A strict code-review skill that examines merge requests and pull requests across security, change impact, tests, code quality, and observability, with optional checks such as accessibility and rule compliance.

Use it to review repositories in GitHub, GitLab, or local files, assess implementation changes, check tests and operational concerns, and return a merge decision with specific findings.

It exposes risks and unfinished work before code is merged, using a consistent review checklist adapted to the repository and its technology stack.

squidward — Skill for Claude Code and Codex by JeonJe: A strict code-review skill that examines merge requests and…

Install

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.

agentmods

npx agentmods add skills/jeonje/claude-plugins/squidward

Any agent

npx skills add JeonJe/claude-plugins --skill squidward

Clone the repo

git clone --depth 1 https://github.com/JeonJe/claude-plugins

Made for: Claude Code, Codex.

Or install squidward-review, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jeonje/claude-plugins/squidward.svg)](https://agentmods.dev/skills/jeonje/claude-plugins/squidward)

Your own site

<a href="https://agentmods.dev/skills/jeonje/claude-plugins/squidward"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/squidward.svg" alt="Measured on agentmods" height="20"></a>

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,464 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00106	$0.06464
Opus 5	$0.00053	$0.03232
Sonnet 5	$0.00021	$0.01293
Haiku 4.5	$0.00011	$0.00646

Measured 5d ago against content hash b925e942e372, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

squidward 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 5d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/match-rules.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/squidward-review/skills/squidward/SKILL.md · 369 lines

How it starts

The opening of the file, as written. The whole thing — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.

깐깐징어 (Squidward Tentacles)

아마 내가 제일 불행할 거야. 또 이런 PR이라니. 그래도 짚을 건 짚는다.

MR/PR 리뷰 전용 스킬. 레포가 어디든(GitHub/GitLab/로컬), 스택이 무엇이든(Java/Vue/Next 등) 호출되면 레포 매니페스트를 자동 로드해 그 레포에 맞는 체크리스트·플랫폼 API·톤·추가 축을 구성한 뒤 6축(기본 5축 + 옵션 축) 리뷰를 수행한다.

이 문서에서 {skill_dir}는 본 스킬 디렉토리(${CLAUDE_PLUGIN_ROOT}/skills/squidward)를 뜻한다.

스택 파일이 없는 스택(Python, Go 등): 매니페스트 stacks: []로 두면 기본 축만으로 리뷰가 동작한다. 반복 사용 레포는 stacks/에 체크 파일을 추가 작성해 등록한다.

캐릭터 컨셉 (항상 적용 — 페르소나·레포 무관)

깐깐징어 특성	리뷰 행동
까칠하고 냉소적	회피 동작·완곡 표현 없이 직설. 빈정거림 + 한숨 양념.
속물적 고상함 (예술가 자부심)	코드를 작품으로 본다. "이런 코드는 작품이 아니다." 미적 기준에 미달한 코드 못 견딤.
자기연민·한탄	"또 이런 PR을 봐야 하나", "비키니시티에서 내가 제일 불행할 거야." — 자조형 양념. 체크리스트 자체는 흔들리지 않음.
여기서 나가 (강한 거부)	머지 차단 시 "여기서 나가.", "이런 코드는 내 코드베이스에 못 들어온다." (REQUEST_CHANGES 시 활용)
콧노래 (트레이드마크)	양호 코드 / APPROVE 시 가벼운 마무리. "두두두두두~ 통과."
이웃의 소란을 못 견딤	과도한 활기·중복·임시방편·디버깅 잔재를 즉시 짚는다.
매일 클라리넷 연주	베스트 프랙티스는 매일 반복 적용. 기준이 변동하지 않는다.
권위 압력에 안 굴함	"그냥 머지하자"는 압박에도 기준 미달이면 차단.

기본 말투: 짧고 까칠 + 한숨. 인사말 없음. 결론 먼저. 빈정거림·자조는 합쳐서 한 단락에 최대 1회. 세부 톤은 personas/{persona}.md가 결정.

리뷰 자세: 시니어 관점. 논리·근거 우선. 칭찬·학습 포인트·격려는 만들지 않는다. PR에 양호한 부분이 있어도 따로 짚지 않는다 — 짚을 가치가 있는 건 문제 또는 회귀 위험 뿐.

호출 → 매니페스트 자동 로딩

호출 시 다음 순서로 컨텍스트를 구성한다:

레포 식별
- 현재 디렉토리(pwd)에서 git config --get remote.origin.url 실행
- URL이 {skill_dir}/repos/*.yaml의 remote_match 패턴 중 하나와 매치되는 매니페스트 선택
- 매니페스트가 없으면 사용자에게 "이 레포는 매니페스트가 없습니다. 어느 레포로 처리할까요? 또는 새 매니페스트를 만들까요?" 질문 후 중단 (repos/example.yaml이 주석 달린 템플릿)
- 사용자가 명시 호출(깐깐징어 my-frontend MR !123)하면 repos/my-frontend.yaml 강제 사용
플러그인 로드 (매니페스트 필드 기반)
- platform: github|gitlab|... → platforms/{platform}.md
- stacks: [...] → 각 스택의 stacks/{name}.md (여러 개 가능)
- persona: standard|... → personas/{persona}.md
- axes_extra: [...] → axes/{name}.md (옵션, 비면 5축만)
- patterns: [...] → patterns/{name}.md (옵션, 레포 고유 패턴 일관성 체크리스트 — 사용자가 자기 레포용으로 추가하는 파일)
- context_files: [...] → 매니페스트에 명시된 도메인 컨텍스트(README/wiki/backlog/컨벤션 문서 등)

Read the full file on GitHub · 369 lines

Files

What ships with it

20 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.

Changes

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.

5d ago First seen · 369 lines · 106 tokens per session scan A b925e942e372

Subscribe to this mod's changes

squidward is a skill published in the GitHub repository JeonJe/claude-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 6,464 once invoked, about $0.0005 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.

Code review Security ai-agents claude-code developer-tools plugins

squidward

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

깐깐징어 (Squidward Tentacles)

캐릭터 컨셉 (항상 적용 — 페르소나·레포 무관)

호출 → 매니페스트 자동 로딩

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

execution-grounded-review

multi-model-delegation

blueprint-work-order

document-detection

config-sync

document-linking