nitm-ai-dev-toolkit 4.0.0 → 5.0.1

package/src/repo/.claude/prompt-snippets/tasks.md

@@ -1,6 +1,8 @@
-# Generate Task Breakdown
+# Generate Task Checklist
 
-Break down the implementation plan into executable tasks. This is the third step in the development lifecycle.
+Break the implementation plan into a slim task checklist. This is the third step in the development lifecycle.
+
+`tasks.md` is a checklist only. Acceptance criteria live in `spec.md`; approach, files, and effort live in `plan.md`. Do not repeat them here.
 
 ## Usage
 
@@ -9,138 +11,73 @@ Break down the implementation plan into executable tasks. This is the third step
 /tasks docs/features/user-authentication/tasks.md
 ```
 
-## Task Consolidation Rules (CRITICAL)
+## When Not to Create tasks.md
 
-Before creating tasks, apply these consolidation principles:
+Small work (1-2 steps) needs no `tasks.md`. Implement it directly.
 
-### Target Task Counts
+## Consolidation Rules (CRITICAL)
 
-| Feature Complexity  | Total Tasks | Max Subtasks/Task |
-| ------------------- | ----------- | ----------------- |
-| Simple (< 4 hours)  | 2-3         | 0                 |
-| Medium (4-16 hours) | 3-5         | 2-4               |
-| Complex (16-40 hrs) | 5-8         | 3-6               |
-| Large (40+ hours)   | 8-12        | 5-10              |
+### Target Task Counts
 
-### Consolidation Principles
+| Feature Complexity  | Total Tasks |
+| ------------------- | ----------- |
+| Simple (< 4 hours)  | 2-3         |
+| Medium (4-16 hours) | 3-5         |
+| Complex (16-40 hrs) | 5-8         |
+| Large (40+ hours)   | 8-12        |
 
-- **Group by deliverable**: Combine work that ships together
-- **Merge related files**: Model + migration + factory = 1 task
-- **Bundle by layer**: All service layer work = 1 task (if related)
-- **Avoid micro-tasks**: Nothing under 1-2 hours as standalone
-- **Limit phases**: Combine Foundation + Implementation when small
+### Principles
 
-### Before Finalizing, Ask:
+- **Group by deliverable**: combine work that ships together (model + migration + factory = 1 task)
+- **Bundle by layer or resource**: all service work for one area, all endpoints for one resource
+- **Avoid micro-tasks**: nothing under 1-2 hours standalone
+- **Limit phases**: combine Foundation + Implementation when small
 
-1. Can any adjacent phases be combined?
-2. Are there tasks under 2 hours that should be merged?
-3. Would a developer naturally complete these together?
-4. Does each task represent meaningful progress?
+Before finalizing, ask: Can adjacent tasks merge? Would one developer naturally finish these together? Does each task show meaningful progress?
 
 ## Process
 
-1. **Load Context**:
-   - Read specification from `docs/features/{{ISSUE_ID}}-{{FEATURE_NAME}}/spec.md`
-   - Read plan from `docs/features/{{ISSUE_ID}}-{{FEATURE_NAME}}/plan.md`
-   - Review `AGENTS.md` for project patterns
-
-2. **Generate Consolidated Task Breakdown**:
-
-   Create `docs/features/{{ISSUE_ID}}-{{FEATURE_NAME}}/tasks.md` with phases (combine where appropriate):
-
-   ### Phase 1: Foundation & Setup (combine into 1 task)
-   - Database schema changes, migrations, seeders
-   - Type definitions and interfaces
-   - Base models and validators
-   - Configuration and dependencies
-
-   ### Phase 2: Core Implementation (group by feature area)
-   - Core functionality grouped by component
-   - API endpoints or components (CRUD together)
-   - Business logic and services
-
-   ### Phase 3: Testing (1 task per major component)
-   - Unit tests for component
-   - Integration tests for feature
-   - E2E tests (if applicable)
-
-   ### Phase 4: Polish & Documentation (combine into 1 task)
-   - Error handling improvements
-   - Performance optimization
-   - Documentation updates
+1. **Load context**: `docs/features/{{ISSUE_ID}}-{{FEATURE_NAME}}/spec.md`, `plan.md`, and `AGENTS.md` (project patterns).
 
-3. **Consolidated Task Format**:
+2. **Write `docs/features/{{ISSUE_ID}}-{{FEATURE_NAME}}/tasks.md`** in the format below.
 
-   ```markdown
-   ### T001: [Consolidated Task Name]
+3. **Report**: tasks file path, task count, number of `[P]` tasks, and the consolidation note ("Combined X items into Y tasks"). Next step: `/implement-feature`, or `/assign-tasks` to create tickets.
 
-   **Phase**: [Foundation/Implementation/Testing/Polish]
-   **Estimated Effort**: [Hours - aim for 2-8 hours per task]
-   **Parallel**: [Yes/No]
+## Task Line Format
 
-   **Scope** (what this task covers):
+```markdown
+# Tasks: {{ISSUE_ID}}-{{FEATURE_NAME}}
 
-   - [Component/feature 1]
-   - [Component/feature 2]
-   - [Related component 3]
-
-   **Files to Create/Modify**:
-
-   - `{{SRC_DIR}}/path/to/file.{{FILE_EXTENSION}}`
-   - `{{SRC_DIR}}/path/to/related.{{FILE_EXTENSION}}`
-   - `{{TEST_DIR}}/path/to/test.{{FILE_EXTENSION}}`
-
-   **Acceptance Criteria**:
-
-   - [ ] All components implemented
-   - [ ] Tests passing
-   - [ ] No type/lint errors
-
-   **Subtasks** (only if task > 8 hours):
-
-   - [ ] Subtask 1
-   - [ ] Subtask 2
-   ```
-
-4. **Task Ordering Rules**:
-   - Setup before implementation
-   - Tests before or alongside code (TDD)
-   - Core before integration
-   - Everything before polish
-
-5. **Parallel Execution**:
-   - Mark parallelizable tasks with `[P]`
-   - Different feature areas = can be parallel
-   - Same files = sequential
+- [ ] T1 Schema + migration for sessions — PROJ-124
+- [ ] T2 Login/logout endpoints [P]
+- [ ] T3 Login form + error states [P]
+```
 
-6. **Report Completion**:
-   - Tasks file path
-   - **Consolidated task count** (should be 3-7)
-   - Estimated total effort
-   - **Consolidation note**: "Combined X items into Y tasks"
-   - Ready for `/implement` command
+Each task is one line:
 
-## Anti-Patterns to Avoid
+- **Checkbox** `- [ ]`. Tick to `- [x]` once the task is implemented and reviewed.
+- **ID** `T<n>`, sequential, in dependency order.
+- **Description**: short and deliverable-focused (what ships, not how). No file lists, effort, or acceptance criteria.
+- **`[P]`** only when the task can run in parallel (different files, no shared state). Omit otherwise.
+- **` — <ticket key>`** appended after an em dash once a ticket exists. Written by `/assign-tasks`; never added before the ticket is created.
+- **Sub-bullets** only when a task truly needs them (rare).
 
-❌ **Don't create separate tasks for**:
+Ordering: setup before implementation; tests before or alongside code (TDD); core before integration; polish last. Tasks that touch the same files run sequentially and are never `[P]`.
 
-- Each individual file
-- "Create X" then "Configure X" then "Test X"
-- Setup tasks under 1 hour
-- Each CRUD operation separately
+## Anti-Patterns
 
-✅ **Do combine into single tasks**:
+❌ One task per file, per CRUD operation, or split into "Create X" / "Configure X" / "Test X"
+❌ Standalone setup tasks under 1 hour
 
-- All database work for an entity
-- All API endpoints for a resource
-- All configuration/setup work
-- Related service layer methods
+✅ All database work for an entity
+✅ All API endpoints for a resource
+✅ All configuration and setup for the feature
 
 ## Orchestrator Dispatch Guide
 
-When this task list is used by `/implement-feature` or `/implement`:
+When this list is used by `/implement-feature` or `/implement`:
 
-- **Parallel [P] tasks**: Dispatch one subagent per `[P]` task concurrently using `dispatching-parallel-agents` skill
-- **Sequential tasks**: Execute in dependency order, one subagent per task using `subagent-driven-development` skill
-- **Domain routing**: Match each task to the appropriate specialist agent (Backend Architect, Frontend Developer, API Specialist, etc.)
-- **Review gate**: Every task must pass a Reviewer agent before being marked complete
+- **`[P]` tasks**: dispatch one subagent per task concurrently, using `dispatching-parallel-agents`
+- **Other tasks**: execute in dependency order, one subagent per task, using `subagent-driven-development`
+- **Domain routing**: match each task to a specialist (Backend Architect, Frontend Developer, API Specialist, etc.)
+- **Review gate**: every task passes a Reviewer before it is ticked `[x]`

package/src/repo/.claude/rules-snippets/subagent-workflow.md

@@ -103,8 +103,8 @@ Before executing any task list, the orchestrator MUST run this analysis:
    - **Mixed** → Dispatch independent group in parallel, then continue sequential chain
 
 ```
-Example: 5 tasks → T001 (setup) → T002 [P] (backend API) + T003 [P] (frontend UI) + T004 [P] (docs) → T005 (integration tests)
-         Dispatch: T001 sequential → T002+T003+T004 parallel → T005 sequential
+Example: 5 tasks → T1 (setup) → T2 [P] (backend API) + T3 [P] (frontend UI) + T4 [P] (docs) → T5 (integration tests)
+         Dispatch: T1 sequential → T2+T3+T4 parallel → T5 sequential
 ```
 
 ## Quality Gates

package/src/repo/.cursor/agents/factory-approver.agent.md

@@ -0,0 +1,11 @@
+---
+description: "Decide whether a factory job is approved for merge or escalated to a human, checking history, final diff, a spot-checked criterion, a dry-run merge, and escalation triggers."
+globs:
+alwaysApply: agent
+---
+
+# Factory Approver Agent
+
+Decide whether a factory job is approved for merge or escalated to a human.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-approver.md](../../.claude/agents-snippets/factory-approver.md)

package/src/repo/.cursor/agents/factory-builder.agent.md

@@ -0,0 +1,11 @@
+---
+description: "Build a factory job's feature inside its git worktree, following TDD, and log results in build.md."
+globs:
+alwaysApply: agent
+---
+
+# Factory Builder Agent
+
+Build a factory job's feature inside its git worktree, following TDD, and log results in build.md.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-builder.md](../../.claude/agents-snippets/factory-builder.md)

package/src/repo/.cursor/agents/factory-reviewer-code.agent.md

@@ -0,0 +1,11 @@
+---
+description: "Review a factory job's branch for correctness, simplicity, reuse, conventions, and docs, and run the project's checks."
+globs:
+alwaysApply: agent
+---
+
+# Factory Reviewer (Code) Agent
+
+Review a factory job's branch for correctness, simplicity, reuse, conventions, and docs, and run the project's checks.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-reviewer-code.md](../../.claude/agents-snippets/factory-reviewer-code.md)

package/src/repo/.cursor/agents/factory-reviewer-security.agent.md

@@ -0,0 +1,11 @@
+---
+description: "Audit a factory job's branch diff for security problems in a fresh context."
+globs:
+alwaysApply: agent
+---
+
+# Factory Reviewer (Security) Agent
+
+Audit a factory job's branch diff for security problems in a fresh context.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-reviewer-security.md](../../.claude/agents-snippets/factory-reviewer-security.md)

package/src/repo/.cursor/agents/factory-reviewer-ui.agent.md

@@ -0,0 +1,11 @@
+---
+description: "Review a factory job's feature at its build location for design-system consistency, spacing, typography, contrast, and responsive layout, without signing in or writing to real services."
+globs:
+alwaysApply: agent
+---
+
+# Factory Reviewer (UI) Agent
+
+Review a factory job's feature at its build location for design-system consistency, spacing, typography, contrast, and responsive layout, without signing in or writing to real services.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-reviewer-ui.md](../../.claude/agents-snippets/factory-reviewer-ui.md)

package/src/repo/.cursor/agents/factory-reviewer-ux.agent.md

@@ -0,0 +1,11 @@
+---
+description: "Review a factory job's feature at its build location for flows, states, copy, accessibility, and mobile, without signing in or writing to real services."
+globs:
+alwaysApply: agent
+---
+
+# Factory Reviewer (UX) Agent
+
+Review a factory job's feature at its build location for flows, states, copy, accessibility, and mobile, without signing in or writing to real services.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-reviewer-ux.md](../../.claude/agents-snippets/factory-reviewer-ux.md)

package/src/repo/.cursor/agents/factory-spec-writer.agent.md

@@ -0,0 +1,11 @@
+---
+description: "Write a testable spec.md for a factory job from a feature request, after inspecting the real code."
+globs:
+alwaysApply: agent
+---
+
+# Factory Spec Writer Agent
+
+Write a testable spec.md for a factory job from a feature request, after inspecting the real code.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-spec-writer.md](../../.claude/agents-snippets/factory-spec-writer.md)

package/src/repo/.cursor/commands/factory.md

@@ -0,0 +1,24 @@
+---
+description: "Run an opt-in factory job: intake, spec and plan gates, build in a worktree or in place, reviews, approval, merge (local, or a merge request on the forge)"
+argument-hint: "[--in-place] <feature request> | start [--in-place] <request | KEY | slug | job-id> | approve <job-id> | rework <job-id> <note> | abandon <job-id> | status [--all] | watch [--all] | archive [--all] [--dry-run] | prune [--all] [--abandoned] [--dry-run]"
+---
+
+# Factory
+
+## Agent Dispatch
+
+> **Run in the main session.** The orchestrator dispatches these agents; they cannot dispatch others.
+
+| Agent | When to use |
+|-------|-------------|
+| `factory-spec-writer` | Spec stage (`spec` mode) writes `spec.md`; plan stage (`plan` mode) writes `plan.md` and `tasks.md` |
+| `factory-builder` | Build, repair, and rework: writes `build.md` in the job folder; its code goes in the build location |
+| `factory-reviewer-code` | Review round, `code` lens |
+| `factory-reviewer-security` | Review round, `security` lens |
+| `factory-reviewer-ux` | Review round, `ux` lens (opt-in) |
+| `factory-reviewer-ui` | Review round, `ui` lens (opt-in) |
+| `factory-approver` | Approval gate: writes `decision.md` |
+
+Dispatch each agent by its kebab-case name, as in the first column. Copilot may show a display name; pick the agent with that name.
+
+**CRITICAL: READ:** [.claude/prompt-snippets/factory.md](../../.claude/prompt-snippets/factory.md)

package/src/repo/.github/agents/factory-approver.agent.md

@@ -0,0 +1,11 @@
+---
+name: Factory Approver
+description: "Decide whether a factory job is approved for merge or escalated to a human, checking history, final diff, a spot-checked criterion, a dry-run merge, and escalation triggers. Dispatched by the factory orchestrator."
+tools: ["read", "search", "edit", "runInTerminal", "terminalLastCommand"]
+---
+
+# Factory Approver Agent
+
+Decide whether a factory job is approved for merge or escalated to a human.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-approver.md](../../.claude/agents-snippets/factory-approver.md)

package/src/repo/.github/agents/factory-builder.agent.md

@@ -0,0 +1,11 @@
+---
+name: Factory Builder
+description: "Build a factory job's feature inside its git worktree, following TDD, and log results in build.md. Runs in build, repair, or rework mode. Dispatched by the factory orchestrator."
+tools: ["read", "search", "edit", "runInTerminal", "terminalLastCommand"]
+---
+
+# Factory Builder Agent
+
+Build a factory job's feature inside its git worktree, following TDD, and log results in build.md.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-builder.md](../../.claude/agents-snippets/factory-builder.md)

package/src/repo/.github/agents/factory-reviewer-code.agent.md

@@ -0,0 +1,11 @@
+---
+name: Factory Reviewer Code
+description: "Review a factory job's branch for correctness, simplicity, reuse, conventions, and docs, and run the project's checks. Dispatched by the factory orchestrator."
+tools: ["read", "search", "edit", "runInTerminal", "terminalLastCommand"]
+---
+
+# Factory Reviewer (Code) Agent
+
+Review a factory job's branch for correctness, simplicity, reuse, conventions, and docs, and run the project's checks.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-reviewer-code.md](../../.claude/agents-snippets/factory-reviewer-code.md)

package/src/repo/.github/agents/factory-reviewer-security.agent.md

@@ -0,0 +1,11 @@
+---
+name: Factory Reviewer Security
+description: "Audit a factory job's branch diff for security problems in a fresh context. Dispatched by the factory orchestrator."
+tools: ["read", "search", "edit", "runInTerminal", "terminalLastCommand"]
+---
+
+# Factory Reviewer (Security) Agent
+
+Audit a factory job's branch diff for security problems in a fresh context.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-reviewer-security.md](../../.claude/agents-snippets/factory-reviewer-security.md)

package/src/repo/.github/agents/factory-reviewer-ui.agent.md

@@ -0,0 +1,11 @@
+---
+name: Factory Reviewer UI
+description: "Review a factory job's feature at its build location for design-system consistency, spacing, typography, contrast, and responsive layout, without signing in or writing to real services. Dispatched by the factory orchestrator."
+tools: ["read", "search", "edit", "runInTerminal", "terminalLastCommand"]
+---
+
+# Factory Reviewer (UI) Agent
+
+Review a factory job's feature at its build location for design-system consistency, spacing, typography, contrast, and responsive layout, without signing in or writing to real services.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-reviewer-ui.md](../../.claude/agents-snippets/factory-reviewer-ui.md)

package/src/repo/.github/agents/factory-reviewer-ux.agent.md

@@ -0,0 +1,11 @@
+---
+name: Factory Reviewer UX
+description: "Review a factory job's feature at its build location for flows, states, copy, accessibility, and mobile, without signing in or writing to real services. Dispatched by the factory orchestrator."
+tools: ["read", "search", "edit", "runInTerminal", "terminalLastCommand"]
+---
+
+# Factory Reviewer (UX) Agent
+
+Review a factory job's feature at its build location for flows, states, copy, accessibility, and mobile, without signing in or writing to real services.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-reviewer-ux.md](../../.claude/agents-snippets/factory-reviewer-ux.md)

package/src/repo/.github/agents/factory-spec-writer.agent.md

@@ -0,0 +1,11 @@
+---
+name: Factory Spec Writer
+description: "Write a testable spec.md for a factory job from a feature request, after inspecting the real code. Dispatched by the factory orchestrator."
+tools: ["read", "search", "edit", "runInTerminal", "terminalLastCommand"]
+---
+
+# Factory Spec Writer Agent
+
+Write a testable spec.md for a factory job from a feature request, after inspecting the real code.
+
+**CRITICAL: READ:** [.claude/agents-snippets/factory-spec-writer.md](../../.claude/agents-snippets/factory-spec-writer.md)

package/src/repo/.github/prompts/factory.prompt.md

@@ -0,0 +1,25 @@
+---
+description: "Run an opt-in factory job: intake, spec and plan gates, build in a worktree or in place, reviews, approval, merge (local, or a merge request on the forge)"
+tools: ["agent", "edit", "search", "read", "runInTerminal", "terminalLastCommand"]
+argument-hint: "[--in-place] <feature request> | start [--in-place] <request | KEY | slug | job-id> | approve <job-id> | rework <job-id> <note> | abandon <job-id> | status [--all] | watch [--all] | archive [--all] [--dry-run] | prune [--all] [--abandoned] [--dry-run]"
+---
+
+# Factory
+
+## Agent Dispatch
+
+> **Run in the main session.** The orchestrator dispatches these agents; they cannot dispatch others.
+
+| Agent | When to use |
+|-------|-------------|
+| `factory-spec-writer` | Spec stage (`spec` mode) writes `spec.md`; plan stage (`plan` mode) writes `plan.md` and `tasks.md` |
+| `factory-builder` | Build, repair, and rework: writes `build.md` in the job folder; its code goes in the build location |
+| `factory-reviewer-code` | Review round, `code` lens |
+| `factory-reviewer-security` | Review round, `security` lens |
+| `factory-reviewer-ux` | Review round, `ux` lens (opt-in) |
+| `factory-reviewer-ui` | Review round, `ui` lens (opt-in) |
+| `factory-approver` | Approval gate: writes `decision.md` |
+
+Dispatch each agent by its kebab-case name, as in the first column. Copilot may show a display name; pick the agent with that name.
+
+**CRITICAL: READ:** [.claude/prompt-snippets/factory.md](../../.claude/prompt-snippets/factory.md).

package/src/repo/.opencode/agents/admin-portal.md

@@ -17,4 +17,4 @@ permissions:
 
 Build administrator portals with RBAC, system dashboards, reporting, analytics, and operational tooling.
 
-@.claude/agents-snippets/admin-portal.md
+Read and follow `.claude/agents-snippets/admin-portal.md` before performing this role.

package/src/repo/.opencode/agents/api-specialist.md

@@ -17,4 +17,4 @@ permissions:
 
 Design and implement API architecture, documentation, and developer experience.
 
-@.claude/agents-snippets/api-specialist.md
+Read and follow `.claude/agents-snippets/api-specialist.md` before performing this role.

package/src/repo/.opencode/agents/backend-architect.md

@@ -17,4 +17,4 @@ permissions:
 
 Design APIs, databases, and server-side architecture.
 
-@.claude/agents-snippets/backend-architect.md
+Read and follow `.claude/agents-snippets/backend-architect.md` before performing this role.

package/src/repo/.opencode/agents/documenter.md

@@ -17,4 +17,4 @@ permissions:
 
 Analyze codebases and create comprehensive documentation.
 
-@.claude/agents-snippets/documenter.md
+Read and follow `.claude/agents-snippets/documenter.md` before performing this role.

package/src/repo/.opencode/agents/factory-approver.md

@@ -0,0 +1,20 @@
+---
+description: "Decide whether a factory job is approved for merge or escalated to a human, checking history, final diff, a spot-checked criterion, a dry-run merge, and escalation triggers. Dispatched by the factory orchestrator."
+mode: subagent
+request:
+  body:
+    temperature: 0.1
+permissions:
+  - action: edit
+    resource: "*"
+    effect: allow
+  - action: shell
+    resource: "*"
+    effect: allow
+---
+
+# Factory Approver Agent
+
+Decide whether a factory job is approved for merge or escalated to a human.
+
+Read and follow `.claude/agents-snippets/factory-approver.md` before performing this role.

package/src/repo/.opencode/agents/factory-builder.md

@@ -0,0 +1,20 @@
+---
+description: "Build a factory job's feature inside its git worktree, following TDD, and log results in build.md. Runs in build, repair, or rework mode. Dispatched by the factory orchestrator."
+mode: subagent
+request:
+  body:
+    temperature: 0.1
+permissions:
+  - action: edit
+    resource: "*"
+    effect: allow
+  - action: shell
+    resource: "*"
+    effect: allow
+---
+
+# Factory Builder Agent
+
+Build a factory job's feature inside its git worktree, following TDD, and log results in build.md.
+
+Read and follow `.claude/agents-snippets/factory-builder.md` before performing this role.

package/src/repo/.opencode/agents/factory-reviewer-code.md

@@ -0,0 +1,20 @@
+---
+description: "Review a factory job's branch for correctness, simplicity, reuse, conventions, and docs, and run the project's checks. Dispatched by the factory orchestrator."
+mode: subagent
+request:
+  body:
+    temperature: 0.1
+permissions:
+  - action: edit
+    resource: "*"
+    effect: allow
+  - action: shell
+    resource: "*"
+    effect: allow
+---
+
+# Factory Reviewer (Code) Agent
+
+Review a factory job's branch for correctness, simplicity, reuse, conventions, and docs, and run the project's checks.
+
+Read and follow `.claude/agents-snippets/factory-reviewer-code.md` before performing this role.

package/src/repo/.opencode/agents/factory-reviewer-security.md

@@ -0,0 +1,20 @@
+---
+description: "Audit a factory job's branch diff for security problems in a fresh context. Dispatched by the factory orchestrator."
+mode: subagent
+request:
+  body:
+    temperature: 0.1
+permissions:
+  - action: edit
+    resource: "*"
+    effect: allow
+  - action: shell
+    resource: "*"
+    effect: allow
+---
+
+# Factory Reviewer (Security) Agent
+
+Audit a factory job's branch diff for security problems in a fresh context.
+
+Read and follow `.claude/agents-snippets/factory-reviewer-security.md` before performing this role.

package/src/repo/.opencode/agents/factory-reviewer-ui.md

@@ -0,0 +1,20 @@
+---
+description: "Review a factory job's feature at its build location for design-system consistency, spacing, typography, contrast, and responsive layout, without signing in or writing to real services. Dispatched by the factory orchestrator."
+mode: subagent
+request:
+  body:
+    temperature: 0.1
+permissions:
+  - action: edit
+    resource: "*"
+    effect: allow
+  - action: shell
+    resource: "*"
+    effect: allow
+---
+
+# Factory Reviewer (UI) Agent
+
+Review a factory job's feature at its build location for design-system consistency, spacing, typography, contrast, and responsive layout, without signing in or writing to real services.
+
+Read and follow `.claude/agents-snippets/factory-reviewer-ui.md` before performing this role.

package/src/repo/.opencode/agents/factory-reviewer-ux.md

@@ -0,0 +1,20 @@
+---
+description: "Review a factory job's feature at its build location for flows, states, copy, accessibility, and mobile, without signing in or writing to real services. Dispatched by the factory orchestrator."
+mode: subagent
+request:
+  body:
+    temperature: 0.1
+permissions:
+  - action: edit
+    resource: "*"
+    effect: allow
+  - action: shell
+    resource: "*"
+    effect: allow
+---
+
+# Factory Reviewer (UX) Agent
+
+Review a factory job's feature at its build location for flows, states, copy, accessibility, and mobile, without signing in or writing to real services.
+
+Read and follow `.claude/agents-snippets/factory-reviewer-ux.md` before performing this role.

package/src/repo/.opencode/agents/factory-spec-writer.md

@@ -0,0 +1,20 @@
+---
+description: "Write a testable spec.md for a factory job from a feature request, after inspecting the real code. Dispatched by the factory orchestrator."
+mode: subagent
+request:
+  body:
+    temperature: 0.1
+permissions:
+  - action: edit
+    resource: "*"
+    effect: allow
+  - action: shell
+    resource: "*"
+    effect: allow
+---
+
+# Factory Spec Writer Agent
+
+Write a testable spec.md for a factory job from a feature request, after inspecting the real code.
+
+Read and follow `.claude/agents-snippets/factory-spec-writer.md` before performing this role.

package/src/repo/.opencode/agents/feature-builder.md

@@ -20,4 +20,4 @@ permissions:
 
 Coordinate end-to-end feature development using subagents for planning, implementation, and review.
 
-@.claude/agents-snippets/feature-builder.md
+Read and follow `.claude/agents-snippets/feature-builder.md` before performing this role.

package/src/repo/.opencode/agents/frontend-developer.md

@@ -17,4 +17,4 @@ permissions:
 
 Build user interfaces, implement components, handle state management, and optimize frontend performance.
 
-@.claude/agents-snippets/frontend-developer.md
+Read and follow `.claude/agents-snippets/frontend-developer.md` before performing this role.

package/src/repo/.opencode/agents/green.md

@@ -17,4 +17,4 @@ permissions:
 
 Write minimal code to make failing tests pass. Part of the TDD red-green-refactor cycle.
 
-@.claude/agents-snippets/green.md
+Read and follow `.claude/agents-snippets/green.md` before performing this role.