How do I install the Review Gate skill?

Run npx skillmds@latest add jajabong/review-gate in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Review Gate skill do?

Layered code quality gate by risk (L1/L2/L3). It is listed under Coding & Dev Tools on SkillMD.

Is Review Gate safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: executes scripts, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Review Gate?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Review Gate free to use?

Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.

Who published Review Gate?

jajabong (@jajabong) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Review Gate by jajabong — Agent Skill

Name: Review Gate
Rating: 4.2 (5 reviews)
Author: jajabong

Review Gate — Layered Code Quality Gate

Queen-mode 的分层代码质量门。Codex 实现后，以风险匹配 L1 确定性检查、L2 OpenCode 独立 review、必要时 L3 Pi/Anchor 复审；Queen 只读结构化摘要和证据。

When to use

Codex 或其他实现 agent 完成代码改动后
用户要求 code review / quality gate / security review
多文件功能、业务逻辑、API、依赖或配置变化
高风险 auth/crypto/schema/concurrency/production 变更

Native tools and fleet

使用 Hermes 原生工具：terminal、read_file、search_files、skill_view、todo、delegate_task、execute_code。可复用 queen-dispatch，但 reviewer 与实现者必须隔离；同一 reviewer 不得修改并批准自己的改动。

CLI discovery — 每次运行先做

不要硬编码未经本机验证的参数。先运行：

opencode run --help
pi --help
codex exec --help
codex review --help

当前本机已验证的调用形态：

# Implementation: writable sandbox
codex exec -C <project> -s workspace-write --skip-git-repo-check --ephemeral "<goal>"

# L2: OpenCode supports --dir and --format json; it does NOT support --allow-read.
# Read-only is enforced by prompt and by omitting --auto.
opencode run --dir <project> -m opencode/deepseek-v4-flash-free \
  --format json "<review prompt>"

# L3: Pi has explicit read-only built-in tool allowlist.
pi -p --provider anchor --model anchor \
  --tools read,grep,find,ls --no-session "<review prompt>"

CLI help 变化时，更新调用方式；不得继续使用失效参数。

Artifact contract

所有产物写到：

~/.hermes/artifacts/review/<run_id>/
├── manifest.json
├── implementation-summary.md
├── l1.json
├── l1.log
├── l2-review.json 或 l2-review.md
├── l3-review.json 或 l3-review.md
└── decision.md

用 scripts/review_gate.py init 创建目录和 manifest；用 classify 做风险分类；用 validate 检查 schema；用 route 查看应运行的层级。

manifest.json required fields

run_id
project_root
goal
acceptance_criteria
base_ref
head_ref
changed_files
risk_level
risk_reasons
started_at
completed_at
status

L2 finding schema

{
  "severity": "blocker|high|medium|low|info",
  "category": "spec|correctness|security|performance|concurrency|compatibility|testing|maintainability",
  "title": "...",
  "evidence": ["path/to/file.py:42"],
  "impact": "...",
  "recommendation": "...",
  "confidence": 0.0
}

L2 报告还必须包含：

verdict
findings
commands_reviewed
tests_missing
escalation_required
escalation_reasons

无 path:line 证据的 finding 必须降为 info。

L3 report additions

reviewed_l2_findings
confirmed_findings
rejected_findings
new_findings
critical_invariants
final_recommendation

Risk classification

LOW

文档、注释、格式
局部测试补充
无行为变化的小重构

Route：L1 必须；L2 单路快速 review；不启动 L3。

MEDIUM

普通业务逻辑
多文件功能
API 内部实现变化
新依赖或配置变化

Route：L1 + 单路完整 L2；L3 仅在冲突、证据不足或 high finding 时升级。

HIGH

auth / authorization / crypto / secrets / 支付 / 计费
migration / schema / 数据删除 / 不可逆操作
并发 / 锁 / 事务 / 缓存一致性 / 分布式系统
远程命令执行 / 文件权限 / 网络边界 / 用户输入执行
public API / 协议 / 持久化格式 / 向后兼容性变化
production hotfix / release blocker
无法完整测试的生产路径
L1 缺失关键验证
L2 blocker/high、结论冲突、低置信度或明确请求升级

Route：L1 + L2 + L3。

Agent 数量随风险和模块独立性增加，不固定三路 swarm。LOW 不运行多 reviewer 共识；多个 reviewer 不得重复读取同一完整 diff。

Workflow

0. Learning-loop preflight

陌生框架、协议、安全机制或项目领域：

skills_list() 查本地 skill
未命中则 skill_view("learning-loop")
从官方文档和高质量 GitHub 项目提取可证伪验收条件
检查 license、活跃度、兼容性、安全边界；不要直接复制

1. Scope and manifest

先用 shell 获取范围，不把完整 stdout 塞入对话：

git -C <project> diff --stat <base>...<head>
git -C <project> diff --name-only <base>...<head>

创建 run：

python3 ~/.hermes/skills/review-gate/scripts/review_gate.py init \
  --project-root <project> --goal "<goal>" \
  --acceptance "<criterion>" --base-ref <base> --head-ref <head> \
  --changed-file path/a.py --changed-file path/b.py

2. Implementation — Codex

使用 workspace-write 或本机 codex exec --help 显示的等价安全模式。实现 agent 必须把简短摘要写入 implementation-summary.md，包含 files changed、关键决策、已知限制。Codex 自带 review 只算实现者自检，不能代替 L2/L3。

3. L1 — deterministic gate

先读项目 AGENTS.md、README、package scripts、pyproject.toml、Makefile、CI 配置，识别真实命令。按项目适用性运行 targeted/full tests、lint、typecheck、build、git diff --check、已有安全扫描。

完整日志写 l1.log；摘要写 l1.json。L1 失败立即回派原实现 agent，不进入 L2。

4. L2 — independent OpenCode review

默认单 reviewer，只读，不修改代码。只传：目标/验收、项目根、diff 范围、L1 摘要、重点 path:line。OpenCode 当前支持 --format json，优先收集 JSON event stream，再让 reviewer 将最终结构化报告写到 artifact；若不能可靠输出 JSON，写 Markdown。

Review：spec、correctness、边界条件、回归、错误/资源处理、测试质量、安全、性能、并发、兼容性、无关改动、过度设计。

5. Escalation decision

以下任一条件触发 L3：HIGH 分类；L1 缺关键验证；L2 blocker/high；证据冲突；低置信度；reviewer 要求升级；用户明确要求 security/architecture/deep review。

6. L3 — Pi/Anchor read-only

使用本机已验证的只读工具白名单：read,grep,find,ls。不启用 edit/write/bash。L3 只验证 L2 高风险 finding、关键不变量、威胁/失败模型、测试缺口、可交付性，不重新实现。

7. Queen decision

Queen 只读：implementation summary、changed files、L1 summary、L2 findings、L3 report（若有）、最终 diff 摘要。

PASS：无 blocker/high，所有必需验证通过
PASS_WITH_NOTES：仅 non-blocking medium/low，列出技术债
CHANGES_REQUIRED：可修复 blocker/high 或验证失败
BLOCKED：缺凭据、环境、需求决策或无法验证

问题回派原实现 agent；只传未解决 findings。受影响的 L1/L2 重跑，最多两轮；仍失败则报告用户。

Token rules

先 diff stat / changed-file list / targeted context
reviewer 按文件或模块分片，禁止重复读全仓库
完整日志落盘，Queen 只收必要证据摘要
每个 finding 必须带 path:line；否则降为 info
无风险信号不启动 L3
修复轮只传 unresolved findings
外部 agent final 简短，详细证据写 artifact
Queen 不把 worker stdout 原样塞回对话

Verification

python3 ~/.hermes/skills/software-development/review-gate/scripts/test_review_gate.py
hermes skills list | grep review-gate

Dispatcher integration (L1 + L2)

Use queen-dispatch to run review-gate without putting LLM in the scheduler loop.

Canonical DAG:

implement (codex write) — optional if code already changed
l1_collect (shell) — deterministic checks → ~/.hermes/artifacts/review/<run_id>/
l2-review (opencode read_only) — independent review
l2_collect (shell) — normalize opencode JSONL → l2-review.json + decision.md

Scripts:

python3 ~/.hermes/skills/software-development/review-gate/scripts/l1_collect.py   --project-root <project> --run-id <id> --goal "..."   --acceptance "..." --changed-file path.py   --risk-level MEDIUM --command "python3 -m pytest -q"

python3 ~/.hermes/skills/software-development/review-gate/scripts/l2_from_opencode.py   --run-id <id>   --stdout ~/.hermes/artifacts/queen/<dispatch_run>/tasks/l2-review/stdout.log

Example plan:

~/.hermes/skills/queen-dispatch/scripts/dispatcher.py   --plan ~/.hermes/skills/queen-dispatch/examples/review-gate-l1-l2-plan.json --dry-run

Rules:

L1 failure blocks L2 (on_failure=block)
L2 is always read_only; never pass --auto to opencode
L3 is not in this default plan; escalate only when route/risk says HIGH
Queen reads status.json + ~/.hermes/artifacts/review/<run_id>/{l1.json,l2-review.json,decision.md}

Dispatcher integration (HIGH → Pi L3)

For HIGH risk, extend the L1+L2 plan with:

l3-pi-review (engine=pi, role=review, execution_mode=read_only)
l3-collect (engine=shell) → l3-review.json + final decision.md

The dispatcher forces Pi review tasks to:

pi-anchor -p --provider anchor --model anchor --mode json --no-session   --tools read,grep,find,ls "<L3 prompt>"

Pi L3 reviews L2 findings and critical invariants only. It must not re-implement.

Normalize output:

python3 ~/.hermes/skills/software-development/review-gate/scripts/l3_from_pi.py   --run-id <id>   --stdout ~/.hermes/artifacts/queen/<dispatch_run>/tasks/l3-pi-review/stdout.log

Example: ~/.hermes/skills/queen-dispatch/examples/review-gate-high-l3-plan.json.

Review Gate

File contents

Review Gate — Layered Code Quality Gate

When to use

Native tools and fleet

CLI discovery — 每次运行先做

Artifact contract

manifest.json required fields

L2 finding schema

L3 report additions

Risk classification

LOW

MEDIUM

HIGH

Workflow

0. Learning-loop preflight

1. Scope and manifest

2. Implementation — Codex

3. L1 — deterministic gate

4. L2 — independent OpenCode review

5. Escalation decision

6. L3 — Pi/Anchor read-only

7. Queen decision

Token rules

Verification

Dispatcher integration (L1 + L2)

Dispatcher integration (HIGH → Pi L3)

Frequently asked questions

Review Gate

File contents

Review Gate — Layered Code Quality Gate

When to use

Native tools and fleet

CLI discovery — 每次运行先做

Artifact contract

manifest.json required fields

L2 finding schema

L3 report additions

Risk classification

LOW

MEDIUM

HIGH

Workflow

0. Learning-loop preflight

1. Scope and manifest

2. Implementation — Codex

3. L1 — deterministic gate

4. L2 — independent OpenCode review

5. Escalation decision

6. L3 — Pi/Anchor read-only

7. Queen decision

Token rules

Verification

Dispatcher integration (L1 + L2)

Dispatcher integration (HIGH → Pi L3)

Related skills

Frequently asked questions

How do I install the Review Gate skill?

What does the Review Gate skill do?

Is Review Gate safe to use?

Which AI agents work with Review Gate?

Is Review Gate free to use?

Who published Review Gate?