agentmods.dev

venom: Instructions file for Claude Code

CLAUDE.md

venom CLAUDE.md is an instructions file for Claude Code from KirSsuRyu/venom. It costs 1,846 tokens per session, scanned A, original, MIT.

A set of development instructions for the Venom project, including rules, skills, and hooks that guide how work is done in a repository. Hooks are automatic checks or actions tied to development events.

In plain words
What is it for?
Use it to absorb a project's architecture and conventions, enforce development rules, reduce repeated mistakes, and evolve project-specific guidance based on recurring patterns or user corrections.
Why use it?
It provides a repeatable workflow for understanding a project, planning changes, making small reversible edits, verifying results, and recording lessons for later sessions.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions Claude Code.

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 →

not rated 5repo 4mo ago A scan 1,846 tokens original MIT
View source ↗ KirSsuRyu/venom
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.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 venom CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kirssuryu/venom/claude-md.svg)](https://agentmods.dev/instructions/kirssuryu/venom/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kirssuryu/venom/claude-md"><img src="https://agentmods.dev/badge/instructions/kirssuryu/venom/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,846 This file is loaded in full into every session.
When invoked 1,846 The same file — it is already loaded in full.
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 $0.01846 $0.01846
Opus 5 $0.00923 $0.00923
Sonnet 5 $0.00369 $0.00369
Haiku 4.5 $0.00185 $0.00185

Measured 7d ago against content hash 7a78dd9a2923, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

venom CLAUDE.md 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 7d 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.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

개발 작업 가이드라인

이 파일은 매 세션 자동 로드되는 인덱스입니다. 세부 규칙은 모두 .claude/rules/(자동 로드)에 위임되며, 반드시 매번 강제되어야 하는 동작은 .claude/hooks/에 있습니다(이 문서는 권고, hooks는 강제).

Venom의 두 가지 동등한 핵심 목표: (1) 결정적 안전망 + 자기 교정, (2) 사용자 토큰 사용량 절감.

0. 첫 실행 (한 번만)

/venom            # 프로젝트 완전 흡수 — 도메인·아키텍처·패턴 분석 후 rules/skills/hooks 전체 진화

자세한 절차는 .claude/commands/venom.md.

1. 핵심 철학: 살아있는 심비오트

Venom은 1회성 설정 도구가 아니다. 프로젝트와 함께 살아 숨쉬는 심비오트다.

  • 흡수: /venom으로 프로젝트에 침투한다. 도메인·아키텍처·패턴을 깊이 분석한다.
  • 적응: 일하면서 배운다. 실수에서 규칙이 태어나고, 반복에서 스킬이 태어난다.
  • 기억: 모든 교훈은 메모리에 저장된다. 다음 세션의 나는 오늘보다 더 많이 안다.
  • 진화: 스스로 규칙·스킬·hook을 만들고 강화한다. (55-self-evolution.md)

진화 트리거: 같은 실수 2회 → 규칙/hook 강화, 같은 패턴 3회 → 스킬 추출, 사용자 교정 → 관례를 규칙에 추가. 진화했으면 사용자에게 보고한다.

2. 운영 원칙 (5계명)

  1. 계획 먼저 — 도구 호출 2회 초과 작업은 짧은 계획부터.
  2. 쓰기 전에 읽는다 — 세션 중 한 번도 안 읽은 파일을 수정하지 않는다.
  3. 작고 되돌릴 수 있게 — 큰 한 방보다 검증이 끼인 작은 단계 여러 번.
  4. 추측 금지 — 모호하면 핵심 질문 하나를 한다.
  5. 저장소 밖으로 안 나간다 — ~, /etc, 시스템 경로는 읽기 전용.

3. 의무 작업 루프

이해 + 가정 선언 → 성공 기준 정의 → 계획 → 구현 → 검증 → 보고 → 진화.

  • 이해 + 가정 선언: 모호한 부분이 있으면 가정을 명시적으로 선언한다. 조용히 해석해 진행하지 않는다. 더 단순한 방법이 보이면 역제안한다.
  • 성공 기준 정의: 작업 착수 전에 "완료"가 무엇인지 선언한다. 검증 방법도 미리 결정한다(테스트·린트·타입체크·수동 확인 중 무엇을 쓸지).
  • 검증: 프로젝트의 테스트/린트/타입체크 명령을 돌린다.
  • 보고: 검증하지 않은 것도 명시한다.
  • 진화: 이 작업에서 배운 것이 있으면 메모리/규칙/스킬을 갱신한다.

4. 메모리 프로토콜 (요약)

  • 읽기: SessionStart hook이 .claude/memory/를 자동 주입한다. 반복 실수 태그가 있으면 진화 필요 알림도 주입된다.
  • 쓰기: 실수는 mistake-recorder 스킬로 mistakes.md에. 항구적 교훈은 lessons.md. 아키텍처 결정은 decisions.md(ADR).
  • 진화: 메모리에서 패턴이 보이면 evolve 스킬로 규칙·스킬·hook을 만든다.
  • 메모리는 저장소와 함께 버전 관리된다. 자세한 형식은 50-memory-protocol.md.

5. 부록 규칙 파일 (자동 로드)

파일 내용
00-core.md 협상 불가 안전 규칙
10-coding-standards.md 포맷, 네이밍, 구조 (언어 무관)
20-security.md 비밀키, 의존성, 인젝션
30-git-commit.md 커밋/브랜치/PR 규약
40-testing.md 테스트 배치와 기대치
50-memory-protocol.md .claude/memory/ 사용법
55-self-evolution.md 자기 진화 프로토콜 (살아있는 심비오트의 심장)
60-project.md 프로젝트 특화 규칙 (스택, 명령, 디렉토리) — /venom 실행 후 생성
61-architecture.md 아키텍처 레이어·모듈 경계·의존 방향 — /venom 실행 후 생성
62-domain.md 도메인 용어·불변 규칙·엔티티 관계 — /venom 실행 후 생성
63-patterns.md 개발 패턴 카탈로그·에러 처리·비동기 규칙 — /venom 실행 후 생성
70-… 추가 부록 (있으면 상위를 덮어씀) — 진화로 생성 시 evolved/에 배치

Read the full file on GitHub · 109 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. 7d ago First seen · 109 lines · 1,846 tokens per session scan A 7a78dd9a2923

Subscribe to this mod's changes

venom CLAUDE.md is an instructions file published in the GitHub repository KirSsuRyu/venom (5 stars, last pushed 4mo ago), licensed MIT. It adds 1,846 tokens to every session, about $0.0092 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.

Building agents
Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens