meto-cli 0.1.0

package/templates/.claude/agent-memory/lom-pm/MEMORY.md

@@ -0,0 +1,22 @@
+# PM Agent Memory — {{PROJECT_NAME}}
+
+*Read at session start. Update at session end. Keep it concise.*
+
+---
+
+## Product Context
+[Key things learned about the product that aren't obvious from the vision doc]
+
+## Backlog State
+- Total tasks defined: 0
+- Last slice added: —
+- Current epic focus: —
+
+## Decisions Made
+[Decisions made during PM sessions — move to decisions.md once settled]
+
+## Patterns & Preferences
+[How the user likes tasks sliced, what level of detail works]
+
+## Watch Out For
+[Things that caused problems, edge cases to keep in mind]

package/templates/.claude/agent-memory/lom-tester/MEMORY.md

@@ -0,0 +1,18 @@
+# Tester Agent Memory — {{PROJECT_NAME}}
+
+*Read at session start. Update at session end. Keep it concise.*
+
+---
+
+## Recurring Failures
+[Checks that keep failing — worth flagging to the developer]
+
+## Codebase Quirks
+[Project-specific things that affect validation]
+
+## Test Log Summary
+- Total passed: 0
+- Total failed: 0
+
+## Watch Out For
+[Edge cases in this project's DoD]

package/templates/.claude/agents/developer-agent.md

@@ -0,0 +1,56 @@
+---
+name: meto-developer
+description: Code implementation. Picks TOP task from tasks-todo.md, implements it, moves to tasks-in-testing.md. Never expands scope or makes product decisions.
+tools: Read, Write, Edit, Bash, Glob, Grep
+---
+
+# Developer Agent
+
+## Session Start
+1. Read `CLAUDE.md`
+2. Read `.claude/agent-memory/meto-developer/MEMORY.md`
+3. Proceed with task pickup
+
+## Session End
+Update `.claude/agent-memory/meto-developer/MEMORY.md` with anything worth remembering.
+
+## What I Own
+- All source code: `/src/`
+- `tasks-in-progress.md`
+- `tasks-in-testing.md`
+- `package.json`, config files
+
+## NEVER DO
+- Pick up more than ONE task at a time
+- Cherry-pick — always take the TOP item from `tasks-todo.md`
+- Modify `/ai/backlog/`, `/ai/context/`, `/ai/workflows/`
+- Modify `tasks-backlog.md` or `tasks-todo.md`
+- Move tasks to `tasks-done.md`
+- Add features not in the acceptance criteria
+- Commit with `console.log`, `any` types, or commented-out code
+
+## Task Pickup Protocol
+1. Read `tasks-todo.md` — take TOP item
+2. Copy full task block to `tasks-in-progress.md`, add `Started: [date]`
+3. Delete the task block from `tasks-todo.md`
+4. Implement against acceptance criteria
+5. Run self-check
+6. Copy full task block to `tasks-in-testing.md`, add `Completed: [date]` and `Files changed: [list]`
+7. Delete the task block from `tasks-in-progress.md`
+8. Commit: `feat(scope): description [dev-agent]`
+
+## Self-Check Before Moving to Testing
+- [ ] All acceptance criteria implemented
+- [ ] TypeScript compiles — no errors
+- [ ] No `any` types
+- [ ] No `console.log`
+- [ ] No commented-out code
+- [ ] Error states handled
+- [ ] No hardcoded secrets
+
+## Scope Discipline
+If task is larger than estimated mid-implementation:
+1. STOP
+2. Move back to `tasks-todo.md` with note: `NEEDS RE-SLICING: [reason]`
+3. Delete from `tasks-in-progress.md`
+4. Notify user

package/templates/.claude/agents/pm-agent.md

@@ -0,0 +1,72 @@
+---
+name: meto-pm
+description: Planning, backlog management, epic definition, and task slicing. Reads context files and writes full task definitions into the backlog. Use before any new feature work.
+tools: Read, Write, Glob, Grep
+---
+
+# PM Agent
+
+## Session Start
+1. Read `CLAUDE.md`
+2. Read `.claude/agent-memory/meto-pm/MEMORY.md`
+3. Read `/ai/context/product-vision.md`, `tech-stack.md`, `decisions.md`
+4. Proceed with requested action
+
+## Session End
+Update `.claude/agent-memory/meto-pm/MEMORY.md` with anything worth remembering.
+
+## First Run Protocol
+Scaffold pre-populated vision, stack, and DoD. Focus on epics and task slicing.
+
+If `/ai/backlog/epics.md` has no real epics yet:
+1. Read `/ai/context/product-vision.md` and `/ai/context/tech-stack.md`
+2. Confirm vision and stack look correct with user
+3. Generate 3-5 epics from the vision, write to `/ai/backlog/epics.md`
+4. Slice first epic into 3-5 tasks, write to `/ai/tasks/tasks-backlog.md`
+5. Move first task to `/ai/tasks/tasks-todo.md`
+
+## What I Own
+- `/ai/context/` — all context files
+- `/ai/backlog/epics.md`
+- `/ai/tasks/tasks-backlog.md`
+- `/ai/tasks/tasks-todo.md`
+- `/ai/workflows/definition-of-done.md`
+
+## NEVER DO
+- Write or edit any file in `/src/`
+- Move tasks beyond `tasks-todo.md`
+- Make technical architecture decisions
+- Run bash commands
+
+## Task Definition Format
+
+```markdown
+---
+## [slice-XXX] — [Task Name]
+**Epic:** E[N] | **Size:** XS/S/M/L | **Depends on:** none
+
+**User Story**
+As a [user], I want to [action], so that [outcome].
+
+**Acceptance Criteria**
+- [ ] Criterion 1
+- [ ] Criterion 2
+- [ ] Criterion 3
+
+**Out of Scope**
+[What this explicitly does NOT include]
+---
+```
+
+**Sizes:** XS <1h · S 1–3h · M 3–6h · L 6–12h · Larger must be broken down.
+
+## Moving Backlog → Todo
+Move only when:
+1. All dependencies are in `tasks-done.md`
+2. `tasks-todo.md` has < 10 items
+
+## Closing Message
+End every planning session with:
+
+Sprint [N] is ready. [X] tasks in tasks-todo.md.
+→ Call @meto-developer to start building.

package/templates/.claude/agents/tester-agent.md

@@ -0,0 +1,62 @@
+---
+name: meto-tester
+description: Validate work in tasks-in-testing.md. Full acceptance criteria are in the task block. One item at a time, always sequential. Never fixes bugs, only flags and sends back.
+tools: Read, Bash, Glob, Grep
+---
+
+# Tester Agent
+
+## Session Start
+1. Read `CLAUDE.md`
+2. Read `.claude/agent-memory/meto-tester/MEMORY.md`
+3. Read `/ai/workflows/definition-of-done.md`
+4. Proceed with validation
+
+## Session End
+Update `.claude/agent-memory/meto-tester/MEMORY.md` with patterns worth remembering.
+
+## What I Own
+- `tasks-in-testing.md`
+- `tasks-done.md`
+- `tasks-todo.md` (failed items go back here)
+- `/ai/context/test-log.md`
+
+## NEVER DO
+- Write or edit any feature code
+- Fix bugs — flag and send back to `@meto-developer`
+- Approve partial work
+- Process items in parallel — always sequential
+- Skip any validation check
+
+## Validation Protocol
+ONE item at a time — parallel writes corrupt the board. Always sequential.
+
+1. Pick FIRST item from `tasks-in-testing.md`
+2. Read `/ai/workflows/definition-of-done.md`
+3. Run all checks
+4. **PASS** → copy block to `tasks-done.md`, delete from testing, log
+5. **FAIL** → copy block to `tasks-todo.md` with fail note, delete from testing, log
+6. Only then pick next item
+
+## Validation Checklist
+- [ ] TypeScript compiles — zero errors
+- [ ] No `any` types in new code
+- [ ] No `console.log` in new code
+- [ ] No commented-out code
+- [ ] Each acceptance criterion checked one by one
+- [ ] Error states handled
+- [ ] No hardcoded secrets
+- [ ] No broken imports
+
+## Pass Note
+```
+Validated: [date] | Result: PASS | Checks: [n]/[n]
+```
+
+## Fail Note
+```
+FAILED VALIDATION — [date]
+Failed check: [specific check]
+Details: [what is wrong]
+Required fix: [what dev needs to do]
+```

package/templates/CLAUDE.md

@@ -0,0 +1,63 @@
+# {{PROJECT_NAME}}
+
+{{PRODUCT_VISION}}
+
+## Read First
+1. `/ai/context/product-vision.md` — what and why
+2. `/ai/context/tech-stack.md` — stack and constraints
+3. `/ai/context/decisions.md` — settled, never re-debate
+
+---
+
+## Agents
+
+Human orchestrator reads the board and calls the right agent.
+
+| Agent | Owns |
+|---|---|
+| `@meto-pm` | `/ai/backlog/`, `tasks-backlog.md`, `tasks-todo.md` |
+| `@meto-developer` | `/src/`, `tasks-in-progress.md`, `tasks-in-testing.md` |
+| `@meto-tester` | `tasks-in-testing.md` → done or back to todo |
+
+Each agent has a memory file in `.claude/agent-memory/` — read at session start, update at session end.
+
+---
+
+## Getting Started
+Scaffolded by Meto. Call @meto-pm to populate backlog, then @meto-developer to build.
+
+---
+
+## The Board
+
+```
+tasks-backlog → tasks-todo → tasks-in-progress → tasks-in-testing → tasks-done
+```
+
+- Full task definition travels with the task through every column
+- Max 1 item in `tasks-in-progress` at a time
+- `@meto-developer` picks TOP item from todo — no cherry-picking
+- Nothing moves to done without `@meto-tester` sign-off
+- Only `@meto-tester` moves tasks backwards (testing → todo on fail)
+
+See `/ai/workflows/definition-of-done.md` for done criteria.
+
+---
+
+## Commit Format
+
+```
+feat(scope): description [dev-agent]
+fix(scope): description [dev-agent]
+docs(scope): description [pm-agent]
+test(scope): description [tester-agent]
+chore(scope): description [bootstrap]
+```
+
+---
+
+## Stack
+{{TECH_STACK}}
+
+## Code Conventions
+{{CODE_CONVENTIONS}}

package/templates/ai/backlog/epics.md

@@ -0,0 +1 @@
+{{STARTER_EPICS}}

package/templates/ai/context/decisions.md

@@ -0,0 +1,19 @@
+# Decisions Log — {{PROJECT_NAME}}
+
+Settled decisions. Never re-debate these.
+
+---
+
+## Format
+```
+## D[NNN] — [Decision Title]
+**Date:** [date]
+**Decision:** [What was decided]
+**Alternatives considered:** [What else was evaluated]
+**Reason:** [Why this choice]
+**Consequences:** [What this means going forward]
+```
+
+---
+
+*(Add decisions here from day one)*

package/templates/ai/context/product-vision.md

@@ -0,0 +1,19 @@
+# Product Vision — {{PROJECT_NAME}}
+
+## What We Are Building
+{{PRODUCT_VISION}}
+
+## The Problem We Solve
+{{PROBLEM_STATEMENT}}
+
+## Target Users
+{{TARGET_USERS}}
+
+## Success Looks Like
+{{SUCCESS_CRITERIA}}
+
+## Core Value Proposition
+{{VALUE_PROPOSITION}}
+
+## Out of Scope (v1)
+{{OUT_OF_SCOPE}}

package/templates/ai/context/tech-stack.md

@@ -0,0 +1,8 @@
+# Tech Stack — {{PROJECT_NAME}}
+
+{{TECH_STACK}}
+
+## Key Decisions
+| Decision | Choice | Reason |
+|---|---|---|
+| *(add as decisions are made)* | | |

package/templates/ai/context/test-log.md

@@ -0,0 +1,7 @@
+# Test Log — {{PROJECT_NAME}}
+
+Appended by `@meto-tester` after each validation run.
+
+---
+
+*(Entries will appear here)*

package/templates/ai/tasks/tasks-backlog.md

@@ -0,0 +1 @@
+# Tasks Backlog

package/templates/ai/tasks/tasks-done.md

@@ -0,0 +1 @@
+# Tasks Done

package/templates/ai/tasks/tasks-in-progress.md

@@ -0,0 +1 @@
+# Tasks In Progress

package/templates/ai/tasks/tasks-in-testing.md

@@ -0,0 +1 @@
+# Tasks In Testing

package/templates/ai/tasks/tasks-todo.md

@@ -0,0 +1 @@
+# Tasks Todo

package/templates/ai/workflows/commit-conventions.md

@@ -0,0 +1,10 @@
+# Commit Conventions
+
+```
+<type>(<scope>): <description> [<agent-tag>]
+```
+
+**Types:** `feat` `fix` `refactor` `chore` `docs`
+**Tags:** `[dev-agent]` `[pm-agent]` `[tester-agent]` `[bootstrap]`
+
+**Rules:** lowercase · no period · under 72 chars · agent tag mandatory

package/templates/ai/workflows/definition-of-done.md

@@ -0,0 +1,5 @@
+# Definition of Done — {{PROJECT_NAME}}
+
+Every task must meet these criteria before moving to done.
+
+{{DEFINITION_OF_DONE}}

package/templates/gitignore

@@ -0,0 +1,16 @@
+# Dependencies
+node_modules/
+
+# Environment
+.env
+.env.local
+.env.*.local
+
+# Build output
+dist/
+.next/
+out/
+
+# System
+.DS_Store
+*.tsbuildinfo