create-harness-vibe-coding 0.4.3 → 0.5.1

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-harness-vibe-coding",
-  "version": "0.4.3",
+  "version": "0.5.1",
   "description": "Scaffold a 0-1 product harness for AI-assisted research, PRD, planning, architecture, build, test, and feedback loops",
   "type": "module",
   "bin": {

package/templates/common/.claude/commands/learn.md

@@ -0,0 +1,17 @@
+# /wf-learn
+
+Force a memory learning cycle. Dispatches `context-master` to analyze the session, then `memory-master` to consolidate extracted knowledge into `Harness/memory/*` (project-level) and cross-project global memory.
+
+## Required
+
+- Load `wf-learn` skill.
+- MUST dispatch `context-master` first, then `memory-master`.
+- Both agents are read-only reporters; CEO writes the final memory files.
+
+## Flow
+
+```text
+context-master (analyze)
+→ memory-master (consolidate)
+→ CEO writes to Harness/memory/* + global memory
+```

package/templates/common/.claude/skills/wf-learn/SKILL.md

@@ -0,0 +1,46 @@
+---
+name: wf-learn
+description: Use for /wf-learn or when the user wants to force a learning cycle from repeated errors, patterns, or session history. Dispatches context-master → memory-master pipeline to extract and consolidate durable knowledge.
+---
+
+# WF Learn
+
+Force a memory learning cycle. Context-master analyzes, memory-master consolidates. Writes to project-level `Harness/memory/*` and cross-project global memory.
+
+## Load
+
+- `Harness/MEMORY.md`
+- `Harness/memory/tool-usage-reflections.md`
+- `Harness/memory/user-corrections-preferences.md`
+- `Harness/memory/agent-lessons-patterns.md`
+- Current `Harness/PROGRESS.md` for active task context
+
+## Flow
+
+```text
+1. context-master: analyze session, extract patterns
+2. memory-master: categorize + deduplicate + write to memory files
+3. CEO: commit memory files
+```
+
+## Write Targets
+
+| Scope | Path | When |
+|---|---|---|
+| Project | `Harness/memory/tool-usage-reflections.md` | tool/command patterns found |
+| Project | `Harness/memory/user-corrections-preferences.md` | user preferences found |
+| Project | `Harness/memory/agent-lessons-patterns.md` | review/debug lessons found |
+| Global | `<user>/.claude/projects/*/memory/` | cross-project patterns |
+
+## Rules
+
+- Never auto-write without context-master analysis first.
+- Memory-master handles dedup — if existing entry covers the same ground, update instead of creating duplicate.
+- If no new patterns found, report "nothing to learn" — don't force empty writes.
+- Subagents are readers and reporters. CEO writes the final memory files.
+
+## Return
+
+- Files written or updated
+- Patterns extracted (one-line each)
+- Skipped (with reason)

package/templates/common/.claude/skills/wf-mode/SKILL.md

@@ -41,7 +41,7 @@ Rules:
 - If subagents are unavailable, emulate the same roles as separate bounded passes.
 - Do not claim browser/UI acceptance without real-browser evidence from Chrome DevTools, CDP, Playwright, or documented manual browser checks.
 - If `Harness/workflows/browser-e2e.md` is not installed, use `Harness/WF.md#Browser And API Evidence` as the fallback evidence contract or ask the user before adding the optional workflow.
-- If the same failure class happens three times, dispatch `memory-master` to record the failure pattern first, then ask the user with evidence-backed options.
+- Before closeout, dispatch `context-master` then `memory-master` (or use `/wf-learn`) to extract and consolidate lessons. Do not skip — the auto-trigger is unreliable; make this a mandatory gate.
 
 Return:
 

package/templates/common/CLAUDE.md

@@ -11,7 +11,7 @@ Root entry for Claude Code. Keep this file short.
 - `Harness/README.md` is the task router. For every request, check `Harness/README.md#Load By Task`; if a row matches, read and follow those docs before acting.
 - `Harness/PROGRESS.md` is the global task index. Load at session start to see active task and task history.
 - If work spans more than one step, create a task capsule from `Harness/tasks/_template/` and update `Harness/tasks/<task-id>/PROGRESS.md`.
-- Use `/wf <task>`, `/wf-max [task]`, `wf mode`, `workflow mode`, `wk mode`, `Harness/WF.md`, or `Harness/WF-MAX.md` for long, difficult, uncertain, multi-file, or repeated-failure work.
+- Use `/wf <task>`, `/wf-max [task]`, `/wf-learn`, `wf mode`, `workflow mode`, `wk mode`, `Harness/WF.md`, or `Harness/WF-MAX.md` for long, difficult, uncertain, multi-file, or repeated-failure work.
 - Use `subagent-orchestrator` and `Harness/subagents.md` when coordinating multiple subagents.
 - Use `/wf update` to check for and apply scaffold updates from GitHub. See `.claude/skills/wf-update/SKILL.md`.
 - Subagents are readers and reporters. Only the main agent writes to `Harness/tasks/<task-id>/PROGRESS.md` and `Harness/tasks/<task-id>/PLAN.md`.
@@ -63,7 +63,7 @@ Root entry for Claude Code. Keep this file short.
 - **Tool reflection trigger**: record a lightweight reflection when the same tool/use pattern fails 3+ times, or when a better command pattern/environment fix is found. Write it newest-first in `Harness/memory/tool-usage-reflections.md`.
 - **User correction trigger**: record a lightweight preference/correction when the user asks to remember it, or when the user corrects the same assumption/pattern 2+ times. Write it newest-first in `Harness/memory/user-corrections-preferences.md`.
 - **Agent lesson trigger**: record reusable lessons from review/debug loops in `Harness/memory/agent-lessons-patterns.md` when they would prevent recurrence.
-- **WF auto-trigger**: when the same failure class happens 3+ times in a WF recovery loop, dispatch `memory-master` to record the failure pattern to `Harness/memory/agent-lessons-patterns.md` before asking the user.
+- **WF auto-trigger**: before WF closeout, dispatch `context-master` then `memory-master` (or use `/wf-learn`). The old "3x same failure" auto-trigger is unreliable — make this a mandatory closeout gate.
 - **Context threshold trigger**: when context approaches ~85% of the window, dispatch `context-master` to analyze and write a non-blocking compression suggestion to `Harness/tasks/<task-id>/PROGRESS.md#Heartbeat`.
 - **Closeout trigger**: during WF closeout, dispatch `context-master` to extract durable knowledge, then `memory-master` to consolidate into `Harness/memory/*`.
 - Never record secrets, credentials, tokens, or private data.

package/templates/common/MEMORY.md

@@ -29,6 +29,7 @@ Stack-specific agents can be added after the product shape is known.
 - [wf-mode](../.claude/skills/wf-mode/SKILL.md) — long-task workflow: exploration, second plan, implementation, review, verification, heartbeat, and recovery loop.
 - [subagent-orchestrator](../.claude/skills/subagent-orchestrator/SKILL.md) — controller-led subagent orchestration, parallel read-only passes, review gates, and recovery handoffs.
 - [readme-optimizer](../.claude/skills/readme-optimizer/SKILL.md) — README preservation, append-only development sections, structured tables, and approved architecture diagrams.
+- [wf-learn](../.claude/skills/wf-learn/SKILL.md) — force memory learning cycle: context-master → memory-master → project + global memory.
 - [wf-update](../.claude/skills/wf-update/SKILL.md) — GitHub-based incremental harness update, checksum comparison, and safe in-place updates.
 - [wf-max](../.claude/skills/wf-max/SKILL.md) — maximum-parallelism workflow: write-set coloring, wave dispatch, parallel review per dimension.
 

package/templates/common/docs/README.md

@@ -51,7 +51,7 @@ Keywords are retrieval hints, not project facts.
 
 Load the matching row only. Add adjacent docs only when the loaded doc directly names them.
 
-Routing priority: if a request explicitly says `/wf <task>`, `/wf-max [task]`, `wf mode`, `workflow mode`, or `wk mode`, or is long, difficult, uncertain, repeated-failure, migration, architecture-heavy, browser-visible, or broad multi-agent implementation work, choose the WF row first. `wf-mode` MUST then delegate subagent coordination to `subagent-orchestrator`.
+Routing priority: if a request explicitly says `/wf <task>`, `/wf-max [task]`, `/wf-learn`, `wf mode`, `workflow mode`, or `wk mode`, or is long, difficult, uncertain, repeated-failure, migration, architecture-heavy, browser-visible, or broad multi-agent implementation work, choose the WF row first. `wf-mode` MUST then delegate subagent coordination to `subagent-orchestrator`.
 
 | When to Read | Keywords | Load | Output |
 | --- | --- | --- | --- |
@@ -60,6 +60,7 @@ Routing priority: if a request explicitly says `/wf <task>`, `/wf-max [task]`, `
 | Need MVP/spec | PRD, MVP, scope, requirement, acceptance, non-goal | [research/PRD.md](research/PRD.md) | one-page PRD with verifiable acceptance criteria |
 | Need architecture or boundaries | architecture, boundary, layer, domain, port, adapter, dependency | [architecture.md](architecture.md), [domain/ports.md](domain/ports.md) | layer map, ports, constraints |
 | Need WF mode | wf, /wf, wf mode, workflow mode, wk mode, long task, difficult, stuck, repeated failure | [WF.md](WF.md), [PROGRESS.md](PROGRESS.md), the current task `tasks/<id>/PROGRESS.md` and `tasks/<id>/PLAN.md` | exploration plan, second plan, heartbeat, recovery loop; explicit WF/WK loads subagent docs immediately |
+| Need to learn from errors | /wf-learn, wf learn, learn, remember, memory, lesson | [MEMORY.md](MEMORY.md), `.claude/skills/wf-learn/SKILL.md`, `Harness/memory/*` | context-master → memory-master → project + global memory |
 | Need WF Max mode | /wf-max, wf max, maximum parallelism, max parallel | [WF-MAX.md](WF-MAX.md), [WF.md](WF.md), [subagents.md](subagents.md), [dispatch.md](dispatch.md) | max-parallel exploration, write-set coloring, wave dispatch |
 | Adding harness to existing project | existing project, onboarding, migrate, bootstrap, preserve, conflict | [extension.md](extension.md), [PROGRESS.md](PROGRESS.md), root `README.md` and package/CI files | discovered project facts, preserved config, manual registration plan |
 | README optimization | README, docs, quickstart, install docs, architecture diagram, command table, documentation polish | root `README.md`, `.claude/skills/readme-optimizer/SKILL.md`, [PROGRESS.md](PROGRESS.md), [architecture.md](architecture.md) as needed | approved README mode, preserved sections, proposed diff plan |
@@ -109,6 +110,7 @@ Harness/WF.md                      long-task workflow and recovery loop
 Harness/WF-MAX.md                  max-parallelism workflow with wave dispatch
 .claude/skills/wf-max/SKILL.md     max-parallelism skill loader
 .claude/commands/wf-max.md         /wf-max slash command bridge
+.claude/commands/learn.md          /wf-learn slash command bridge
 Harness/lifecycle.md               0-1 product flow
 Harness/subagents.md               controller-led subagent orchestration
 Harness/context-loading.md         dynamic loading and subagent packs

package/templates/common/docs/harness/WF.md

@@ -122,7 +122,7 @@ If verification fails:
 5. Run verifier again.
 6. Repeat until verified or blocked by missing user input/external state.
 
-If the same failure class happens three times, stop blind fixes. Before asking the user, dispatch `memory-master` to record the failure pattern, attempted paths, and root cause hypothesis to `Harness/memory/agent-lessons-patterns.md`. Then present evidence-backed options to the user.
+Before asking the user after repeated failures, dispatch `context-master` then `memory-master` (or use `/wf-learn`) to record the failure pattern, attempted paths, and root cause hypothesis. Present evidence-backed options to the user.
 
 ## Heartbeat Protocol