Full | ✅ Extension |
+| **MCP Tool Cap** | **0 (unlimited)** | **40** | **100** | **0 (unlimited)** |
+| **Browser** | ✅ Playwright MCP | ✅ Native browser (v2.0+) | ✅ Browser Preview | ⚠️ Limited |
+
+## Collaboration & Tracking
+
+| Capability | Claude Code | Cursor | Windsurf | Codex |
+|---|---|---|---|---|
+| **Task Tracking** | ✅ TaskCreate/Update/List | ❌ Plan checklists only | ❌ Conversation-embedded | ❌ None |
+| **Persistent Tasks** | ✅ Yes | ❌ | ❌ | ❌ |
+| **Git Worktrees** | ✅ EnterWorktree | ⚠️ Background agents use branches | ✅ Native (up to 20) | ⚠️ Manual |
+| **Parallel Execution** | ⚠️ Sequential Tasks | ✅ Async subagents | ✅ @cascade worktrees | ❌ |
+
+## Configuration Paths
+
+| Item | Claude Code | Cursor | Windsurf | Codex |
+|---|---|---|---|---|
+| **Config Dir** | `.claude/` | `.cursor/` | `.windsurf/` | `.codex/` |
+| **Commands** | `.claude/commands/agileflow/` | `.cursor/commands/` | `.windsurf/workflows/` | N/A |
+| **Agents** | `.claude/agents/agileflow/` | `.cursor/agents/` | N/A (use workflows) | N/A |
+| **Skills** | `.claude/skills/` | N/A (use agents) | `.windsurf/skills/*/` | `.codex/skills/agileflow-*/` |
+| **Rules** | N/A | `.cursor/rules/` (MDC) | `.windsurf/rules/` | N/A |
+| **Hooks Config** | `.claude/settings.json` | `.cursor/hooks.json` | `.windsurf/hooks.json` | N/A |
+| **MCP Config** | `.claude/settings.json` | `.cursor/mcp.json` | `~/.codeium/windsurf/mcp_config.json` | N/A |
+| **Instructions** | `CLAUDE.md` | `CURSOR.md` | `WINDSURF.md` | `AGENTS.md` |
+
+## Limits & Constraints
+
+| Constraint | Claude Code | Cursor | Windsurf | Codex |
+|---|---|---|---|---|
+| **Max File Size** | Unlimited | Unlimited | Unlimited | Unlimited |
+| **Max Command Length** | Unlimited | Unlimited | Unlimited | Unlimited |
+| **Workflow Size** | N/A | N/A | **12,000 chars** | N/A |
+| **MCP Tools** | 0 (unlimited) | **40** | 100 | 0 (unlimited) |
+| **Git Worktrees** | Via tool | Via branches | Up to 20 | Manual |
+| **Parallel Agents** | Sequential | Unlimited | Via @cascade | No nesting |
+
+**Key constraint**: Cursor's 40-tool MCP limit is the binding constraint for multi-IDE installations.
+
+## AgileFlow Feature Support
+
+| Feature | Claude Code | Cursor | Windsurf | Codex |
+|---|---|---|---|---|
+| **/agileflow:babysit** | ✅ Full | ⚠️ Conversational input | ⚠️ Conversational input | ❌ Limited |
+| **AskUserQuestion** | ✅ Structured menus | ❌ Fallback to text | ❌ Fallback to text | ✅ Text-only |
+| **Task delegation** | ✅ Task tool | ✅ Async agents | ⚠️ Workflow chaining | ❌ Skill suggestions |
+| **Plan mode hooks** | ✅ Full integration | ✅ Native mode | ✅ Native mode | ❌ None |
+| **Sub-agent nesting** | ✅ Full support | ✅ Full support | ⚠️ Parallel only | ❌ None |
+| **Persistent task list** | ✅ Yes | ❌ | ❌ | ❌ |
+| **Async execution** | ❌ Sequential | ✅ Native | ⚠️ @cascade | ❌ |
+
+## Implementation Notes
+
+### Claude Code
+- **Recommended target** for new AgileFlow features
+- All capabilities validated here first
+- Full support for structured user interaction
+- No tool limits for multi-IDE deployments
+
+### Cursor
+- **Fast-follower to Claude Code** (v2.5 Feb 2026)
+- Async native agents eliminate need for Task tool
+- 40-tool MCP cap is **binding constraint** for all IDEs
+- No AskUserQuestion - replace with numbered text prompts
+- Plan mode fully native (no enter/exit needed)
+
+### Windsurf
+- **Most hook events** (11 total) but most restrictive
+- **No true sub-agent spawning** - use workflow chaining or @cascade
+- **12,000 char limit per workflow** - must split large commands
+- **Global MCP config only** - no project-level customization
+- Native worktrees (up to 20)
+- Browser preview built-in to IDE
+
+### Codex
+- **Most restrictive** - use as minimum baseline
+- Skills cannot spawn other skills (no delegation)
+- No plan mode, hooks, or task tracking
+- Text-only user input
+- Best for linear workflows only
+
+## Multi-IDE Deployment Strategy
+
+**Canonical source**: Claude Code format
+**Generation**: Read IDE profile → Transform to IDE-native format
+**MCP constraint**: Cap at 40 tools (Cursor's limit) for consistency
+
+**Fallback order when feature unavailable**:
+1. Use native IDE equivalent (if exists)
+2. Replace with text-based alternative
+3. Document limitation in profile
+
+**Example - AskUserQuestion replacement**:
+```
+Claude Code:
+  AskUserQuestion(options=[{label: "Yes"}, {label: "No"}])
+
+Cursor/Windsurf:
+  Would you like to continue? (Type "Yes" or "No")
+
+Codex:
+  Please choose:
+  1. Yes
+  2. No
+```
+
+## Version Support
+
+- **Claude Code**: Latest (no version pinning)
+- **Cursor**: v2.5+ (Feb 2026)
+- **Windsurf**: Wave 13+ (native worktrees, 11 hooks)
+- **Codex**: Latest (limited feature set)
+
+Last updated: 2026-02-20 | Source: Cross-IDE Compatibility Findings

package/src/core/profiles/README.md

@@ -0,0 +1,178 @@
+# IDE Capability Profiles
+
+IDE-agnostic capability declarations for AgileFlow's multi-IDE support strategy.
+
+## Overview
+
+This directory contains one YAML profile per supported IDE. Each profile declares:
+- Supported capabilities (plan mode, hooks, task tracking, MCP, etc.)
+- Config directory structure and paths
+- Tool name mappings (how each IDE names equivalent functions)
+- Frontmatter formats for commands/agents
+- Limitations and workarounds
+
+## Design Philosophy
+
+**Capability profiles separate declarations from implementation.** Instead of baking IDE differences into generators, prompts, or installers, we declaratively describe what each IDE supports. This enables:
+
+1. **Build-time generation** - Generators read profiles and produce IDE-native output
+2. **Feature detection** - Commands can check IDE capabilities at install time
+3. **Graceful fallbacks** - Prompts suggest alternatives when features unavailable
+4. **Extensibility** - Adding new IDEs requires only a new YAML file, not code changes
+
+## Files
+
+### claude-code.yaml
+**Primary target.** Anthropic's CLI-based environment with full support for:
+- Structured interactive input (AskUserQuestion)
+- True sub-agent spawning with nesting (Task tool)
+- Plan mode with programmatic control
+- Persistent task tracking (TaskCreate/Update)
+- Comprehensive hooks (SessionStart, PreToolUse, PostToolUse)
+- Unlimited MCP tools
+
+**Key paths:**
+- Commands: `.claude/commands/agileflow/`
+- Agents: `.claude/agents/agileflow/`
+- Instructions: `CLAUDE.md`
+
+### cursor.yaml
+**Closest competitor to Claude Code.** v2.5 (Feb 2026) now supports:
+- Async subagents with nesting (no Task tool needed)
+- Plan mode with native interface
+- 6 lifecycle hooks (beta)
+- 40-tool MCP limit (binding constraint)
+- Native browser tool
+
+**Gaps:**
+- No structured menus (conversational only)
+- No persistent task tracking
+- No background sub-agent execution
+
+**Key paths:**
+- Commands: `.cursor/commands/`
+- Agents: `.cursor/agents/`
+- Rules: `.cursor/rules/` (MDC format)
+- MCP config: `.cursor/mcp.json`
+
+### windsurf.yaml
+**Most comprehensive hooks (11 events).** Wave 13+ with:
+- Native worktrees (up to 20 per workspace)
+- 11 lifecycle hook events
+- 100-tool MCP limit
+- Native browser preview (in-IDE)
+
+**Gaps:**
+- No true sub-agent spawning (use workflow chaining or cascades)
+- 12,000 character limit per workflow file
+- Global-only MCP config (`~/.codeium/windsurf/mcp_config.json`)
+- No persistent task tracking
+- Conversational input only
+
+**Key paths:**
+- Workflows: `.windsurf/workflows/`
+- Skills: `.windsurf/skills/*/SKILL.md` (agentskills.io spec)
+- Rules: `.windsurf/rules/`
+- MCP config: `~/.codeium/windsurf/mcp_config.json` (global-only)
+
+### codex.yaml
+**Most restrictive.** OpenAI's CLI with:
+- Skills (no direct file tools)
+- Sandbox modes (read-only, auto, full-access)
+- Text-only user input (no structured menus)
+
+**Gaps:**
+- No plan mode
+- No hooks
+- No sub-agent delegation
+- No task tracking
+- No MCP
+
+## Usage
+
+### For Installers
+```javascript
+const profile = require('./profiles/claude-code.yaml');
+if (profile.capabilities.core.planMode) {
+  installPlanModePrompts();
+}
+```
+
+### For Generators
+```javascript
+// Read profile to generate IDE-native commands
+const generator = new CommandGenerator(profile);
+const ideSpecificMarkdown = generator.transform(canonicalCommand);
+```
+
+### For Feature Detection
+```javascript
+// Check if IDE supports a feature
+if (!profile.capabilities.collaboration.taskTracking) {
+  console.warn('Task tracking not available in this IDE');
+  suggestFileBasedAlternative();
+}
+```
+
+## Capability Categories
+
+### Core Capabilities
+- **fileOperations** - Read, write, edit files
+- **shell** - Execute shell commands
+- **fileSearch** - Glob and grep
+- **interactiveInput** - Structured user menus (structured vs conversational)
+- **subAgents** - Spawn sub-agents/skills
+- **nestedSubAgents** - Sub-agents can spawn other sub-agents
+
+### Planning
+- **planMode** - Explicit planning phase
+- **planModeEditable** - Plans can be edited during execution
+
+### Lifecycle
+- **hooks** - Pre/post execution hooks
+- **hookEvents** - List of specific hook events supported
+
+### External Integration
+- **webSearch** - Internet search capability
+- **webFetch** - Fetch URLs
+- **mcp** - Model Context Protocol support
+- **mcpToolLimit** - Max tools per MCP (0 = unlimited)
+- **browser** - Screenshot/browser automation
+
+### Collaboration
+- **taskTracking** - Persistent task tracking
+- **persistentTasks** - Tasks survive across sessions
+- **worktrees** - Git worktree support
+
+## MCP Tool Limits
+
+| IDE | Tool Cap | Notes |
+|---|---|---|
+| Claude Code | Unlimited (0) | Can install entire ecosystem |
+| Cursor | 40 | Hard limit; binding constraint for multi-IDE |
+| Windsurf | 100 | Good balance |
+| Codex | Unlimited (0) | Via MCP extension |
+
+**Design decision**: Cap multi-IDE MCP installations at 40 tools (Cursor's limit) to ensure compatibility across all platforms.
+
+## Implementation Priority
+
+| Tier | Capabilities | IDEs | Status |
+|---|---|---|---|
+| 1 | File ops, shell, search, web | All | Ready |
+| 2 | Hooks, plan mode | Claude Code, Cursor, Windsurf | Profiles complete |
+| 3 | Sub-agents, task tracking | Claude Code, Cursor | Profiles complete |
+| 4 | Worktrees, MCP | All | Profiles complete |
+
+## Next Steps
+
+1. **Validators** - Build validators to check profile format/completeness
+2. **Loaders** - Create load functions (YAML → JS objects) with caching
+3. **Generators** - Build content transformers that read profiles and output IDE-native prompts
+4. **Tests** - Snapshot tests per IDE profile
+5. **Documentation** - ADR-0011 documenting the capability profile strategy
+
+## References
+
+- Cross-IDE Compatibility Findings: `docs/10-research/20260220-ide-cross-compatibility-findings.md`
+- ADR-0011 (TBD): Capability Profile Strategy

package/src/core/profiles/claude-code.yaml

@@ -0,0 +1,111 @@
+# Claude Code IDE Capability Profile
+# Anthropic CLI - Primary target, fully supported
+# Reference: Cross-IDE Compatibility Findings (20260220)
+
+ide:
+  id: claude-code
+  name: Claude Code
+  displayName: Claude Code
+  description: Anthropic's native CLI-based development environment
+  configDir: .claude
+  instructionsFile: CLAUDE.md
+  fileFormat: markdown
+  commandPrefix: "/agileflow:"
+  agentPrefix: "agileflow-"
+
+paths:
+  commands: .claude/commands/agileflow/
+  agents: .claude/agents/agileflow/
+  skills: .claude/skills/
+  hooks: .claude/settings.json
+  mcp: .claude/settings.json
+
+capabilities:
+  core:
+    fileOperations: true      # Read, Write, Edit tools
+    shell: true               # Bash tool with full execution
+    fileSearch: true          # Glob and Grep tools
+    interactiveInput: true    # AskUserQuestion with structured options
+    subAgents: true           # Task tool for spawning subagents
+    nestedSubAgents: true     # Sub-agents can spawn sub-sub-agents
+  planning:
+    planMode: true            # EnterPlanMode/ExitPlanMode
+    planModeEditable: true    # User can edit plans mid-execution
+  lifecycle:
+    hooks: true               # PreToolUse, PostToolUse, SessionStart
+    hookEvents:
+      - SessionStart
+      - PreToolUse
+      - PostToolUse
+      - Notification
+      - Stop
+  external:
+    webSearch: true           # WebSearch tool
+    webFetch: true            # WebFetch tool
+    mcp: true                 # Model Context Protocol
+    mcpToolLimit: 0           # 0 = unlimited
+    browser: true             # Playwright MCP for screenshots
+  collaboration:
+    taskTracking: true        # TaskCreate, TaskUpdate, TaskList
+    persistentTasks: true     # Tasks survive across sessions
+    worktrees: true           # EnterWorktree for parallel branches
+
+toolNames:
+  # Interactive
+  askUser: AskUserQuestion
+  # Delegation
+  spawnAgent: Task
+  createTask: TaskCreate
+  updateTask: TaskUpdate
+  listTasks: TaskList
+  # Planning
+  planModeEnter: EnterPlanMode
+  planModeExit: ExitPlanMode
+  # Execution
+  bash: Bash
+  # Files
+  read: Read
+  write: Write
+  edit: Edit
+  # Search
+  glob: Glob
+  grep: Grep
+  # Web
+  webSearch: WebSearch
+  webFetch: WebFetch
+  # Branching
+  worktree: EnterWorktree
+
+frontmatter:
+  agents:
+    format: yaml
+    fields:
+      - name
+      - description
+      - tools
+      - model
+  commands:
+    format: yaml
+    fields:
+      - description
+      - argument-hint
+
+limits:
+  maxFileSize: 0              # 0 = unlimited
+  maxCommandLength: 0         # 0 = unlimited
+  maxToolsPerMCP: 0           # 0 = unlimited
+
+installation:
+  supportsFileOps: true
+  supportsHooks: true
+  supportsMCP: true
+  commandsRequireApproval: false
+  agentFilesCanBeNestedDirs: true
+
+notes:
+  - "Primary target for AgileFlow development"
+  - "All new capabilities are validated against Claude Code first"
+  - "AskUserQuestion provides structured menu presentation with JSON options"
+  - "Task tool supports full async delegation with result callbacks"
+  - "Plan mode integrated via native EnterPlanMode/ExitPlanMode"
+  - "No tool count limits - can install entire MCP ecosystem"

package/src/core/profiles/codex.yaml

@@ -0,0 +1,103 @@
+# OpenAI Codex CLI Capability Profile
+# Reference: Cross-IDE Compatibility Findings (20260220)
+
+ide:
+  id: codex
+  name: OpenAI Codex CLI
+  displayName: Codex
+  description: OpenAI's CLI-based development assistant
+  configDir: .codex
+  configDirUser: ~/.codex
+  instructionsFile: AGENTS.md
+  fileFormat: markdown
+  commandPrefix: "$agileflow-"
+  agentPrefix: "agileflow-"
+
+paths:
+  commands: null              # Not directly supported
+  agents: null                # Not directly supported
+  skills: .codex/skills/agileflow-*/SKILL.md
+  skillsUser: ~/.codex/prompts/agileflow-*.md
+  hooks: null                 # Not supported
+  mcp: null                   # Not supported
+
+capabilities:
+  core:
+    fileOperations: true      # Via skills (no direct tools)
+    shell: true               # Via sandbox
+    fileSearch: true          # Via sandbox search
+    interactiveInput: true    # ask_user_question (text-only, no structured menus)
+    subAgents: false          # Experimental multi-agent support (disabled by default)
+    nestedSubAgents: false    # No nested delegation; experimental agents are flat
+  planning:
+    planMode: true            # On by default since v0.96
+    planModeEditable: true    # Plans are editable
+  lifecycle:
+    hooks: false              # No lifecycle hooks
+    approvalPolicies: true    # Approval gates only
+  external:
+    webSearch: false          # Not built-in
+    webFetch: false           # Not built-in
+    mcp: true                 # Via MCP extension
+    mcpToolLimit: 0           # 0 = unlimited
+    browser: false            # Not available
+  collaboration:
+    taskTracking: false       # No task tracking
+    persistentTasks: false
+    worktrees: false          # Manual git operations
+
+sandboxModes:
+  - id: read-only
+    description: "No file modifications, workspace read access"
+  - id: auto
+    description: "Auto-approved operations within workspace"
+  - id: full-access
+    description: "Full system access with approval"
+
+toolNames:
+  # Interactive
+  askUser: ask_user_question  # Text-only, not structured
+  # File operations (via skill)
+  read: null                  # Use skill instead
+  write: null                 # Use skill instead
+  edit: null                  # Use skill instead
+  # Execution (via skill)
+  bash: null                  # Use sandbox instead
+  # Search (via skill)
+  glob: null                  # Use sandbox instead
+  grep: null                  # Use sandbox instead
+  # Web (not available)
+  webSearch: null
+  webFetch: null
+
+frontmatter:
+  skills:
+    format: yaml
+    fields:
+      - name
+      - description
+      - model
+      - requiredPermissions
+
+limitations:
+  noSubAgents: "Cannot spawn other skills; use numbered prompts for sequential work"
+  noInteractiveMenus: "ask_user_question is text-only; convert to numbered options"
+  noPlanning: "No plan mode; use sequential skill instructions instead"
+  noHooks: "No lifecycle hooks; use approval policies"
+  noTaskTracking: "No persistent task tracking; use external tools"
+  skillScope: "Skills are repository-scoped, user prompts are global"
+
+installation:
+  supportsFileOps: false      # Via skills, not native tools
+  supportsHooks: false
+  supportsMCP: true           # Via MCP extension
+  commandsRequireApproval: true
+  skillsCanBeNestedDirs: false
+
+notes:
+  - "Skills are the primary extension mechanism"
+  - "Per-repo skills in .codex/skills/, global prompts in ~/.codex/prompts/"
+  - "Plan mode available (on by default since v0.96); no hooks or true sub-agent delegation"
+  - "AgileFlow /babysit features must fallback to conversational prompts"
+  - "Best used for simple linear workflows"
+  - "ask_user_question produces text output, not structured menus"