forge-orkes 0.3.20 → 0.4.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "forge-orkes",
-  "version": "0.3.20",
+  "version": "0.4.1",
   "description": "Set up the Forge meta-prompting framework for Claude Code in your project",
   "bin": {
     "create-forge": "./bin/create-forge.js"

package/template/.claude/skills/forge/SKILL.md

@@ -108,6 +108,7 @@ Subagents via `Task` → same precedence.
 | reviewing | sonnet | Audit judgment |
 | quick-tasking | haiku | Speed |
 | discussing | sonnet | Conversation |
+| testing | sonnet | Code gen (author) + audit judgment (analyst) — matches executing/reviewing |
 
 | `current.status` | Route To |
 |-------------------|----------|
@@ -183,7 +184,7 @@ After clear, skills load from disk via "Read Context"/"Pre-Execution Checklist".
 Standard: not_started → [init?] → researching → discussing → planning → executing → verifying → reviewing → complete
 Full:     not_started → [init?] → researching → discussing → architecting → planning → executing → verifying → reviewing → complete
 
-Branches (any tier, on-demand): debugging (stuck) · designing (UI) · securing (auth/data/API)
+Branches (any tier, on-demand): debugging (stuck) · designing (UI) · securing (auth/data/API) · testing (e2e/integration/flake)
 Phase boundaries: `[clear]` recommended between phases to reset context.
 ```
 

package/template/.claude/skills/planning/SKILL.md

@@ -186,6 +186,26 @@ Executor TDD (RED -> GREEN -> REFACTOR) auto-activates.
 - Multi-component integration (key_links)
 - Undefined interfaces (spec after architecting)
 
+### UI Coverage Carve-Out
+
+Step 7 intentionally skips UI — that coverage is owned by `testing` skill (e2e + integration flows).
+
+**Auto-suggest heuristic:** When requirements contain UI signals, prompt user once (pre-code) to invoke `testing`:
+
+Signals (any match):
+- `requirements.yml` description mentions: "UI", "page", "flow", "form", "dashboard", "component", "screen"
+- Tasks in Step 6 have files matching: `src/components/**`, `src/pages/**`, `src/app/**`, `*.tsx`, `*.vue`, `*.svelte`
+- `project.yml` stack includes web framework (Next.js, React, Vue, Svelte, Astro, Remix)
+
+Prompt pattern:
+> *"UI work detected. Invoke `testing` skill for e2e/integration coverage? (yes/no/later)"*
+
+- **yes** — defer to `testing` after planning completes; note in plan frontmatter
+- **no** — document rationale in `context.md` Discretion Areas
+- **later** — surface again at verifying gate if UI tests still missing
+
+Decision captured once, pre-code. Does not block planning.
+
 ## Step 8: Verify Plans
 
 8 dimensions:

package/template/.claude/skills/reviewing/SKILL.md

@@ -315,5 +315,5 @@ pending → dismissed (during triage or later)
 ## Phase Handoff
 
 1. Confirm report + backlog
-2. Set `current.status: complete`
+2. Set `current.status: complete` and `current.completed_at: "<ISO 8601 timestamp>"`
 3. *"Milestone [{name}] complete. Report: `.forge/audits/milestone-{id}-health-report.md`. {N} backlog items. `/forge` or backlog."*

package/template/.forge/templates/state/milestone.yml

@@ -13,7 +13,8 @@ current:
   phase_name: ""                       # Human-readable phase name
   plan: null                           # Current plan number within phase
   task: null                           # Current task number within plan
-  status: not_started                  # not_started | researching | discussing | planning | executing | verifying | auditing | refactoring | complete
+  status: not_started                  # not_started | researching | discussing | planning | executing | verifying | reviewing | complete
+  completed_at: null                    # ISO 8601 timestamp — set when status transitions to complete
 
 progress:
   phases_complete: 0                   # Number of roadmap phases with all tasks done

package/template/CLAUDE.md

@@ -34,7 +34,7 @@ Auto-detects complexity. Override: "Use Quick/Standard/Full tier."
 ### Full (days)
 **Triggers:** new project, major milestone, complex multi-system, architectural decisions
 **Flow:** `researching` → `discussing` → `architecting` → `planning` → `executing` → `verifying` → `reviewing` → done
-**Optional:** `designing` (UI), `securing` (auth/data/API), `debugging` (stuck)
+**Optional:** `designing` (UI), `securing` (auth/data/API), `debugging` (stuck), `testing` (e2e/integration/flake)
 
 ## Skill Routing
 
@@ -52,6 +52,7 @@ Auto-detects complexity. Override: "Use Quick/Standard/Full tier."
 | Small scoped fix | `quick-tasking` | Quick |
 | UI with design system | `designing` | When UI |
 | Security review | `securing` | When auth/data/API |
+| E2E/integration tests + suite audit | `testing` | When UI/flows or flaky suite |
 | Systematic debugging | `debugging` | When stuck |
 | Upgrade Forge files | `upgrading` | On-demand |
 | Cross-session memory | `beads-integration` | When Beads installed |
@@ -103,6 +104,7 @@ models:
 | `executor` | Building + deviation rules | All dev tools | Execution |
 | `verifier` | Goal-backward verification | Read + Bash (tests) | Verification |
 | `reviewer` | Security + architecture + refactoring | Read, Bash, Grep, Glob | Reviewing |
+| `tester` | E2E/integration authoring + suite analysis | Dual-mode: author (Write/Edit/Bash/git) · analyst (Read/Glob/Grep/Bash read-only) | Testing skill |
 
 ## Project Init (First Run)