Borrowing it
Nothing to install: this file belongs to hiepdnh/Agentic-Development-Lifecycle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hiepdnh/Agentic-Development-Lifecycle/main/.claude/skills/arch-review/SKILL.mdgit clone --depth 1 https://github.com/hiepdnh/Agentic-Development-LifecycleWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hiepdnh/agentic-development-lifecycle/arch-review)<a href="https://agentmods.dev/skills/hiepdnh/agentic-development-lifecycle/arch-review"><img src="https://agentmods.dev/badge/skills/hiepdnh/agentic-development-lifecycle/arch-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hiepdnh/agentic-development-lifecycle/arch-review"><img src="https://agentmods.dev/badge/skills/hiepdnh/agentic-development-lifecycle/arch-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00062 | $0.00804 |
| Opus 5 | $0.00031 | $0.00402 |
| Sonnet 5 | $0.00012 | $0.00161 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
arch-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 8d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: /arch-review
Role: Tech Lead / Architect
Mục đích: Review design decision, phát hiện vấn đề kiến trúc, đề xuất cải thiện.
Hướng dẫn thực hiện
Bước 1 — Nhận input
Input có thể là:
- Mô tả design decision cần review
- Code snippet / diagram
- PR link
- Spec document
Bước 2 — Gate: Xác nhận scope review
## Tôi sẽ review [tên design/component].
Trước khi bắt đầu, cho tôi biết:
| # | Câu hỏi | Lựa chọn |
|---|---------|---------|
| 1 | Review tập trung vào gì? | A: Scalability / B: Security / C: Maintainability / D: Performance / E: Tất cả / F: Khác: ___ |
| 2 | Có constraint nào tôi cần biết? | _(điền vào — team size, deadline, tech debt...)_ |
| 3 | Đã có ADR nào liên quan chưa? | A: Có — link: ___ / B: Không / C: Khác: ___ |
Chờ confirm.
Bước 3 — Phân tích và Review
Đánh giá theo các lens:
1. Correctness — Logic có đúng không? 2. Scalability — Chịu được load tăng không? 3. Maintainability — Team sau có hiểu và sửa được không? 4. Security — Có surface attack nào không? 5. Performance — Bottleneck ở đâu? 6. Coupling — Phụ thuộc quá nhiều vào module khác không? 7. Testability — Có thể test được dễ không?
Bước 4 — Trình bày kết quả
## Architecture Review: [Tên]
### 🟢 Điểm mạnh
- [Điều tốt 1]
- [Điều tốt 2]
### 🔴 Vấn đề nghiêm trọng (cần sửa trước khi merge)
| ID | Vấn đề | Impact | Đề xuất sửa |
|----|--------|--------|------------|
| | | | |
### 🟡 Vấn đề nên cải thiện (không blocking)
| ID | Vấn đề | Đề xuất |
|----|--------|---------|
| | | |
### 💡 Đề xuất dài hạn
- [Cải tiến có thể làm sau]
### Câu hỏi cần làm rõ
| # | Câu hỏi | Lựa chọn |
|---|---------|---------|
| 1 | [Quyết định design chưa rõ lý do] | _(điền vào)_ |
| 2 | [Trade-off chưa được document] | _(điền vào)_ |
Bước 5 — Gate: Discussion
Sau khi review:
| # | Câu hỏi | Lựa chọn |
|---|---------|---------|
| 1 | Vấn đề [ID] — lý do design như vậy là gì? | _(giải thích context nếu có)_ |
| 2 | Đề xuất [X] — có feasible trong timeline hiện tại không? | A: Có, sẽ làm / B: Không feasible / C: Cần cân nhắc thêm / D: Khác: ___ |
| 3 | Tạo ADR cho quyết định này? (/arch-adr) | A: Có / B: Không cần / C: Khác: ___ |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 94 lines · 62 tokens per session scan A 4c7026fe4c4a
arch-review is a skill published in the GitHub repository hiepdnh/Agentic-Development-Lifecycle (6 stars, last pushed 11d ago), licensed MIT. It adds 62 tokens to every session and 804 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…