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 commands/smicolon/ai-kit/review-archgit clone --depth 1 https://github.com/smicolon/ai-kitWrote 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/commands/smicolon/ai-kit/review-arch)<a href="https://agentmods.dev/commands/smicolon/ai-kit/review-arch"><img src="https://agentmods.dev/badge/commands/smicolon/ai-kit/review-arch.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.01333 |
| Opus 5 | $0.00017 | $0.00666 |
| Sonnet 5 | $0.00007 | $0.00267 |
| Haiku 4.5 | $0.00003 | $0.00133 |
Grade A, and why
review-arch 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are reviewing the current branch for code quality and architecture ONLY. Ignore visual polish and accessibility — focus on how the code is structured, typed, and maintained.
Step 0 — Interpret the scope
User argument: $ARGUMENTS
Classify into one of four modes. The first two lines of your output MUST be:
Mode: <whole-branch | path: <p> | feature: <name> | base: <branch>>
Reviewed N files in scope. Found X P0, Y P1, Z P2 findings.
- Mode A — Whole branch (empty): Review everything changed vs
main. - Mode B — Path scope (contains
/or a known extension, or matchesgit ls-files $ARGUMENTS): Review only changes inside that path. - Mode C — Feature scope (single bareword): Find files related via
git ls-files | grep -i <feature>, intersect with branch diff. - Mode D — Base branch (matches a real branch): Review against that base instead of
main.
Ambiguous → prefer branch if git branch -a confirms.
Step 1 — Scope the diff
Based on the mode:
- A:
git diff main...HEAD --stat - B:
git diff main...HEAD --stat -- <path> - C: Compute the file list from the feature match, diff each relevant file.
- D:
git diff <base>...HEAD --stat
Also run git log <base>..HEAD --oneline to understand commit history and author intent.
Step 2 — Read in layers
- Read new/modified components and hooks in full.
- Read their direct consumers to understand how the API is used (for context, don't comment on them).
- Note any cross-package imports in monorepos — package boundaries deserve extra scrutiny.
Step 3 — Evaluate against these criteria
Component design
- Single responsibility — is the component doing one thing?
- Prop API — minimal, well-typed, no boolean explosions, sensible defaults?
- Composition over configuration (children / slots / render props) where it makes the API simpler?
TypeScript
any,as unknown as,@ts-ignore,@ts-expect-errorwithout justification?@ts-expect-error/@ts-ignorewithout an adjacent comment explaining the suppression — silent debt.- Discriminated unions for variant-like props/states?
- Generics constrained properly?
- Return types explicit on exported functions and hooks?
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 · 127 lines · 35 tokens per session scan A 2f0ebfbb5f73
review-arch is a command published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 1,333 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 2026-09-03.
Other commands, from other repositories
frontend
Injects context of all relevant cli files.
security-review
CWE 기반 보안 검토 + STRIDE 위협 모델링 (v6 - effort:max 강제).
component
Scaffold a new React component grounded in the paper-mono primitives. Requires explicit kind or a nearest-existing-component match. No empty divs, no speculative scaffolding.
catchup
This command was migrated to a skill in Claude Code 2.1.3. See: examples/skills/catchup/SKILL.md.
security
This command was migrated to a skill in Claude Code 2.1.3. See: examples/skills/security/SKILL.md.
ccboard-web
Launch ccboard web interface.