@howlil/ez-agents 3.5.0 → 4.0.0

package/commands/ez/release.md

@@ -1,153 +0,0 @@
----
-name: ez:release
-description: Create a tier-aware release with branch automation, changelog generation, security gates, and rollback plan.
-usage: /ez:release <tier> <version>
-argument-hint: "<tier> <version> | preflight <tier>"
-allowed-tools:
-  - Read
-  - Write
-  - Edit
-  - Bash
-  - Glob
-  - Grep
-  - Task
----
-
-<execution_context>
-@~/.claude/ez-agents/workflows/release.md
-</execution_context>
-
-<process>
-Execute the release workflow from @~/.claude/ez-agents/workflows/release.md end-to-end.
-Parse ARGUMENTS for tier, version, and flags before executing.
-</process>
-
-# /ez:release
-
-Create a production release. Automates branch strategy, security gates, tier checklist, changelog generation, and rollback plan based on the target tier (mvp/medium/enterprise).
-
-## Usage
-
-```
-/ez:release <tier> <version>
-/ez:release preflight <tier>
-```
-
-## Arguments
-
-| Argument | Required | Description |
-|----------|----------|-------------|
-| `tier` | Yes | `mvp`, `medium`, or `enterprise` |
-| `version` | Yes | Semver version (e.g., `1.0.0`, `2.1.0`) |
-
-## Release Tiers
-
-### MVP (`/ez:release mvp v1.0.0`)
-For: "Ship working software fast"
-- Scope: @must scenarios only
-- Coverage: 60% minimum
-- Git: Trunk-based (tag directly on main)
-- Checklist: 6 items
-- Typical use: First public release, early access
-
-### Medium (`/ez:release medium v1.1.0`)
-For: "Production-ready for real users"
-- Scope: @must + @should scenarios
-- Coverage: 80% minimum
-- Git: GitHub Flow (release branch → PR → main)
-- Checklist: 18 items
-- Typical use: General availability, paying customers
-
-### Enterprise (`/ez:release enterprise v2.0.0`)
-For: "Compliance-grade production"
-- Scope: All MoSCoW priorities
-- Coverage: 95% minimum
-- Git: GitFlow (release/vX.Y.Z → develop → main)
-- Checklist: 30 items
-- Typical use: Enterprise customers, regulated industries
-
-## Auto-Invocation (Smart Orchestration)
-
-Based on tier, this command automatically runs pre-flight checks before the release:
-
-| Tier | Auto Pre-flight |
-|------|----------------|
-| `mvp` | None — proceed directly to release checklist |
-| `medium` | `[auto]` verify-work (if no existing VERIFICATION.md) |
-| `enterprise` | `[auto]` verify-work → `[auto]` audit-milestone → `[auto]` arch-review |
-
-All auto-invocations appear with `[auto]` prefix in output.
-
-Override with `--no-auto` to skip all pre-invocations.
-
-## Flags
-
-| Flag | Effect |
-|------|--------|
-| `--no-auto` | Skip all auto pre-flight invocations |
-
-## What It Does
-
-1. **Smart pre-flight** (auto, tier-based — see above)
-2. **Validates** state (clean working tree, tests passing, coverage meets tier threshold)
-3. **Runs security gates** (no secrets, no critical vulns, no production TODOs)
-4. **Evaluates tier checklist** (6/18/30 items based on tier)
-5. **Creates release branch** (per tier git strategy)
-6. **Generates changelog** (from commits since last tag)
-7. **Bumps version** in package.json
-8. **Creates rollback plan** in `.planning/releases/`
-9. **Tags the release** with `v{version}`
-10. **Reports Production Readiness Score** (0-100)
-
-## Output Example
-
-```
-## Release: v1.0.0 (mvp tier)
-
-Security Gates: 4/4 passed
-Checklist: 6/6 items passed
-Production Readiness Score: 96/100
-
-Branch: main (trunk-based)
-Tag: v1.0.0
-Changelog: Updated
-Rollback Plan: .planning/releases/v1.0.0-ROLLBACK-PLAN.md
-
-✓ Ready to push:
-  git push origin main && git push origin v1.0.0
-```
-
-## Tier Promotion
-
-Promote tier when ready for more users:
-
-```bash
-# Start MVP
-/ez:release mvp v1.0.0
-
-# 3 months later, enough users for proper testing
-/ez:release medium v1.5.0
-
-# Enterprise deal signed
-/ez:release enterprise v2.0.0
-```
-
-Each promotion checks that previous tier requirements are still satisfied.
-
-## Preflight Check
-
-Run checklist without creating release:
-
-```bash
-/ez:release preflight mvp
-/ez:release preflight enterprise
-```
-
-Shows which items pass/fail without creating branch or tag.
-
-## Related Commands
-
-- `/ez:hotfix` — Emergency fix on released version
-- `/ez:standup` — Check sprint health before release
-- `/ez:arch-review` — Architecture review before release
-- `/ez:verify-work` — Manual verification before release

package/commands/ez/remove-phase.md

@@ -1,31 +0,0 @@
----
-name: ez:remove-phase
-description: Remove a future phase from roadmap and renumber subsequent phases
-argument-hint: <phase-number>
-allowed-tools:
-  - Read
-  - Write
-  - Bash
-  - Glob
----
-<objective>
-Remove an unstarted future phase from the roadmap and renumber all subsequent phases to maintain a clean, linear sequence.
-
-Purpose: Clean removal of work you've decided not to do, without polluting context with cancelled/deferred markers.
-Output: Phase deleted, all subsequent phases renumbered, git commit as historical record.
-</objective>
-
-<execution_context>
-@~/.claude/ez-agents/workflows/remove-phase.md
-</execution_context>
-
-<context>
-Phase: $ARGUMENTS
-
-Roadmap and state are resolved in-workflow via `init phase-op` and targeted reads.
-</context>
-
-<process>
-Execute the remove-phase workflow from @~/.claude/ez-agents/workflows/remove-phase.md end-to-end.
-Preserve all validation gates (future phase check, work check), renumbering logic, and commit.
-</process>

package/commands/ez/research-phase.md

@@ -1,190 +0,0 @@
----
-name: ez:research-phase
-description: Research how to implement a phase (standalone - usually use /ez:plan-phase instead)
-argument-hint: "[phase]"
-allowed-tools:
-  - Read
-  - Bash
-  - Task
----
-
-<objective>
-Research how to implement a phase. Spawns ez-phase-researcher agent with phase context.
-
-**Note:** This is a standalone research command. For most workflows, use `/ez:plan-phase` which integrates research automatically.
-
-**Use this command when:**
-- You want to research without planning yet
-- You want to re-research after planning is complete
-- You need to investigate before deciding if a phase is feasible
-
-**Orchestrator role:** Parse phase, validate against roadmap, check existing research, gather context, spawn researcher agent, present results.
-
-**Why subagent:** Research burns context fast (WebSearch, Context7 queries, source verification). Fresh 200k context for investigation. Main context stays lean for user interaction.
-</objective>
-
-<context>
-Phase number: $ARGUMENTS (required)
-
-Normalize phase input in step 1 before any directory lookups.
-</context>
-
-<process>
-
-## 0. Initialize Context
-
-```bash
-INIT=$(node "$HOME/.claude/ez-agents/bin/ez-tools.cjs" init phase-op "$ARGUMENTS")
-if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
-```
-
-Extract from init JSON: `phase_dir`, `phase_number`, `phase_name`, `phase_found`, `commit_docs`, `has_research`, `state_path`, `requirements_path`, `context_path`, `research_path`.
-
-Resolve researcher model:
-```bash
-RESEARCHER_MODEL=$(node "$HOME/.claude/ez-agents/bin/ez-tools.cjs" resolve-model ez-phase-researcher --raw)
-```
-
-## 1. Validate Phase
-
-```bash
-PHASE_INFO=$(node "$HOME/.claude/ez-agents/bin/ez-tools.cjs" roadmap get-phase "${phase_number}")
-```
-
-**If `found` is false:** Error and exit. **If `found` is true:** Extract `phase_number`, `phase_name`, `goal` from JSON.
-
-## 2. Check Existing Research
-
-```bash
-ls .planning/phases/${PHASE}-*/RESEARCH.md 2>/dev/null
-```
-
-**If exists:** Offer: 1) Update research, 2) View existing, 3) Skip. Wait for response.
-
-**If doesn't exist:** Continue.
-
-## 3. Gather Phase Context
-
-Use paths from INIT (do not inline file contents in orchestrator context):
-- `requirements_path`
-- `context_path`
-- `state_path`
-
-Present summary with phase description and what files the researcher will load.
-
-## 4. Spawn ez-phase-researcher Agent
-
-Research modes: ecosystem (default), feasibility, implementation, comparison.
-
-```markdown
-<research_type>
-Phase Research — investigating HOW to implement a specific phase well.
-</research_type>
-
-<key_insight>
-The question is NOT "which library should I use?"
-
-The question is: "What do I not know that I don't know?"
-
-For this phase, discover:
-- What's the established architecture pattern?
-- What libraries form the standard stack?
-- What problems do people commonly hit?
-- What's SOTA vs what Claude's training thinks is SOTA?
-- What should NOT be hand-rolled?
-</key_insight>
-
-<objective>
-Research implementation approach for Phase {phase_number}: {phase_name}
-Mode: ecosystem
-</objective>
-
-<files_to_read>
-- {requirements_path} (Requirements)
-- {context_path} (Phase context from discuss-phase, if exists)
-- {state_path} (Prior project decisions and blockers)
-</files_to_read>
-
-<additional_context>
-**Phase description:** {phase_description}
-</additional_context>
-
-<downstream_consumer>
-Your RESEARCH.md will be loaded by `/ez:plan-phase` which uses specific sections:
-- `## Standard Stack` → Plans use these libraries
-- `## Architecture Patterns` → Task structure follows these
-- `## Don't Hand-Roll` → Tasks NEVER build custom solutions for listed problems
-- `## Common Pitfalls` → Verification steps check for these
-- `## Code Examples` → Task actions reference these patterns
-
-Be prescriptive, not exploratory. "Use X" not "Consider X or Y."
-</downstream_consumer>
-
-<quality_gate>
-Before declaring complete, verify:
-- [ ] All domains investigated (not just some)
-- [ ] Negative claims verified with official docs
-- [ ] Multiple sources for critical claims
-- [ ] Confidence levels assigned honestly
-- [ ] Section names match what plan-phase expects
-</quality_gate>
-
-<output>
-Write to: .planning/phases/${PHASE}-{slug}/${PHASE}-RESEARCH.md
-</output>
-```
-
-```
-Task(
-  prompt=filled_prompt,
-  subagent_type="ez-phase-researcher",
-  model="{researcher_model}",
-  description="Research Phase {phase}"
-)
-```
-
-## 5. Handle Agent Return
-
-**`## RESEARCH COMPLETE`:** Display summary, offer: Plan phase, Dig deeper, Review full, Done.
-
-**`## CHECKPOINT REACHED`:** Present to user, get response, spawn continuation.
-
-**`## RESEARCH INCONCLUSIVE`:** Show what was attempted, offer: Add context, Try different mode, Manual.
-
-## 6. Spawn Continuation Agent
-
-```markdown
-<objective>
-Continue research for Phase {phase_number}: {phase_name}
-</objective>
-
-<prior_state>
-<files_to_read>
-- .planning/phases/${PHASE}-{slug}/${PHASE}-RESEARCH.md (Existing research)
-</files_to_read>
-</prior_state>
-
-<checkpoint_response>
-**Type:** {checkpoint_type}
-**Response:** {user_response}
-</checkpoint_response>
-```
-
-```
-Task(
-  prompt=continuation_prompt,
-  subagent_type="ez-phase-researcher",
-  model="{researcher_model}",
-  description="Continue research Phase {phase}"
-)
-```
-
-</process>
-
-<success_criteria>
-- [ ] Phase validated against roadmap
-- [ ] Existing research checked
-- [ ] ez-phase-researcher spawned with context
-- [ ] Checkpoints handled correctly
-- [ ] User knows next steps
-</success_criteria>

package/commands/ez/resume.md

@@ -1,107 +0,0 @@
----
-name: ez:resume
-description: Resume from last session or navigate session chain
-argument-hint: "[session_id] [--previous|--next|--chain]"
-allowed-tools:
-  - Read
-  - Write
-  - AskUserQuestion
-  - Bash
----
-
-<objective>
-Resume work from the last session or navigate the session chain.
-
-This command:
-- Loads the most recent session from .planning/sessions/
-- Displays a formatted summary with model, phase, plan, duration, and last activity
-- Shows incomplete items, open decisions, and file changes
-- Presents recommended next action
-- Waits for user confirmation before proceeding
-- Supports navigation through session chain (previous/next)
-</objective>
-
-<execution_context>
-@~/.claude/ez-agents/workflows/resume-session.md
-</execution_context>
-
-<context>
-$ARGUMENTS
-
-Session ID is optional. If not provided, the last session is loaded.
-</context>
-
-<process>
-**Follow the resume-session workflow** from @~/.claude/ez-agents/workflows/resume-session.md.
-
-The workflow handles all resumption logic including:
-
-1. **Load last session:**
-   - Use ez-tools to access SessionManager
-   - Call getLastSession()
-   - If no sessions: output "No previous sessions found. Start a new session with your work."
-   - Exit
-
-2. **Parse session data:**
-   - Extract: metadata (model, phase, plan, started_at, ended_at, status)
-   - Extract: context (transcript, tasks, decisions, file_changes)
-   - Extract: state (incomplete_tasks, last_action, next_recommended_action)
-
-3. **Generate summary display:**
-   - Use box-drawing characters for header:
-     ```
-     ╔══════════════════════════════════════════════════════════════╗
-     ║  SESSION RESUME: {session_id}                                 ║
-     ╠══════════════════════════════════════════════════════════════╣
-     ║  Model: {model}                                              ║
-     ║  Phase: {phase} - {phase_name}                               ║
-     ║  Plan: {plan} - {plan_name}                                  ║
-     ║  Duration: {calculated}                                      ║
-     ║  Ended: {ended_at formatted}                                 ║
-     ╚══════════════════════════════════════════════════════════════╝
-     ```
-   - Section: "## Last Activity" - shows last completed task and in-progress task
-   - Section: "## Incomplete Items" - lists state.incomplete_tasks
-   - Section: "## Open Decisions" - lists context.open_questions or "None"
-   - Section: "## File Changes" - lists context.file_changes
-   - Section: "## Recommended Next Action" - shows state.next_recommended_action
-
-4. **Present options:**
-   ```
-   What would you like to do?
-
-   1. Continue from last task
-   2. Show full transcript
-   3. Export session for handoff
-   4. Navigate session chain
-   5. Start fresh (ignore session)
-   6. Something else
-   ```
-
-5. **Handle user choice:**
-   - "1" or "Continue":
-     - Update STATE.md with session continuity
-     - Load session context into conversation
-     - Proceed with recommended action
-   - "2" or "Show transcript":
-     - Display full transcript from session.context.transcript
-   - "3" or "Export":
-     - Trigger export-session workflow
-   - "4" or "Navigate":
-     - Show chain visualization
-     - Offer: Previous, Next, Jump to specific
-   - "5" or "Start fresh":
-     - Acknowledge, start new context
-   - "6" or "Something else":
-     - Enter interactive mode
-
-6. **On confirmation to continue:**
-   - Call ez-tools state record-session with stopped-at and resume-file
-   - Load relevant context files (PLAN.md, STATE.md, incomplete task files)
-   - Output: "Resuming from {session_id}. Last action: {last_action}"
-
-**Navigation flags:**
-- `--previous`: Navigate to previous session in chain
-- `--next`: Navigate to next session in chain
-- `--chain`: Show full chain visualization
-</process>

package/commands/ez/set-profile.md

@@ -1,34 +0,0 @@
----
-name: ez:set-profile
-description: Switch model profile for EZ Agents agents (quality/balanced/budget)
-argument-hint: <profile>
-allowed-tools:
-  - Read
-  - Write
-  - Bash
----
-
-<objective>
-Switch the model profile used by EZ Agents agents. Controls which Claude model each agent uses, balancing quality vs token spend.
-
-Routes to the set-profile workflow which handles:
-- Argument validation (quality/balanced/budget)
-- Config file creation if missing
-- Profile update in config.json
-- Confirmation with model table display
-</objective>
-
-<execution_context>
-@~/.claude/ez-agents/workflows/set-profile.md
-</execution_context>
-
-<process>
-**Follow the set-profile workflow** from `@~/.claude/ez-agents/workflows/set-profile.md`.
-
-The workflow handles all logic including:
-1. Profile argument validation
-2. Config file ensuring
-3. Config reading and updating
-4. Model table generation from MODEL_PROFILES
-5. Confirmation display
-</process>

package/commands/ez/standup.md

@@ -1,85 +0,0 @@
----
-name: ez:standup
-description: Run a sprint standup simulation. Scrum Master agent reports velocity, blockers, and sprint health score.
-argument-hint: "[phase]"
-allowed-tools:
-  - Read
-  - Bash
-  - Glob
-  - Grep
----
-
-<execution_context>
-@~/.claude/ez-agents/workflows/standup.md
-</execution_context>
-
-<process>
-Execute the standup workflow from @~/.claude/ez-agents/workflows/standup.md end-to-end.
-Parse ARGUMENTS for optional phase number before executing.
-</process>
-
-# /ez:standup
-
-Run a sprint standup simulation. The Scrum Master agent analyzes project state and reports velocity trends, active blockers, and sprint health score.
-
-## Usage
-
-```
-/ez:standup [phase]
-```
-
-## Arguments
-
-| Argument | Description |
-|----------|-------------|
-| `phase` | Optional phase number for phase-specific standup. Defaults to current phase. |
-
-## What It Produces
-
-```
-## Daily Standup — 2026-03-19
-
-### Yesterday
-- Completed: Phase 17 — Package Manager Flexibility (3 plans)
-- Verified: Phase 17 passed verification (score 4/5)
-
-### Today (Planned)
-- Phase 18: Session Memory — 3 plans ready
-- Next: Execute Phase 18
-
-### Blockers
-None
-
-### Velocity Trend
-↑ IMPROVING — avg 2.3 plans/session (up from 1.8 last 5 sessions)
-
-Sprint Health: 78/100 — SOME FRICTION
-Recommendation: Coverage at 71% — target 80% for medium tier release
-```
-
-## Sprint Health Score
-
-The standup includes a 0-100 sprint health score:
-
-| Score | Status | Meaning |
-|-------|--------|---------|
-| 80-100 | HEALTHY | Continue at pace |
-| 60-79 | SOME FRICTION | Address specific warnings |
-| 40-59 | STRUGGLING | Consider scope reduction |
-| <40 | AT RISK | Pause and address blockers |
-
-Dimensions tracked: velocity trend, active blockers, deviation rate, requirements coverage, plan completion rate, BDD pass rate.
-
-## When to Use
-
-- Before starting a new phase to check team health
-- After a phase completes to see trend
-- When things feel slow — get an objective measure
-- Before a release to check if ready
-
-## Related Commands
-
-- `/ez:arch-review` — Technical architecture review
-- `/ez:progress` — Project progress overview
-- `/ez:stats` — Enhanced metrics dashboard
-- `/ez:release` — Release with readiness validation

package/commands/ez/stats.md

@@ -1,18 +0,0 @@
----
-name: ez:stats
-description: Display project statistics — phases, plans, requirements, git metrics, and timeline
-allowed-tools:
-  - Read
-  - Bash
----
-<objective>
-Display comprehensive project statistics including phase progress, plan execution metrics, requirements completion, git history stats, and project timeline.
-</objective>
-
-<execution_context>
-@~/.claude/ez-agents/workflows/stats.md
-</execution_context>
-
-<process>
-Execute the stats workflow from @~/.claude/ez-agents/workflows/stats.md end-to-end.
-</process>

package/commands/ez/ui-phase.md

@@ -1,34 +0,0 @@
----
-name: ez:ui-phase
-description: Generate UI design contract (UI-SPEC.md) for frontend phases
-argument-hint: "[phase]"
-allowed-tools:
-  - Read
-  - Write
-  - Bash
-  - Glob
-  - Grep
-  - Task
-  - WebFetch
-  - AskUserQuestion
-  - mcp__context7__*
----
-<objective>
-Create a UI design contract (UI-SPEC.md) for a frontend phase.
-Orchestrates ez-ui-researcher and ez-ui-checker.
-Flow: Validate → Research UI → Verify UI-SPEC → Done
-</objective>
-
-<execution_context>
-@~/.claude/ez-agents/workflows/ui-phase.md
-@~/.claude/ez-agents/references/ui-brand.md
-</execution_context>
-
-<context>
-Phase number: $ARGUMENTS — optional, auto-detects next unplanned phase if omitted.
-</context>
-
-<process>
-Execute @~/.claude/ez-agents/workflows/ui-phase.md end-to-end.
-Preserve all workflow gates.
-</process>

package/commands/ez/ui-review.md

@@ -1,32 +0,0 @@
----
-name: ez:ui-review
-description: Retroactive 6-pillar visual audit of implemented frontend code
-argument-hint: "[phase]"
-allowed-tools:
-  - Read
-  - Write
-  - Bash
-  - Glob
-  - Grep
-  - Task
-  - AskUserQuestion
----
-<objective>
-Conduct a retroactive 6-pillar visual audit. Produces UI-REVIEW.md with
-graded assessment (1-4 per pillar). Works on any project.
-Output: {phase_num}-UI-REVIEW.md
-</objective>
-
-<execution_context>
-@~/.claude/ez-agents/workflows/ui-review.md
-@~/.claude/ez-agents/references/ui-brand.md
-</execution_context>
-
-<context>
-Phase: $ARGUMENTS — optional, defaults to last completed phase.
-</context>
-
-<process>
-Execute @~/.claude/ez-agents/workflows/ui-review.md end-to-end.
-Preserve all workflow gates.
-</process>