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 agentmods add instructions/hanjin-kim/redcell/claude-mdgit clone --depth 1 https://github.com/hanjin-kim/redcellWrote 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/instructions/hanjin-kim/redcell/claude-md)<a href="https://agentmods.dev/instructions/hanjin-kim/redcell/claude-md"><img src="https://agentmods.dev/badge/instructions/hanjin-kim/redcell/claude-md.svg" alt="Measured on agentmods" 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 | $0.03008 | $0.03008 |
| Opus 5 | $0.01504 | $0.01504 |
| Sonnet 5 | $0.00602 | $0.00602 |
| Haiku 4.5 | $0.00301 | $0.00301 |
Grade A, and why
redcell 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 6d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
redcell — guide for Claude Code agents
사용자가 Claude Code로 redcell 을 커스터마이즈할 때 이 파일을 먼저 읽으세요. 특히 "도메인 경험표(experience table) 를 가진 사용자" — 산업별 액션 효과 범위, 이벤트 풀, 경쟁사 행동 패턴을 이미 알고 있는 사용자가 그것을 LLM 생성이 아닌 자기 데이터로 주입하는 경로가 이 문서의 1순위입니다.
한 줄 요약
redcell 은 (전략, 환경) → multi-turn 시뮬레이션 → 양측 반응 trajectory 도구. 입력은 redcell_config.yaml + scenario.yaml, 출력은 brief.md + brief_trace.md.
Override hooks — 경험표를 가진 사용자의 1순위 경로
scenario.yaml 의 top-level 에 아래 키를 채우면 해당 단계 LLM 생성을 건너뜁니다. 일부만 채우는 부분 override 도 가능 — 채운 것은 사용자 데이터, 비운 것은 LLM 생성.
권장 워크플로 — 최소 scenario.yaml → LLM 으로 빈 곳 채우기
rulebook / event_deck (12-18 이벤트) / competitor_strategies 를 백지에서 손으로 쓰는 건 비효율. 사용자가 최소 baseline 만 적으면 LLM 이 나머지를 채워줍니다.
최소 baseline (scenario.yaml) — 다음 정보만 있으면 됩니다 (LLM 이 추론할 수 없는 구조적 사실들):
industry— 산업명 (rulebook/event_deck 톤 결정)sides[]— 시장 명단:id(side_a/b/c),company.name,structural_advantages/structural_disadvantages, CEOpersonality.aggression/risk_tolerance/leadership_constraints- (옵션) 사용자가 이미 가진
rulebook안의 일부 rule 만 — 나머지는 비워둬도 LLM 이 보충하지 않습니다(rulebook 키가 있으면 그대로 사용, 없으면 통째로 LLM 생성).
채우는 단계:
redcell init-scenario config.yaml— 설정 단계만 LLM 으로 돌립니다 (~5 calls, ~10-30s, 턴 시뮬레이션 안 함). 같은 폴더에scenario.overrides.yaml가 생성되며 헤더에 각 블록이 user-supplied 인지 auto-generated 인지 표시.- 그 파일을 직접 편집 — LLM 이 산업 특성을 잘못 잡은 부분 (확률, side_effects 비대칭, 누락 이벤트, 비현실적인 cash_delta) 을 자기 데이터로 수정. paste-back 불필요.
redcell run config.yaml -o brief.md— 본 시뮬레이션 (5턴 × 3측 × deliberation/adjudication, ~200 calls). 엔진이scenario.overrides.yaml을 자동 로드해서 편집한 그대로 사용 — 설정 단계 LLM 호출 0회.- (선택)
redcell init-scenario --regenerate— 산업 변경 등 큰 변동 후 override 파일을 폐기하고 처음부터 재생성. 기존 캐시도 무시.
scenario.overrides.yaml와scenario.yaml둘 다 같은 키를 가지면 overrides 파일이 이긴다. scenario.yaml 은 시장 명단(sides)·페르소나 같은 구조적 정보 전용, overrides 파일은 튜닝 가능한 rulebook/event_deck/competitor_strategies 전용 — 이렇게 역할을 분리하면 깔끔.LLM 생성이 실패 하면 silent fallback 없이 즉시
RuntimeError로 종료합니다. 에러 메시지가 "scenario.overrides.yaml (또는 scenario.yaml top-level) 에 그 블록을 직접 채우라" 고 안내합니다 — 분석이 fallback 으로 조용히 망가지는 일은 없습니다.
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.
- 6d ago First seen · 196 lines · 3,008 tokens per session scan A d879e1fa311d
redcell CLAUDE.md is an instructions file published in the GitHub repository hanjin-kim/redcell (10 stars, last pushed 2mo ago), licensed MIT. It adds 3,008 tokens to every session, about $0.0150 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.
Other instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
LLM-TradeBot copilot-instructions.md
Copilot instructions for EthanAlgoX/LLM-TradeBot, covering repository instructions, core rules, validation and ai asset governance.
Convertible-Bond-Pricing-Research CLAUDE.md
Instructions for ericxuzhesheng/Convertible-Bond-Pricing-Research, covering claude.md — convertible bond pricing research, current published state and routine commands.
bukio-cli AGENTS.md
AGENTS.md instructions for erikvankempen/bukio-cli, covering agents.md — bukio-cli agent manual, 1. house rules (non-negotiable), 2. environment, 3. command quick reference and 3.1 jurisdiction profiles (16 markets).
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.