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 skills add SW-in-beta/simon-skills --skill simon-code-reviewgit clone --depth 1 https://github.com/SW-in-beta/simon-skillsWrote 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/sw-in-beta/simon-skills/simon-code-review)<a href="https://agentmods.dev/skills/sw-in-beta/simon-skills/simon-code-review"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-code-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/sw-in-beta/simon-skills/simon-code-review"><img src="https://agentmods.dev/badge/skills/sw-in-beta/simon-skills/simon-code-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 | $0.00132 | $0.07034 |
| Opus 5.5 | $0.00053 | $0.02814 |
| Sonnet 5.5 | $0.00026 | $0.01407 |
| Haiku 4.5 | $0.00013 | $0.00703 |
Grade A, and why
simon-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 2mo 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 — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
simon-code-review
PR 기반 코드 리뷰 스킬. Draft PR을 생성하고, 논리적 변경 단위별 인라인 코드 리뷰를 작성하며, CI 모니터링과 사용자 피드백 루프를 반복한다.
Mode Detection
스킬 시작 시 모드를 자동 감지한다:
.claude/memory/review-sequence.md존재 확인- 존재 → CONNECTED 모드 (simon/grind에서 넘어온 것)
.claude/memory/branch-name.md읽기.claude/reports/{feature-name}-report.md확인 → PR description에 활용.claude/memory/plan-summary.md확인 → 계획 매핑용.claude/memory/pr-info.md확인 → 이미 PR이 있으면 재사용
- 미존재 → STANDALONE 모드
git diff {base-branch}...HEAD로 변경사항 분석- Agent team으로 review-sequence.md 자체 생성
- Report도 자체 생성
- 이후 워크플로는 양 모드 동일
Shared Protocols:
~/.claude/skills/_shared/preamble.md읽기 — Session Isolation, Error Resilience, Forbidden Rules, Agent Teams, Cognitive Independence 공통 프로토콜 포함.
Session Isolation Protocol (확장)
SESSION_DIR 결정: CONNECTED 모드에서는 simon-dev이 전달한 {SESSION_DIR}을 사용한다. STANDALONE 모드에서는 현재 브랜치명으로 직접 결정한다 (preamble의 SESSION_DIR 결정 bash 참조).
Workflow
[Mode Detection]
↓
[STANDALONE only] → Step 0: Diff 분석 + review-sequence 생성
↓
Step 1: Draft PR 생성
↓
Step 2: 인라인 코드 리뷰 작성
↓
Step 3: CI Watch (background) + 사용자에게 리뷰 안내
↓
Step 4: 피드백 루프 ──────────────────────┐
4-A: 사용자 피드백 수집 (PR 코멘트) │
4-B: [GATE] 전문가 검증 → 코드 수정 │
4-C: 수정된 부분에 인라인 리뷰 재작성 │
4-D: [GATE] CI Watch 재시작 (코드 변경 시 필수) │
4-E: 사용자에게 수정 완료 안내 │
↓ │
사용자 승인? ─── No ─────────────────────┘
│
Yes
↓
Step 5: 마무리
중단 복구 프로토콜
어떤 Step에서든 외부 요인(push 실패, API 오류, 사용자 개입 등)으로 흐름이 중단되었다가 재개될 때, 반드시 아래 체크리스트를 따른다:
- 현재 Step의 완료 여부 확인 — 부분 완료 상태면 미완료 하위 단계부터 재개
- 잔여 워크플로 전체를 확인 — 현재 Step 완료 후 남은 Step(특히 Step 2 인라인 리뷰)을 순서대로 실행
- "사용자에게 안내"는 흐름의 종료가 아니라 일시 정지 — 안내 후에도 대기 상태를 유지하고, 문제 해결 시 자동 재개
금지 패턴: push/PR 생성 등 하나의 하위 작업 해결 후 "완료"로 간주하고 후속 Step을 누락하는 것. 특히 Step 2(인라인 리뷰)는 이 스킬의 핵심 가치이므로 절대 누락해서는 안 된다.
Step 0: Standalone 분석 (STANDALONE 모드만)
STANDALONE 모드에서는 simon-dev의 Step 18-A/B에 해당하는 분석을 자체적으로 수행한다. simon-dev이 전문가 패널을 거쳐 생성하는 review-sequence와 동등한 품질을 위해 agent team을 구성한다.
What ships with it
4 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.
- 2mo ago First seen · 421 lines · 132 tokens per session scan A 9a509b4f13be
simon-code-review is a skill published in the GitHub repository SW-in-beta/simon-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 132 tokens to every session and 7,034 once invoked, about $0.0005 per session on Opus 5.5. 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
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…