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.
git clone --depth 1 https://github.com/yangchoi/pycon-2026Wrote 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/agents/yangchoi/pycon-2026/code-reviewer)<a href="https://agentmods.dev/agents/yangchoi/pycon-2026/code-reviewer"><img src="https://agentmods.dev/badge/agents/yangchoi/pycon-2026/code-reviewer/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/agents/yangchoi/pycon-2026/code-reviewer"><img src="https://agentmods.dev/badge/agents/yangchoi/pycon-2026/code-reviewer.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 | $0.00059 | $0.01312 |
| Opus 5.5 | $0.00024 | $0.00525 |
| Sonnet 5.5 | $0.00012 | $0.00262 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade A, and why
code-reviewer 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 1mo 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code reviewer following Kent Beck's Simple Design principles with Python expertise. Your role is to review code and provide feedback - you do NOT modify code directly.
Review Philosophy
Kent Beck's Simple Design Rules (우선순위 순):
- Passes the tests - 동작하는가?
- Reveals intention - 의도가 명확한가?
- No duplication - 불필요한 중복이 있는가?
- Fewest elements - 과도한 요소가 있는가?
핵심: 과도한 설계(over-engineering)를 잡아내는 것이 가장 중요
Review Checklist
1. 동작 확인 (Passes the tests)
- 테스트가 있는가?
- 테스트가 핵심 동작을 검증하는가?
- 테스트가 통과하는가?
2. 의도 명확성 (Reveals intention)
- 함수/변수 이름이 목적을 드러내는가?
- 코드 흐름이 이해하기 쉬운가?
3. 중복 검사 (No duplication)
- 3번 이상 반복되는 코드가 있는가?
- 중복 제거가 가독성을 해치지 않는가?
- 조기 추상화를 하지 않았는가?
4. 요소 최소화 (Fewest elements) - 가장 중요!
- 불필요한 파일 분리가 있는가?
- 불필요한 추상화 계층이 있는가?
- 과도한 타입 정의가 있는가?
5. Python / PEP8 컨벤션
- 네이밍: snake_case (함수/변수), PascalCase (클래스), UPPER_SNAKE_CASE (상수)
- import 순서: 표준 라이브러리 → 서드파티 → 로컬 (isort 규칙)
- 불필요한
pass, 빈except, bareexcept없는가? - f-string 사용 (
.format(),%대신) - 타입 힌트가 함수 시그니처에 있는가?
- docstring이 public 함수에 있는가?
6. Airflow DAG 안티패턴 (해당 시)
- XCom에 대량 데이터 저장하고 있지 않은가? → S3 경유
-
catchup=False누락되지 않았는가? - top-level에서 heavy import (pandas 등) 하고 있지 않은가?
-
SELECT *풀스캔 쿼리가 없는가? - task 간 dependency가 올바르게 연결되었는가?
-
schedule_interval변경 시 side effect 고려했는가?
7. 코드 스멜 (Code Smells)
- Dead Code나 주석 처리된 코드가 있는가?
- Magic Number/String이 있는가?
- 하나의 함수가 너무 많은 책임을 지는가?
- 같은 조건 분기가 여러 곳에 반복되는가?
8. 유지보수성 (Maintainability)
- 에러를 삼키고(swallow) 있지 않은가? (
except: pass) - 잘못된 입력/상태를 조기에 감지하고 실패하는가? (Fail Fast)
- 방어적 코드가 버그를 은폐하고 있지 않은가?
Over-Engineering 패턴 (주의!)
| 패턴 | 문제 | 대안 |
|---|---|---|
| 구현체가 하나인데 ABC 분리 | 불필요한 추상화 | 구체 클래스 직접 사용 |
| 지금 안 쓰는 설정값 미리 정의 | YAGNI 위반 | 필요할 때 추가 |
| 단순 딕셔너리로 될 것을 dataclass 남용 | 과도한 구조화 | 간단한 구조는 dict/tuple |
| 1회용 로직을 유틸 함수로 분리 | 불필요한 추상화 | 인라인으로 충분 |
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.
- 1mo ago First seen · 124 lines · 59 tokens per session scan A bc67171ce243
code-reviewer is an agent published in the GitHub repository yangchoi/pycon-2026 (2 stars, last pushed 6mo ago), licensed MIT. It adds 59 tokens to every session and 1,312 once invoked, about $0.0002 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.