venom: Skill for Claude Code

.claude/skills/retro/SKILL.md

retro is a skill for Claude Code from KirSsuRyu/venom. It costs 97 tokens per session (1,391 once invoked), scanned A, original, MIT.

A debugging agent that investigates bugs, outages, and failed tests in an isolated context. It gathers evidence, tests possible causes, identifies the root cause, and suggests a fix without applying it.

In plain words
What is it for?
Use it to diagnose why code or tests fail, trace an error to its cause, propose the smallest correction, and outline a regression test.
Why use it?
It reduces guesswork by requiring reproduction steps, full errors, relevant code locations, and checks of recent changes. It also stops after three failed fix suggestions and calls for a new investigation direction.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is KirSsuRyu/venom's own configuration. It tells Claude Code how to work on venom itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything venom configures →

Reuse

Borrowing it

Nothing to install: this file belongs to KirSsuRyu/venom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/KirSsuRyu/venom/main/.claude/skills/retro/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/KirSsuRyu/venom

Made for: Claude Code.

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.

agentmods badge for retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/kirssuryu/venom/retro.svg)](https://agentmods.dev/skills/kirssuryu/venom/retro)
Your own site
<a href="https://agentmods.dev/skills/kirssuryu/venom/retro"><img src="https://agentmods.dev/badge/skills/kirssuryu/venom/retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,391 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00097 $0.01391
Opus 5 $0.00048 $0.00696
Sonnet 5 $0.00019 $0.00278
Haiku 4.5 $0.00010 $0.00139

Measured 8d ago against content hash 3f94746e5a11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

retro 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.

.claude/skills/retro/SKILL.md · 124 lines

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.

회고(Retro) 스킬

숫자는 거짓말하지 않는다. git과 메모리가 말하는 것을 들어라. 회고는 자책이 아니라 다음 주를 더 잘 보내기 위한 데이터 수집이다.

트리거

  • "회고해줘" / "이번 주 어땠어" / "retro" / "/retro"
  • 주간 또는 세션 종료 시점
  • 릴리스 직후 ("이번 배포 정리해줘")

입력 파싱

기간을 지정하지 않으면 지난 7일이 기본. 명시적 기간 예시:

  • "오늘 회고" → 오늘 0시 이후
  • "이번 주 회고" → 지난 7일
  • "이번 스프린트" → 사용자에게 시작 날짜를 묻는다
  • "v1.2 릴리스 이후" → 해당 태그 이후

절차

1단계: git 통계 수집 (병렬)

# 커밋 수 및 메시지
git log --oneline --since="7 days ago" --no-merges

# 파일별 변경량
git diff --stat HEAD~$(git log --oneline --since="7 days ago" --no-merges | wc -l) HEAD 2>/dev/null || \
git log --since="7 days ago" --no-merges --numstat --format="" | awk '{add+=$1; del+=$2} END {print "+"add" -"del}'

# 변경된 파일 목록
git log --since="7 days ago" --no-merges --name-only --format="" | sort -u | head -30

# 작업한 브랜치
git log --since="7 days ago" --no-merges --format="%D" | tr ',' '\n' | grep -v '^$' | sort -u | head -10

# 커밋 타입 분포 (conventional commits 기준)
git log --since="7 days ago" --no-merges --format="%s" | grep -oP '^(feat|fix|docs|refactor|test|chore|perf|build|ci)' | sort | uniq -c | sort -rn

기간 내 커밋이 0개이면 파라미터를 늘려 재시도하고, 그래도 없으면 사용자에게 알린다.

2단계: 메모리 패턴 분석

a) .claude/memory/mistakes.md 에서 해당 기간 항목 추출
   - 새로 기록된 실수 개수
   - 반복 태그 있는지 (진화 트리거 확인)

b) .claude/memory/lessons.md 에서 새 항목 확인

c) .claude/memory/decisions.md 에서 기간 내 ADR 확인

3단계: 진화 신호 감지

아래 조건이 감지되면 진화 권고 섹션에 명시:

신호 의미
mistakes.md 동일 태그 2회 이상 해당 영역 규칙/hook 강화 필요
같은 커밋 타입이 전체의 60% 이상 특정 작업 패턴 → 스킬 추출 고려
fix 커밋이 feat 커밋보다 많음 테스트 커버리지 또는 설계 문제 신호
문서 관련 커밋이 0개 코드-문서 불일치 누적 가능성

4단계: 리포트 생성

출력 형식

## 🔁 회고 — YYYY-MM-DD ~ YYYY-MM-DD

### 📊 숫자
| 항목 | 값 |
|---|---|
| 커밋 | N개 |
| 추가 라인 | +X |
| 삭제 라인 | -Y |
| 순 변화 | +Z |
| 변경 파일 | N개 |
| 테스트 커밋 비율 | N% |

### 🏗️ 무엇을 했나
커밋 타입별 요약. 가장 많이 건드린 영역 3개.

### 🐛 실수와 학습
- 이번 기간 mistakes.md에 기록된 실수: N개
- 새 교훈(lessons.md): N개
- 반복 태그: <있으면 나열 / 없음>

### 🚧 막힌 곳
fix 커밋이 많거나 같은 파일을 반복 수정한 경우 식별.

### ⚡ 진화 권고
<감지된 진화 신호가 있으면 나열. 없으면 "이번 기간 진화 트리거 없음">

### 📝 다음 주 제안
데이터 기반으로 1~3개 제안. 추측 금지 — 숫자에서 도출한 것만.

Read the full file on GitHub · 124 lines

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.

  1. 8d ago First seen · 124 lines · 97 tokens per session scan A 3f94746e5a11

Subscribe to this mod's changes

retro is a skill published in the GitHub repository KirSsuRyu/venom (5 stars, last pushed 4mo ago), licensed MIT. It adds 97 tokens to every session and 1,391 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.

Related

Other skills, from other repositories

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens

establishing-project-context

Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

GanyuanRan/Aegis · 45 tokens