@howlil/ez-agents 3.5.0 → 4.0.0

package/commands/ez/add-todo.md

@@ -1,47 +0,0 @@
----
-name: ez:add-todo
-description: Capture idea or task as todo from current conversation context
-argument-hint: [optional description]
-allowed-tools:
-  - Read
-  - Write
-  - Bash
-  - AskUserQuestion
----
-
-<objective>
-Capture an idea, task, or issue that surfaces during an EZ Agents session as a structured todo for later work.
-
-Routes to the add-todo workflow which handles:
-- Directory structure creation
-- Content extraction from arguments or conversation
-- Area inference from file paths
-- Duplicate detection and resolution
-- Todo file creation with frontmatter
-- STATE.md updates
-- Git commits
-</objective>
-
-<execution_context>
-@~/.claude/ez-agents/workflows/add-todo.md
-</execution_context>
-
-<context>
-Arguments: $ARGUMENTS (optional todo description)
-
-State is resolved in-workflow via `init todos` and targeted reads.
-</context>
-
-<process>
-**Follow the add-todo workflow** from `@~/.claude/ez-agents/workflows/add-todo.md`.
-
-The workflow handles all logic including:
-1. Directory ensuring
-2. Existing area checking
-3. Content extraction (arguments or conversation)
-4. Area inference
-5. Duplicate checking
-6. File creation with slug generation
-7. STATE.md updates
-8. Git commits
-</process>

package/commands/ez/arch-review.md

@@ -1,102 +0,0 @@
----
-name: ez:arch-review
-description: Run a Tech Lead architecture review on phase plans. Flags drift from established patterns, technical debt, and design conflicts.
-argument-hint: "<phase>"
-allowed-tools:
-  - Read
-  - Bash
-  - Glob
-  - Grep
-  - Task
----
-
-<execution_context>
-@~/.claude/ez-agents/workflows/arch-review.md
-</execution_context>
-
-<process>
-Execute the arch-review workflow from @~/.claude/ez-agents/workflows/arch-review.md end-to-end.
-Parse ARGUMENTS for phase number before executing.
-</process>
-
-# /ez:arch-review
-
-Run a Tech Lead architecture review on phase plans. The Tech Lead agent checks plans against established codebase patterns, prior design decisions, and security requirements.
-
-## Usage
-
-```
-/ez:arch-review <phase>
-```
-
-## Arguments
-
-| Argument | Required | Description |
-|----------|----------|-------------|
-| `phase` | Yes | Phase number to review (e.g., `5`, `5.1`) |
-
-## What Gets Reviewed
-
-1. **Pattern Consistency** — Plans follow established codebase conventions
-2. **Technical Debt Risk** — Plans avoid shortcuts that cost more later
-3. **Cross-Phase Design Conflicts** — Plans don't contradict prior decisions
-4. **Security Architecture** — Auth, input validation, sensitive data handled correctly
-5. **Scalability Concerns** — No N+1 queries, unbounded operations
-6. **Dependency Analysis** — New packages are appropriate and vetted
-
-## Output
-
-```
-## Tech Lead Review: Phase 5 — Authentication
-
-Technical Risk: LOW
-Blockers: 0 | Warnings: 1 | Advisory: 2
-
-### Findings
-
-⚠️ WARNING — Security Architecture
-Plan 5-02 adds POST /api/users endpoint without auth middleware.
-Recommendation: Add requireAuth() middleware to protect this route.
-
-💡 ADVISORY — Pattern Consistency
-Plan 5-01 introduces bcrypt for password hashing. Existing codebase uses
-argon2 in Phase 3. Consider using argon2 for consistency.
-(Both are secure — this is style, not a blocker)
-
-### Overall: APPROVE_WITH_WARNINGS
-Plans are architecturally sound. Address the auth middleware warning before executing.
-```
-
-## Severity Levels
-
-| Level | Meaning | Effect |
-|-------|---------|--------|
-| BLOCKER | Irreversible change or security hole | Must fix before execution |
-| WARNING | Technical debt or missing validation | Highlight and suggest fix |
-| ADVISORY | Alternative worth considering | Informational only |
-
-## Integration with Planning
-
-Arch review fits between planning and execution:
-
-```
-/ez:plan-phase 5      → Plans created
-/ez:arch-review 5     → Tech lead reviews plans
-/ez:execute-phase 5   → Execute with awareness of any warnings
-```
-
-The `execute-phase` workflow automatically spawns a tech lead review when `workflow.agent_discussion` is enabled in config.
-
-## When to Use
-
-- After planning a phase with significant new architecture
-- When introducing new dependencies
-- When modifying auth, payments, or other sensitive systems
-- Before a major milestone
-
-## Related Commands
-
-- `/ez:standup` — Sprint health standup
-- `/ez:plan-phase` — Create phase plans
-- `/ez:execute-phase` — Execute with pre-flight checks
-- `/ez:release` — Release validation

package/commands/ez/auth.md

@@ -1,87 +0,0 @@
----
-name: ez:auth
-description: Manage API credentials securely (save, list, delete)
-argument-hint: "<save|list|delete|test> [provider] [secret]"
-agent: ez-helper
-allowed-tools:
-  - Read
-  - Bash
----
-<objective>
-Manage API credentials securely using system keychain or fallback file storage
-
-**Subcommands:**
-- `ez:auth save <provider> <secret>` — Save credential for provider
-- `ez:auth list` — List all stored providers
-- `ez:auth delete <provider>` — Delete credential for provider
-- `ez:auth test` — Test credential system and show keychain status
-
-**Providers:** anthropic, moonshot, alibaba, qwen, openai
-</objective>
-
-<execution_context>
-@~/.claude/ez-agents/workflows/ez-helper.md
-</execution_context>
-
-<context>
-@.planning/PROJECT.md
-@.planning/STATE.md
-
-# Credential storage module:
-@ez-agents/bin/lib/auth.cjs
-
-# EZ tools CLI:
-@ez-agents/bin/ez-tools.cjs
-</context>
-
-<process>
-## Subcommand Routing
-
-1. **Parse arguments** — First arg is subcommand (save/list/delete/test), remaining are parameters
-2. **Route to handler** — Call appropriate auth function from ez-tools.cjs
-3. **Output result** — Show success/failure with user-friendly messages
-
-## Handlers
-
-### save <provider> <secret>
-1. Validate provider name against known providers
-2. Call saveCredential(provider, secret)
-3. Output: "✓ Credential saved for {provider}" or error message
-
-### list
-1. Call listProviders()
-2. Check isKeychainAvailable()
-3. Output table:
-   ```
-   Provider       Storage
-   ─────────────────────────
-   anthropic      Keychain ✓
-   qwen           File (fallback)
-   ```
-4. If using file storage, show warning: "⚠ Using file storage — consider installing keytar for better security"
-
-### delete <provider>
-1. Validate provider exists
-2. Confirm deletion (ask user or require --force)
-3. Call deleteCredential(provider)
-4. Output: "✓ Credential deleted for {provider}"
-
-### test
-1. Check isKeychainAvailable()
-2. Output:
-   ```
-   Credential System Test
-   
-   Keychain (keytar): {Available | Unavailable}
-   Storage mode: {System keychain | Fallback file}
-   
-   Stored providers: {count}
-   ```
-3. If keytar unavailable, show install hint: "npm install keytar"
-
-## Error Handling
-
-- **Invalid provider:** "Unknown provider '{name}'. Valid: anthropic, moonshot, alibaba, qwen, openai"
-- **Credential not found:** "No credential found for {provider}. Use 'save' to add one."
-- **Keychain error:** "Failed to access keychain: {error}. Using fallback storage."
-</process>

package/commands/ez/autonomous.md

@@ -1,41 +0,0 @@
----
-name: ez:autonomous
-description: Run all remaining phases autonomously — discuss→plan→execute per phase
-argument-hint: "[--from N]"
-allowed-tools:
-  - Read
-  - Write
-  - Bash
-  - Glob
-  - Grep
-  - AskUserQuestion
-  - Task
----
-<objective>
-Execute all remaining milestone phases autonomously. For each phase: discuss → plan → execute. Pauses only for user decisions (grey area acceptance, blockers, validation requests).
-
-Uses ROADMAP.md phase discovery and Skill() flat invocations for each phase command. After all phases complete: milestone audit → complete → cleanup.
-
-**Creates/Updates:**
-- `.planning/STATE.md` — updated after each phase
-- `.planning/ROADMAP.md` — progress updated after each phase
-- Phase artifacts — CONTEXT.md, PLANs, SUMMARYs per phase
-
-**After:** Milestone is complete and cleaned up.
-</objective>
-
-<execution_context>
-@~/.claude/ez-agents/workflows/autonomous.md
-@~/.claude/ez-agents/references/ui-brand.md
-</execution_context>
-
-<context>
-Optional flag: `--from N` — start from phase N instead of the first incomplete phase.
-
-Project context, phase list, and state are resolved inside the workflow using init commands (`ez-tools.cjs init milestone-op`, `ez-tools.cjs roadmap analyze`). No upfront context loading needed.
-</context>
-
-<process>
-Execute the autonomous workflow from @~/.claude/ez-agents/workflows/autonomous.md end-to-end.
-Preserve all workflow gates (phase discovery, per-phase execution, blocker handling, progress display).
-</process>

package/commands/ez/check-todos.md

@@ -1,45 +0,0 @@
----
-name: ez:check-todos
-description: List pending todos and select one to work on
-argument-hint: [area filter]
-allowed-tools:
-  - Read
-  - Write
-  - Bash
-  - AskUserQuestion
----
-
-<objective>
-List all pending todos, allow selection, load full context for the selected todo, and route to appropriate action.
-
-Routes to the check-todos workflow which handles:
-- Todo counting and listing with area filtering
-- Interactive selection with full context loading
-- Roadmap correlation checking
-- Action routing (work now, add to phase, brainstorm, create phase)
-- STATE.md updates and git commits
-</objective>
-
-<execution_context>
-@~/.claude/ez-agents/workflows/check-todos.md
-</execution_context>
-
-<context>
-Arguments: $ARGUMENTS (optional area filter)
-
-Todo state and roadmap correlation are loaded in-workflow using `init todos` and targeted reads.
-</context>
-
-<process>
-**Follow the check-todos workflow** from `@~/.claude/ez-agents/workflows/check-todos.md`.
-
-The workflow handles all logic including:
-1. Todo existence checking
-2. Area filtering
-3. Interactive listing and selection
-4. Full context loading with file summaries
-5. Roadmap correlation checking
-6. Action offering and execution
-7. STATE.md updates
-8. Git commits
-</process>

package/commands/ez/cleanup.md

@@ -1,18 +0,0 @@
----
-name: ez:cleanup
-description: Archive accumulated phase directories from completed milestones
----
-<objective>
-Archive phase directories from completed milestones into `.planning/milestones/v{X.Y}-phases/`.
-
-Use when `.planning/phases/` has accumulated directories from past milestones.
-</objective>
-
-<execution_context>
-@~/.claude/ez-agents/workflows/cleanup.md
-</execution_context>
-
-<process>
-Follow the cleanup workflow at @~/.claude/ez-agents/workflows/cleanup.md.
-Identify completed milestones, show a dry-run summary, and archive on confirmation.
-</process>

package/commands/ez/debug.md

@@ -1,168 +0,0 @@
----
-name: ez:debug
-description: Systematic debugging with persistent state across context resets
-argument-hint: [issue description]
-allowed-tools:
-  - Read
-  - Bash
-  - Task
-  - AskUserQuestion
----
-
-<objective>
-Debug issues using scientific method with subagent isolation.
-
-**Orchestrator role:** Gather symptoms, spawn ez-debugger agent, handle checkpoints, spawn continuations.
-
-**Why subagent:** Investigation burns context fast (reading files, forming hypotheses, testing). Fresh 200k context per investigation. Main context stays lean for user interaction.
-</objective>
-
-<context>
-User's issue: $ARGUMENTS
-
-Check for active sessions:
-```bash
-ls .planning/debug/*.md 2>/dev/null | grep -v resolved | head -5
-```
-</context>
-
-<process>
-
-## 0. Initialize Context
-
-```bash
-INIT=$(node "$HOME/.claude/ez-agents/bin/ez-tools.cjs" state load)
-if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
-```
-
-Extract `commit_docs` from init JSON. Resolve debugger model:
-```bash
-debugger_model=$(node "$HOME/.claude/ez-agents/bin/ez-tools.cjs" resolve-model ez-debugger --raw)
-```
-
-## 1. Check Active Sessions
-
-If active sessions exist AND no $ARGUMENTS:
-- List sessions with status, hypothesis, next action
-- User picks number to resume OR describes new issue
-
-If $ARGUMENTS provided OR user describes new issue:
-- Continue to symptom gathering
-
-## 2. Gather Symptoms (if new issue)
-
-Use AskUserQuestion for each:
-
-1. **Expected behavior** - What should happen?
-2. **Actual behavior** - What happens instead?
-3. **Error messages** - Any errors? (paste or describe)
-4. **Timeline** - When did this start? Ever worked?
-5. **Reproduction** - How do you trigger it?
-
-After all gathered, confirm ready to investigate.
-
-## 3. Spawn ez-debugger Agent
-
-Fill prompt and spawn:
-
-```markdown
-<objective>
-Investigate issue: {slug}
-
-**Summary:** {trigger}
-</objective>
-
-<symptoms>
-expected: {expected}
-actual: {actual}
-errors: {errors}
-reproduction: {reproduction}
-timeline: {timeline}
-</symptoms>
-
-<mode>
-symptoms_prefilled: true
-goal: find_and_fix
-</mode>
-
-<debug_file>
-Create: .planning/debug/{slug}.md
-</debug_file>
-```
-
-```
-Task(
-  prompt=filled_prompt,
-  subagent_type="ez-debugger",
-  model="{debugger_model}",
-  description="Debug {slug}"
-)
-```
-
-## 4. Handle Agent Return
-
-**If `## ROOT CAUSE FOUND`:**
-- Display root cause and evidence summary
-- Offer options:
-  - "Fix now" - spawn fix subagent
-  - "Plan fix" - suggest /ez:plan-phase --gaps
-  - "Manual fix" - done
-
-**If `## CHECKPOINT REACHED`:**
-- Present checkpoint details to user
-- Get user response
-- If checkpoint type is `human-verify`:
-  - If user confirms fixed: continue so agent can finalize/resolve/archive
-  - If user reports issues: continue so agent returns to investigation/fixing
-- Spawn continuation agent (see step 5)
-
-**If `## INVESTIGATION INCONCLUSIVE`:**
-- Show what was checked and eliminated
-- Offer options:
-  - "Continue investigating" - spawn new agent with additional context
-  - "Manual investigation" - done
-  - "Add more context" - gather more symptoms, spawn again
-
-## 5. Spawn Continuation Agent (After Checkpoint)
-
-When user responds to checkpoint, spawn fresh agent:
-
-```markdown
-<objective>
-Continue debugging {slug}. Evidence is in the debug file.
-</objective>
-
-<prior_state>
-<files_to_read>
-- .planning/debug/{slug}.md (Debug session state)
-</files_to_read>
-</prior_state>
-
-<checkpoint_response>
-**Type:** {checkpoint_type}
-**Response:** {user_response}
-</checkpoint_response>
-
-<mode>
-goal: find_and_fix
-</mode>
-```
-
-```
-Task(
-  prompt=continuation_prompt,
-  subagent_type="ez-debugger",
-  model="{debugger_model}",
-  description="Continue debug {slug}"
-)
-```
-
-</process>
-
-<success_criteria>
-- [ ] Active sessions checked
-- [ ] Symptoms gathered (if new)
-- [ ] ez-debugger spawned with context
-- [ ] Checkpoints handled correctly
-- [ ] Root cause confirmed before fixing
-</success_criteria>

package/commands/ez/export-session.md

@@ -1,79 +0,0 @@
----
-name: ez:export-session
-description: Export session for model handoff
-argument-hint: "[session_id] [--format markdown|json] [--output path]"
-allowed-tools:
-  - Read
-  - Write
-  - Bash
----
-
-<objective>
-Export a session summary for handoff to a different model or for archival.
-
-This command:
-- Accepts optional session ID (default: last session)
-- Supports markdown and JSON export formats
-- Writes output to specified path or default location
-- Shows confirmation message with export details
-- Enables seamless model transitions (Claude ↔ Qwen ↔ OpenAI ↔ Kimi)
-</objective>
-
-<execution_context>
-@~/.claude/ez-agents/workflows/export-session.md
-</execution_context>
-
-<context>
-$ARGUMENTS
-
-Parameters:
-- session_id: Optional. Session ID to export (default: last session)
-- --format: Optional. Export format: 'markdown' or 'json' (default: markdown)
-- --output: Optional. Output file path (default: .planning/sessions/export-{session_id}.{ext})
-</context>
-
-<process>
-**Follow the export-session workflow** from @~/.claude/ez-agents/workflows/export-session.md.
-
-The workflow handles all export logic including:
-
-1. **Parse parameters:**
-   - Extract session_id from args (or use "last")
-   - Extract --format flag (default: 'markdown')
-   - Extract --output flag (default: auto-generated)
-
-2. **Resolve session ID:**
-   - If session_id === 'last':
-     - Call SessionManager.getLastSession()
-     - Use session.metadata.session_id
-   - Else: use provided session_id
-
-3. **Validate format:**
-   - Must be 'markdown' or 'json'
-   - If invalid: error "Format must be 'markdown' or 'json'"
-
-4. **Generate output path if not specified:**
-   - For markdown: `.planning/sessions/export-{session_id}.md`
-   - For JSON: `.planning/sessions/export-{session_id}.json`
-
-5. **Export session:**
-   - Create SessionExport instance with SessionManager
-   - Call exportToFile(sessionId, format, outputPath)
-   - Catch SessionExportError and display user-friendly message
-
-6. **Show confirmation:**
-   ```
-   Session exported successfully!
-
-   Session: {session_id}
-   Format: {format}
-   Output: {outputPath}
-
-   You can now share this file with another model or import it later.
-   ```
-
-7. **Offer follow-up actions:**
-   - "Open file?"
-   - "Export another session?"
-   - "Return to work?"
-</process>