vibe-forge 0.8.1 → 0.8.3

package/{context → templates}/project-context-template.md

@@ -1,122 +1,122 @@
-# Project Context
-
-**This file is the single source of truth for all Vibe Forge agents.**
-
-Every agent loads this file at session start. Update this when architecture or conventions change.
-
----
-
-## Project Identity
-
-- **Name:** {PROJECT_NAME}
-- **Description:** {ONE_LINE_DESCRIPTION}
-- **Repository:** {REPO_URL}
-
----
-
-## Tech Stack
-
-### Frontend
-- Framework: {React/Vue/Svelte/etc}
-- Styling: {Tailwind/CSS Modules/Styled Components/etc}
-- State: {Redux/Zustand/Context/etc}
-- Build: {Vite/Webpack/etc}
-
-### Backend
-- Runtime: {Node/Deno/Bun/etc}
-- Framework: {Express/Fastify/Hono/etc}
-- Database: {PostgreSQL/MongoDB/SQLite/etc}
-- ORM: {Prisma/Drizzle/TypeORM/etc}
-
-### Testing
-- Unit: {Vitest/Jest/etc}
-- E2E: {Playwright/Cypress/etc}
-- Coverage target: {80%/etc}
-
----
-
-## File Structure
-
-```
-{PROJECT_ROOT}/
-├── src/
-│   ├── components/     # React components (Anvil's domain)
-│   ├── pages/          # Page components
-│   ├── api/            # API routes (Furnace's domain)
-│   ├── services/       # Business logic
-│   ├── models/         # Data models
-│   ├── utils/          # Shared utilities
-│   └── types/          # TypeScript types
-├── tests/              # Test files (Crucible's domain)
-├── docs/               # Documentation (Scribe's domain)
-└── ...
-```
-
----
-
-## Coding Standards
-
-### Naming
-- Components: PascalCase (`UserProfile.tsx`)
-- Functions: camelCase (`getUserById`)
-- Constants: SCREAMING_SNAKE (`MAX_RETRIES`)
-- Files: kebab-case for non-components (`auth-service.ts`)
-
-### Patterns
-- {Pattern 1: e.g., "Use custom hooks for shared logic"}
-- {Pattern 2: e.g., "Services return Result<T, E> types"}
-- {Pattern 3: e.g., "API routes follow REST conventions"}
-
-### Forbidden
-- {Anti-pattern 1: e.g., "No any types"}
-- {Anti-pattern 2: e.g., "No console.log in production code"}
-- {Anti-pattern 3: e.g., "No direct DOM manipulation in React"}
-
----
-
-## Key Decisions
-
-### Architecture
-- {Decision 1: e.g., "Monorepo with Turborepo"}
-- {Decision 2: e.g., "Feature-based folder structure"}
-
-### Why We Chose X
-- {Rationale for major tech choice}
-
----
-
-## Environment
-
-### Local Development
-```bash
-{SETUP_COMMANDS}
-```
-
-### Environment Variables
-- `DATABASE_URL` - Database connection string
-- `API_KEY` - External API key
-- {etc}
-
----
-
-## Agent-Specific Notes
-
-### Anvil (Frontend)
-- Component library: {Shadcn/Radix/etc}
-- Design system: {Link to Figma/Storybook}
-
-### Furnace (Backend)
-- API base path: `/api/v1`
-- Auth method: {JWT/Session/etc}
-
-### Crucible (Testing)
-- Run tests: `npm test`
-- Coverage: `npm run test:coverage`
-
----
-
-## Links
-
-- Design: {Figma URL}
-- API Docs: {Swagger/OpenAPI URL}
-- Deployment: {Vercel/AWS/etc dashboard}
+# Project Context
+
+**This file is the single source of truth for all Vibe Forge agents.**
+
+Every agent loads this file at session start. Update this when architecture or conventions change.
+
+---
+
+## Project Identity
+
+- **Name:** {PROJECT_NAME}
+- **Description:** {ONE_LINE_DESCRIPTION}
+- **Repository:** {REPO_URL}
+
+---
+
+## Tech Stack
+
+### Frontend
+- Framework: {React/Vue/Svelte/etc}
+- Styling: {Tailwind/CSS Modules/Styled Components/etc}
+- State: {Redux/Zustand/Context/etc}
+- Build: {Vite/Webpack/etc}
+
+### Backend
+- Runtime: {Node/Deno/Bun/etc}
+- Framework: {Express/Fastify/Hono/etc}
+- Database: {PostgreSQL/MongoDB/SQLite/etc}
+- ORM: {Prisma/Drizzle/TypeORM/etc}
+
+### Testing
+- Unit: {Vitest/Jest/etc}
+- E2E: {Playwright/Cypress/etc}
+- Coverage target: {80%/etc}
+
+---
+
+## File Structure
+
+```
+{PROJECT_ROOT}/
+├── src/
+│   ├── components/     # React components (Anvil's domain)
+│   ├── pages/          # Page components
+│   ├── api/            # API routes (Furnace's domain)
+│   ├── services/       # Business logic
+│   ├── models/         # Data models
+│   ├── utils/          # Shared utilities
+│   └── types/          # TypeScript types
+├── tests/              # Test files (Crucible's domain)
+├── docs/               # Documentation (Scribe's domain)
+└── ...
+```
+
+---
+
+## Coding Standards
+
+### Naming
+- Components: PascalCase (`UserProfile.tsx`)
+- Functions: camelCase (`getUserById`)
+- Constants: SCREAMING_SNAKE (`MAX_RETRIES`)
+- Files: kebab-case for non-components (`auth-service.ts`)
+
+### Patterns
+- {Pattern 1: e.g., "Use custom hooks for shared logic"}
+- {Pattern 2: e.g., "Services return Result<T, E> types"}
+- {Pattern 3: e.g., "API routes follow REST conventions"}
+
+### Forbidden
+- {Anti-pattern 1: e.g., "No any types"}
+- {Anti-pattern 2: e.g., "No console.log in production code"}
+- {Anti-pattern 3: e.g., "No direct DOM manipulation in React"}
+
+---
+
+## Key Decisions
+
+### Architecture
+- {Decision 1: e.g., "Monorepo with Turborepo"}
+- {Decision 2: e.g., "Feature-based folder structure"}
+
+### Why We Chose X
+- {Rationale for major tech choice}
+
+---
+
+## Environment
+
+### Local Development
+```bash
+{SETUP_COMMANDS}
+```
+
+### Environment Variables
+- `DATABASE_URL` - Database connection string
+- `API_KEY` - External API key
+- {etc}
+
+---
+
+## Agent-Specific Notes
+
+### Anvil (Frontend)
+- Component library: {Shadcn/Radix/etc}
+- Design system: {Link to Figma/Storybook}
+
+### Furnace (Backend)
+- API base path: `/api/v1`
+- Auth method: {JWT/Session/etc}
+
+### Crucible (Testing)
+- Run tests: `npm test`
+- Coverage: `npm run test:coverage`
+
+---
+
+## Links
+
+- Design: {Figma URL}
+- API Docs: {Swagger/OpenAPI URL}
+- Deployment: {Vercel/AWS/etc dashboard}

package/config/task-template.md

@@ -1,159 +0,0 @@
----
-id: task-{ID}
-title: "{TITLE}"
-type: {TYPE}  # frontend | backend | test | docs | review | release | devops | security
-priority: {PRIORITY}  # critical | high | medium | low
-status: pending
-assigned_to: null
-blocked_by: []
-depends_on: []
-created: {TIMESTAMP}
-updated: {TIMESTAMP}
-estimated_complexity: {COMPLEXITY}  # trivial | low | medium | high | unknown
-epic: {EPIC_ID}
-story: {STORY_ID}  # optional - epic_num.story_num format (e.g. 2.3)
-isolation: none  # none | worktree - use worktree for risky or experimental changes
----
-
-# Context
-
-## Parent Epic
-See: /specs/epics/{EPIC_ID}.md
-
-## Relevant Files
-<!-- List ONLY files the agent needs to read or modify -->
-- /path/to/relevant/file.ts (reason: what to do here)
-- /path/to/reference/file.ts (reference only)
-
-## Dependencies
-<!-- Other tasks that must complete first -->
-- task-{DEP_ID} (status: pending|completed)
-
-## Background
-<!-- Brief context the agent needs - keep minimal, reference docs instead -->
-{BACKGROUND}
-
-## Dev Notes
-<!-- Architecture guardrails, relevant patterns, tech constraints - filled by Hub/Architect before assignment -->
-<!-- Example:
-- Auth uses JWT with refresh tokens - follow the pattern in src/middleware/auth.ts
-- All DB access goes through the repository layer in src/repositories/ - no raw queries in controllers
-- Error responses must use the Result<T,E> pattern from src/utils/result.ts
-- Relevant architecture decisions: context/architecture.md#section-3
--->
-
----
-
-# Acceptance Criteria
-
-<!-- Number each criterion - agents link tasks to AC numbers, Sentinel audits each one -->
-1. {CRITERION_1}
-2. {CRITERION_2}
-3. {CRITERION_3}
-
----
-
-# Tasks / Subtasks
-
-<!-- Each task mapped to one or more AC numbers - enables per-criterion review audit -->
-- [ ] Task 1 (AC: #1, #2)
-  - [ ] Subtask 1.1
-  - [ ] Subtask 1.2
-- [ ] Task 2 (AC: #3)
-  - [ ] Subtask 2.1
-
----
-
-# Agent Instructions
-
-<!-- Specific instructions for the assigned agent -->
-{AGENT_TYPE}: {SPECIFIC_INSTRUCTIONS}
-
-**Boundaries:**
-- DO modify: {ALLOWED_PATHS}
-- DO NOT modify: {FORBIDDEN_PATHS}
-
-**When to STOP and write to tasks/attention/:**
-- Required package/dependency not in project - get approval before adding
-- 3 consecutive failures on the same test
-- Acceptance criteria are ambiguous or contradictory
-- Schema or migration change would affect live data
-- Security concern requires Aegis review
-
-**On Completion:**
-1. Verify all Definition of Done items below are checked
-2. Run relevant tests - confirm they pass
-3. Move this file to `/tasks/completed/`
-4. Fill in completion summary below
-
----
-
-# Definition of Done
-
-<!-- All items must be checked before setting ready_for_review: true -->
-<!-- Crucible audits this list before approving any task -->
-
-**Implementation**
-- [ ] All acceptance criteria satisfied (verify each numbered AC individually)
-- [ ] All tasks and subtasks completed
-- [ ] Edge cases handled — not just the happy path
-- [ ] No TODO/FIXME left in new code without a linked tracking task
-- [ ] No dead code or commented-out blocks committed
-
-**Testing**
-- [ ] Unit tests written for new functionality
-- [ ] Existing tests still pass (full suite, not just new tests)
-- [ ] No linting errors
-- [ ] Integration tests updated if this touches a service boundary
-- [ ] Negative cases tested (invalid input, error paths, boundary conditions)
-- [ ] No test is skipped or marked `.only` without a comment explaining why
-
-**Documentation**
-- [ ] File list complete in completion summary (every file touched)
-- [ ] Inline comments where logic is non-obvious
-- [ ] API contract documented if this adds or changes an endpoint
-- [ ] Breaking changes noted in completion summary with migration path
-
-**Security** _(if touching auth, data, external APIs, or file I/O)_
-- [ ] No hardcoded secrets or credentials
-- [ ] Input validated at boundaries
-- [ ] Error paths handled explicitly — not swallowed
-- [ ] Least privilege: no permissions broader than necessary
-
-**Database** _(if touching schema or data)_
-- [ ] Migration is reversible (down migration written and tested)
-- [ ] Migration does not destroy existing data without explicit task approval
-- [ ] Queries use parameterized inputs (no string concatenation)
-
-**Handoff**
-- [ ] Completion summary fully filled in (completed_by, files, test counts)
-- [ ] `ready_for_review: true` only when ALL above items are checked
-- [ ] Known limitations or follow-up tasks noted
-
----
-
-# Output Expected
-
-- [ ] Files created/modified listed in completion summary
-- [ ] Tests passing (include count)
-- [ ] No linting errors
-- [ ] Definition of Done fully checked
-
----
-
-# Completion Summary
-<!-- Filled by agent on completion -->
-
-```yaml
-completed_by: null
-completed_at: null
-duration_minutes: null
-agent_model: null
-files_modified: []
-files_created: []
-tests_added: 0
-tests_passing: 0
-notes: ""
-blockers_encountered: []
-ready_for_review: false
-```

package/config/templates/handoff-template.md

@@ -1,40 +0,0 @@
----
-task_id: {{TASK_ID}}
-agent: {{AGENT}}
-handoff_reason: context_limit | task_too_large | blocked | shift_change
-created: {{ISO_TIMESTAMP}}
-status: pending
----
-
-# Session Handoff: {{TASK_ID}}
-
-## What Was Done
-
-- [ ] List completed subtasks or acceptance criteria
-
-## What Remains
-
-- [ ] List remaining subtasks or acceptance criteria
-
-## Current State
-
-Describe the exact state of the work so the next agent can resume:
-
-- **Last file touched:** `path/to/file.ts`
-- **Pattern being used:** (e.g., "React Hook Form with Zod validation")
-- **Branch:** `task/TASK-XXX-description`
-- **Commits so far:** (list or count)
-
-## Key Context
-
-Anything the next agent needs to know that isn't in the task file:
-
-- Decisions made during this session
-- Gotchas discovered
-- Dependencies or blockers encountered
-
-## Resume Instructions
-
-1. Read this handoff file
-2. Check out branch `task/TASK-XXX-description`
-3. Continue from [specific file/function/line]