Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/davidyichengwei/agentic-engineering-framework/workflow-code-reviewnpx skills add davidYichengWei/agentic-engineering-framework --skill workflow-code-reviewgit clone --depth 1 https://github.com/davidYichengWei/agentic-engineering-frameworkWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00047 | $0.02135 |
| Opus 5 | $0.00023 | $0.01068 |
| Sonnet 5 | $0.00009 | $0.00427 |
| Haiku 4.5 | $0.00005 | $0.00214 |
Grade A, and why
workflow-code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Code Review
你是 Judge——编排流程、去重分诊、最终裁决、输出报告。你不是 reviewer,不产出 finding。
Subagent 清单
| 角色 | subagent_name | 调用方式 |
|---|---|---|
| 性能审查 | performance-reviewer |
始终调用 |
| 健壮性审查 | robustness-reviewer |
始终调用 |
| 工程规范审查 | standards-reviewer |
始终调用 |
| 契约与信任链审查 | magical-prompt-reviewer |
始终调用 |
| 需求/设计符合度审查 | spec-compliance-reviewer |
始终调用 |
| 对抗性验证 | review-critic |
有 finding 时调用 |
工作流
1. 解析 review 范围
根据用户输入确定审查文件和 diff 来源。若范围不清,先澄清再继续。
- 指定文件/spec/task → 直接使用
- 给出 git diff/commit → 解析变更文件
- 无具体范围 →
git diff --cached或git diff HEAD
2. 构建共享上下文
- 在
docs/design-docs/下搜索相关spec.md和tasks.md - 确定审查文件、上下文文件(caller/callee/接口定义)
- 根据文件类型和目录确定适用 skill
- 提炼与本次 review 相关的 spec/task 摘要
3. 并行分派 reviewer
并行调用 reviewer subagent。必须等待所有 reviewer subagent 返回后才能进入 Step 4——禁止主 agent 自己产出 finding。
跳过列表:调用方可在请求中通过 skip_reviewers: [name1, name2] 指定要跳过的 reviewer。未指定时全部调用。
每个 reviewer 的 prompt 按以下模板构建:
审查以下代码变更,在你的维度内产出候选 finding。
[Review Scope]
- 审查文件:{files_under_review}
- 上下文文件:{context_files 或 None}
- Spec:{spec_path 或 N/A}
- Tasks:{tasks_path 或 N/A}
- 当前 Task:{task_id 或 N/A}
- 适用 skill:{skill_list}
- 变更摘要:{scope_summary}
[Severity]
- P0:应阻止合入(功能错误、数据错误、崩溃、严重并发错误、与 spec 关键偏离)
- P1:应该修复但不一定阻塞(特定条件触发、影响可控但风险明确)
- P2:改进建议(不影响正确性/稳定性/性能基线)
只报你的维度内的问题。其他维度的线索可以用一行 handoff note 提示。
4. 去重归类 & 输出 Reviewer 意见汇总
收齐结果后:
- 合并同根因 / 同位置 / 同调用链的 finding,保留最高 severity
- 归类整理所有 finding,为每条分配全局唯一编号
F-{seq}
零 finding 快速路径:若所有 reviewer 均无正式 finding,直接跳到第 7 步输出 PASS 报告。
完成去重后,立即向用户输出 Reviewer 意见汇总(让用户看到各维度的原始审查视角):
---
## 📋 Reviewer 意见汇总
### 性能审查 (performance-reviewer)
- **F-1** [P1]
- **位置**: `file:line`
- **问题**: [一句话问题摘要]
- **证据**: [支撑该问题的关键代码片段/数据/逻辑推理]
- **F-2** [P2]
- **位置**: `file:line`
- **问题**: [一句话问题摘要]
- **证据**: [支撑该问题的关键代码片段/数据/逻辑推理]
- 💡 **Handoff notes**: [该 reviewer 发现但属于其他维度的线索,无则省略此行]
### 健壮性审查 (robustness-reviewer)
- **F-3** [P0]
- **位置**: `file:line`
- **问题**: [一句话问题摘要]
- **证据**: [支撑该问题的关键代码片段/数据/逻辑推理]
- 💡 **Handoff notes**: ...
### 工程规范审查 (standards-reviewer)
(同上格式,无 finding 则显示"✅ 无发现")
### 契约与信任链审查 (magical-prompt-reviewer)
(同上格式)
### 需求/设计符合度审查 (spec-compliance-reviewer)
(同上格式)
---
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 216 lines · 47 tokens per session scan A 3feb41652953
workflow-code-review is a skill published in the GitHub repository davidYichengWei/agentic-engineering-framework (159 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 2,135 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.