Skip to content

Claude/context aware review pl gx t #22

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Chachamaru127 merged 5 commits into from
Jan 26, 2026
Merged

Claude/context aware review pl gx t #22

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
81138ef
feat: make /harness-review context-aware with plan/scope experts
claude Jan 26, 2026
9f3441d
fix(PR4): resolve 4/8 experts contradiction and add plan/scope mode docs
Chachamaru127 Jan 26, 2026
0009869
fix(PR4): complete removal of 8-expert references, align all docs
Chachamaru127 Jan 26, 2026
3cac72d
fix(PR4): align all docs to 4-experts-per-review-type architecture
Chachamaru127 Jan 26, 2026
a1dfc56
chore: merge main and resolve version conflicts (2.12.4)
Chachamaru127 Jan 26, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion .claude-plugin/plugin.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
{
"name": "claude-code-harness",
"version": "2.12.1",
"version": "2.12.4",
"version": "2.12.4",
"version": "2.12.4",
"description": "Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.",
"author": {
"name": "Chachamaru",
Expand Down
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@ English | [日本語](README_ja.md)
Claude Harness runs Claude Code in an autonomous **Plan → Work → Review** cycle,
catching mistakes before they ship.

[![Version: 2.12.1](https://img.shields.io/badge/version-2.12.1-blue.svg)](VERSION)
[![Version: 2.12.4](https://img.shields.io/badge/version-2.12.4-blue.svg)](VERSION)
[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE.md)
[![Claude Code](https://img.shields.io/badge/Claude_Code-v2.1.6+-purple.svg)](docs/CLAUDE_CODE_COMPATIBILITY.md)

Expand Down
2 changes: 1 addition & 1 deletion VERSION
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
2.12.1
2.12.4
40 changes: 30 additions & 10 deletions commands/core/harness-review.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
---
description: Code review (multi-perspective security/performance/quality)
description-en: Code review (multi-perspective security/performance/quality)
description: Multi-perspective review (auto-detects: code, plan, scope based on context)
description-en: Multi-perspective review (auto-detects: code, plan, scope based on context)
context: fork
hooks:
- event: PreCommandInvoke
Expand All @@ -9,21 +9,41 @@ hooks:
once: true
---

# /harness-review - Code Review (Solo Mode)
# /harness-review - Multi-Perspective Review

Checks the quality of created code.
Analyzes from multiple perspectives and suggests improvements.
Reviews your work from multiple perspectives. **Auto-detects what to review based on context.**

---

## 🎯 Context-Aware Review

This command automatically detects what to review based on your recent activity:

| Recent Activity | Review Type | 4 Perspectives |
|-----------------|-------------|----------------|
| After `/plan-with-agent` | Plan Review | Clarity, Feasibility, Dependencies, Acceptance |
| After `/work` | Code Review | Security, Performance, Quality, Accessibility |
| After adding tasks to Plans.md | Scope Review | Scope-creep, Priority, Feasibility, Impact |

### Usage

```bash
/harness-review # Auto-detect from context
/harness-review code # Force code review
/harness-review plan # Force plan review
/harness-review scope # Force scope analysis
```

---

## 💡 VibeCoder Usage Guide

**This command is designed so you can receive high-quality code review without technical knowledge.**
**This command is designed so you can receive high-quality review without technical knowledge.**

- ✅ Auto-detect security issues
- ✅ Suggest performance improvements
- ✅ Auto-check code quality
- ✅ Verify accessibility compliance
- ✅ Auto-detect what needs review
- ✅ Multi-perspective analysis (4 experts)
- ✅ Clear actionable feedback
- ✅ Works for code, plans, and scope

**Important for contract development**: You can submit review results as a report to reassure clients

Expand Down
27 changes: 11 additions & 16 deletions commands/core/work.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -131,8 +131,8 @@ tail -20 .claude/state/session.events.jsonl
┌─────────────────────────────────────────────────────────┐
│ Phase 2: Cross-review │
├─────────────────────────────────────────────────────────┤
│ Codex available: Codex 8-parallel expert review │
│ Codex not set: Fall back to normal review (review skill) │
│ Codex available: Codex 4-parallel expert review │
│ Codex not set: Fall back to normal review (harness-review) │
│ ※Detects issues missed by self-review │
│ ※Additional issues → Return that task to Phase 1 │
└─────────────────────────────────────────────────────────┘
Expand Down Expand Up @@ -269,11 +269,11 @@ Determine review mode:
- Otherwise → Fall back to normal review (default)
↓
Codex mode:
- Codex 8-parallel expert review
- Simultaneous review from 8 expert perspectives
- Codex 4-parallel expert review (per review type)
- Simultaneous review from 4 expert perspectives
↓
Normal review mode:
- Execute review skill
- Execute harness-review skill
- Check security/performance/quality/accessibility
↓
Extract additional issues:
Expand All @@ -283,18 +283,13 @@ Extract additional issues:
No issues → Phase 3
```

**Review perspectives in Codex mode (8 parallel)**:
**Review perspectives in Codex mode (4 parallel per review type)**:

| # | Expert | Perspective |
|---|--------|-------------|
| 1 | Security | Vulnerabilities, auth, input validation |
| 2 | Performance | N+1, memory leaks, rendering |
| 3 | Maintainability | Readability, naming, structure |
| 4 | Compatibility | API compatibility, regression risk |
| 5 | Accessibility | a11y, keyboard navigation |
| 6 | Type Safety | Type definitions, any avoidance |
| 7 | Error Handling | Error handling, fallbacks |
| 8 | Best Practices | Framework conventions, patterns |
| Review Type | Experts |
|-------------|---------|
| **Code Review** | Security, Performance, Quality, Accessibility |
| **Plan Review** | Clarity, Feasibility, Dependencies, Acceptance |
| **Scope Review** | Scope-creep, Priority, Feasibility, Impact |

### Phase 3: Integrated Commit

Expand Down
49 changes: 35 additions & 14 deletions opencode/commands/core/harness-review.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,28 +1,49 @@
---
description: Code review (multi-perspective security/performance/quality)
description: Multi-perspective review (auto-detects: code, plan, scope based on context)
description-en: Multi-perspective review (auto-detects: code, plan, scope based on context)
context: fork
hooks:
- event: PreCommandInvoke
type: command
command: "${CLAUDE_PLUGIN_ROOT}/scripts/check-codex.sh"
once: true
hooks:
- event: PreCommandInvoke
type: command
command: "${CLAUDE_PLUGIN_ROOT}/scripts/check-codex.sh"
once: true
---

# /harness-review - Multi-Perspective Review

Reviews your work from multiple perspectives. **Auto-detects what to review based on context.**

---

# /harness-review - Code Review (Solo Mode)
## 🎯 Context-Aware Review

This command automatically detects what to review based on your recent activity:

| Recent Activity | Review Type | 4 Perspectives |
|-----------------|-------------|----------------|
| After `/plan-with-agent` | Plan Review | Clarity, Feasibility, Dependencies, Acceptance |
| After `/work` | Code Review | Security, Performance, Quality, Accessibility |
| After adding tasks to Plans.md | Scope Review | Scope-creep, Priority, Feasibility, Impact |

Checks the quality of created code.
Analyzes from multiple perspectives and suggests improvements.
### Usage

```bash
/harness-review # Auto-detect from context
/harness-review code # Force code review
/harness-review plan # Force plan review
/harness-review scope # Force scope analysis
```

---

## 💡 VibeCoder Usage Guide

**This command is designed so you can receive high-quality code review without technical knowledge.**
**This command is designed so you can receive high-quality review without technical knowledge.**

- ✅ Auto-detect security issues
- ✅ Suggest performance improvements
- ✅ Auto-check code quality
- ✅ Verify accessibility compliance
- ✅ Auto-detect what needs review
- ✅ Multi-perspective analysis (4 experts)
- ✅ Clear actionable feedback
- ✅ Works for code, plans, and scope

**Important for contract development**: You can submit review results as a report to reassure clients

Expand Down
27 changes: 11 additions & 16 deletions opencode/commands/core/work.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,8 +130,8 @@ tail -20 .claude/state/session.events.jsonl
┌─────────────────────────────────────────────────────────┐
│ Phase 2: Cross-review │
├─────────────────────────────────────────────────────────┤
│ Codex available: Codex 8-parallel expert review │
│ Codex not set: Fall back to normal review (review skill) │
│ Codex available: Codex 4-parallel expert review │
│ Codex not set: Fall back to normal review (harness-review) │
│ ※Detects issues missed by self-review │
│ ※Additional issues → Return that task to Phase 1 │
└─────────────────────────────────────────────────────────┘
Expand Down Expand Up @@ -268,11 +268,11 @@ Determine review mode:
- Otherwise → Fall back to normal review (default)
↓
Codex mode:
- Codex 8-parallel expert review
- Simultaneous review from 8 expert perspectives
- Codex 4-parallel expert review (per review type)
- Simultaneous review from 4 expert perspectives
↓
Normal review mode:
- Execute review skill
- Execute harness-review skill
- Check security/performance/quality/accessibility
↓
Extract additional issues:
Expand All @@ -282,18 +282,13 @@ Extract additional issues:
No issues → Phase 3
```

**Review perspectives in Codex mode (8 parallel)**:
**Review perspectives in Codex mode (4 parallel per review type)**:

| # | Expert | Perspective |
|---|--------|-------------|
| 1 | Security | Vulnerabilities, auth, input validation |
| 2 | Performance | N+1, memory leaks, rendering |
| 3 | Maintainability | Readability, naming, structure |
| 4 | Compatibility | API compatibility, regression risk |
| 5 | Accessibility | a11y, keyboard navigation |
| 6 | Type Safety | Type definitions, any avoidance |
| 7 | Error Handling | Error handling, fallbacks |
| 8 | Best Practices | Framework conventions, patterns |
| Review Type | Experts |
|-------------|---------|
| **Code Review** | Security, Performance, Quality, Accessibility |
| **Plan Review** | Clarity, Feasibility, Dependencies, Acceptance |
| **Scope Review** | Scope-creep, Priority, Feasibility, Impact |

### Phase 3: Integrated Commit

Expand Down
6 changes: 3 additions & 3 deletions opencode/skills/codex-review/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ OpenAI Codex CLI を MCP サーバーとして Claude Code に統合し、コー
|------|------|
| **MCP セットアップ** | See [references/codex-mcp-setup.md](references/codex-mcp-setup.md) |
| **レビュー統合** | See [references/codex-review-integration.md](references/codex-review-integration.md) |
| **最大8並列レビュー** | See [references/codex-parallel-review.md](references/codex-parallel-review.md) |
| **4並列レビュー** | See [references/codex-parallel-review.md](references/codex-parallel-review.md) |

@coderabbitai coderabbitai Bot Jan 26, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🔴 Critical

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
# Check if .claude/memory directory and files exist
echo "=== Checking .claude/memory structure ==="
find .claude/memory -type f 2>/dev/null | head -20

echo ""
echo "=== Searching for 4-parallel or parallel review references in SSOT files ==="
rg -n "4.*並列|4.*expert|並列レビュー" .claude/memory/ 2>/dev/null || echo "No matches found in .claude/memory"

echo ""
echo "=== Searching in decisions.md specifically ==="
if [ -f .claude/memory/decisions.md ]; then
  cat .claude/memory/decisions.md
else
  echo ".claude/memory/decisions.md not found"
fi

echo ""
echo "=== Searching in patterns.md specifically ==="
if [ -f .claude/memory/patterns.md ]; then
  cat .claude/memory/patterns.md
else
  echo ".claude/memory/patterns.md not found"
fi

echo ""
echo "=== Checking for referenced files ==="
ls -la opencode/skills/codex-review/references/codex-parallel-review.md 2>/dev/null || echo "references/codex-parallel-review.md not found"

echo ""
echo "=== Checking for accessibility-expert.md ==="
find opencode -name "*accessibility*" -type f 2>/dev/null | head -10

Repository: Chachamaru127/claude-code-harness

Length of output: 739

🏁 Script executed:

#!/bin/bash
# Check .claude directory existence
echo "=== Checking .claude directory ==="
ls -la .claude 2>/dev/null || echo ".claude directory not found"

echo ""
echo "=== Reading SKILL.md around line 28 ==="
sed -n '20,40p' opencode/skills/codex-review/SKILL.md

echo ""
echo "=== Reading lines 49-53 for expert changes ==="
sed -n '45,60p' opencode/skills/codex-review/SKILL.md

echo ""
echo "=== Reading codex-parallel-review.md ==="
head -50 opencode/skills/codex-review/references/codex-parallel-review.md

Repository: Chachamaru127/claude-code-harness

Length of output: 2858

.claude/memory に SSOT ファイルが見つかりません。アーキテクチャドキュメントとして decisions.md と patterns.md を作成してください。

コーディングガイドラインに従い、opencode/**/*.md への変更は .claude/memory/decisions.md（Why）と .claude/memory/patterns.md（How）を SSOT として記載する必要があります。

以下の内容を記載してください:

  • decisions.md: 「なぜ 4 並列レビューに変更したのか」（背景、意思決定根拠）
  • patterns.md: 「4 並列レビューの実行パターン」（エキスパート定義、MCP 呼び出し手順、codex-parallel-review.md への参照）
🤖 Prompt for AI Agents 
In `@opencode/skills/codex-review/SKILL.md` at line 28, opencode/**/*.md の変更に対して
SSOT が存在しないため、.claude/memory/decisions.md（Why）と
.claude/memory/patterns.md（How）を作成してください; decisions.md に「なぜ 4
並列レビューに変更したのか」という背景と意思決定根拠（利点・トレードオフ・関係者の合意）を明確に記載し、patterns.md に「4
並列レビューの実行パターン」（エキスパートの役割定義、MCP 呼び出し手順、参照として references/codex-parallel-review.md
へのリンクと実践フロー）を具体的な手順として記載してください; 作成後、opencode/skills/codex-review/SKILL.md
の該当箇所にある「4並列レビュー」エントリがこれらの SSOT を参照するように更新してください。


## 実行手順

Expand All @@ -46,11 +46,11 @@ OpenAI Codex CLI を MCP サーバーとして Claude Code に統合し、コー
4. 絶対に1回の呼び出しで複数観点をまとめない

```
✅ 正しい（6エキスパート有効の場合）:
✅ 正しい（Code Reviewの場合、4エキスパート）:
mcp__codex__codex({prompt: security-expert.md})
mcp__codex__codex({prompt: performance-expert.md})
mcp__codex__codex({prompt: quality-expert.md})
... (有効なもののみ並列)
mcp__codex__codex({prompt: accessibility-expert.md})

❌ 間違い:
mcp__codex__codex({prompt: "セキュリティとパフォーマンスと品質をレビューして"})
Expand Down
Loading
Loading