create-harness-vibe-coding 0.5.1 → 0.6.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-harness-vibe-coding",
-  "version": "0.5.1",
+  "version": "0.6.0",
   "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/agents/reviewer.md

@@ -22,6 +22,7 @@ Rules:
 - Do not write files.
 - Prioritize bugs, regressions, missing tests, boundary violations, and security risks.
 - Findings must include file and line when possible.
+- Flag unsupported factual claims: if a code comment, doc line, or agent output asserts a fact you cannot confirm by reading the referenced file, report it as a "Hallucination Risk" finding.
 - Separate critical/high findings from minor cleanup.
 - If no issues are found, state residual risk and test gaps.
 

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

@@ -0,0 +1,31 @@
+# /wf-review [focus]
+
+Cross-model peer review. Invokes the OTHER agent CLI to review changes from a fresh perspective.
+
+## How it works
+
+1. Detect which runtime we're running under
+2. Prepare context: diff, relevant files, architecture docs, problem description
+3. Pipe to the OTHER CLI for independent review
+4. Synthesize the response
+
+## Required
+
+- Load `wf-review` skill.
+- MUST use `Bash` to invoke the other CLI — never simulate or fake the review.
+- Present the raw review output to the user, then add your own analysis.
+
+## CLI Detection
+
+- If `codex` is available: use `codex exec` for code review
+- If only `claude` is available: use `claude -p` for code review
+- Try `codex exec` first, fall back to `claude -p`
+
+## Flow
+
+```text
+CEO prepares context (diff + architecture docs + focus prompt)
+→ Bash: codex exec "..."  (or claude -p "...")
+→ CEO reads output
+→ CEO presents findings + own analysis
+```

package/templates/common/.claude/commands/wf-max.md

@@ -13,7 +13,7 @@ Enter maximum-parallelism workflow mode with an optional task description. Split
 
 ```text
 intake
--> max-parallel exploration (5-14 read-only agents)
+-> max-parallel exploration (5-10 read-only agents)
 -> synthesis + write-set coloring → dependency graph
 -> wave 1: N parallel implementers (disjoint file claims)
 -> wave 1 review: parallel spec/code/security reviewers

package/templates/common/.claude/skills/subagent-orchestrator/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: subagent-orchestrator
-description: Use when work needs bounded subagent coordination, parallel read-only exploration, independent review gates, broad context partitioning, or controlled handoffs after wf-mode has been selected when applicable.
+description: Use when work needs bounded subagent coordination, parallel read-only exploration, independent review gates, broad context partitioning, or controlled handoffs after wf-mode has been selected.
 ---
 
 # Subagent Orchestrator

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

@@ -25,7 +25,7 @@ intake + 95% confidence gate
 -> bounded implementation
 -> review
 -> verification
--> debugger recovery loop when verification fails (dispatch memory-master after 3 same-class failures)
+-> debugger recovery loop when verification fails (dispatch context-master then memory-master, or use /wf-learn)
 -> context-master session analysis + knowledge extraction
 -> memory-master consolidation
 -> close with evidence

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

@@ -0,0 +1,49 @@
+---
+name: wf-review
+description: Cross-model peer review. Invokes the other agent CLI (Codex or Claude) to independently review changes, architecture, or bug fixes. Use for /wf-review, peer review, second opinion, or when stuck.
+---
+
+# WF Review
+
+Cross-model peer review via the OTHER agent CLI. Fresh eyes on your changes.
+
+## Load
+
+- `Harness/README.md` for project context
+- Current diff or target files
+
+## How It Works
+
+1. **Detect runtime**: Check `which codex` and `which claude`
+2. **Prepare context**: Gather diff (`git diff`), relevant architecture docs, the specific question
+3. **Invoke the OTHER CLI** — the one we're NOT currently running under
+4. **Read and synthesize**: Present the raw output, then add analysis
+
+## CLI Commands
+
+| Current Runtime | Review Command |
+|---|---|
+| Claude Code | `git diff \| codex exec "review prompt"` |
+| Claude Code (commit) | `codex exec "review this commit: $(git log -1 --format=%B)"` |
+| Codex | `git diff \| claude -p "review prompt"` |
+| Either | fallback: try the other CLI, warn if neither available |
+
+## Context to Include
+
+For a good review, pipe or include:
+- `git diff` or `git diff --cached`
+- Relevant `Harness/` docs (architecture.md, domain/ports.md if filled)
+- The specific focus: "find bugs", "critique architecture from 4+ dimensions", "fix this bug", "check for security issues"
+
+## Rules
+
+- Never simulate or fake the review. The Bash tool MUST invoke the other CLI.
+- If both CLIs fail, report the error — don't silently skip.
+- Present the raw review output to the user before adding your own analysis.
+- Distinguish between: the peer's findings (authoritative) and your interpretation (supplementary).
+
+## Return
+
+- Which CLI was used for review
+- Raw review output
+- CEO's synthesis and action items

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-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 `/wf <task>`, `/wf-max [task]`, `/wf-learn`, `/wf-review [focus]`, `wf mode`, `wf max`, `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`.
@@ -27,6 +27,7 @@ Root entry for Claude Code. Keep this file short.
 - If multiple valid approaches exist and the choice affects architecture, scope, stack, or user-facing behavior, present trade-offs instead of picking silently.
 - State assumptions before implementation and record durable assumptions, decisions, blockers, handoffs, and verification evidence in `Harness/tasks/<task-id>/PLAN.md`.
 - If something is unclear, stop. Name what is unclear and ask instead of guessing.
+- Before asserting a fact about the codebase, read the file that proves it. If you cannot cite the file and line, do not assert.
 
 ## 3. Simplicity First
 

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-review](../.claude/skills/wf-review/SKILL.md) — cross-model peer review: invoke the other agent CLI (Codex/Claude) for independent review.
 - [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-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`.
+Routing priority: if a request explicitly says `/wf <task>`, `/wf-max [task]`, `/wf-learn`, `wf mode`, `wf max`, `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 |
 | --- | --- | --- | --- |
@@ -61,6 +61,7 @@ Routing priority: if a request explicitly says `/wf <task>`, `/wf-max [task]`, `
 | 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 peer review | /wf-review, peer review, second opinion, cross-check, stuck | `.claude/skills/wf-review/SKILL.md`, `Harness/README.md` | cross-model review via other CLI (Codex/Claude) |
 | 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 |
@@ -102,6 +103,8 @@ Routing priority: if a request explicitly says `/wf <task>`, `/wf-max [task]`, `
 ```text
 Harness/README.md                  router only
 Harness/MEMORY.md                  resource index
+Harness/PLAN.md                    active project plan
+Harness/SETUP.md                   install/bootstrap contract
 Harness/PROGRESS.md                global task index and cross-task decisions
 Harness/tasks/<id>/PROGRESS.md     per-task progress, phase, heartbeat
 Harness/tasks/<id>/PLAN.md         per-task implementation plan and evidence
@@ -109,8 +112,10 @@ Harness/tasks/_template/           task capsule template (copy to create new tas
 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/skills/wf-review/SKILL.md  cross-model peer review skill
 .claude/commands/wf-max.md         /wf-max slash command bridge
 .claude/commands/learn.md          /wf-learn slash command bridge
+.claude/commands/review.md         /wf-review 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