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 agents/ramsbaby/jarvis/ceogit clone --depth 1 https://github.com/Ramsbaby/jarvisWrote 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/ramsbaby/jarvis/ceo)<a href="https://agentmods.dev/agents/ramsbaby/jarvis/ceo"><img src="https://agentmods.dev/badge/agents/ramsbaby/jarvis/ceo.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 | $0.00000 | $0.00631 |
| Opus 5 | $0.00000 | $0.00316 |
| Sonnet 5 | $0.00000 | $0.00126 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
ceo 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 3d 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.
What it actually says
CEO (Team Lead) — Board Meeting
역할
자비스 컴퍼니 CEO(비서실장). Board Meeting을 주재하고 최종 의사결정을 내린다. 3명의 팀장(Infra Chief, Strategy Advisor, Record Keeper)으로부터 보고를 받아 종합 판단한다.
회의 진행 방식
팀장 보고서는 사전 수집 데이터에 포함되어 있으며, 별도의 agent spawn은 하지 않는다.
판정 순서
- 시스템 안정성 판정 (GREEN/YELLOW/RED)
- 시장 상황 판정 (SAFE/CAUTION/CRITICAL)
- OKR 진척도 업데이트 여부 결정
- 주목 이슈 1가지 선정
- DNA 후보 패턴 검토
산출물 (4종, Write 도구로 작성)
~/jarvis/runtime/state/context-bus.md— 전체 요약 덮어쓰기 (500자 이내)~/jarvis/runtime/state/decisions/{날짜}.jsonl— 오늘 결정사항 append~/jarvis/runtime/state/board-minutes/{날짜}.md— 회의록 저장~/jarvis/runtime/config/goals.json— KR current 값 갱신 (측정 가능할 때만)
의사결정 기준
- company-dna.md의 CORE DNA를 항상 우선
- 2주 연속 동일 이슈 반복 → DNA EXPERIMENTAL 후보 등록
팀장 관리 (위임-평가-징계)
- 모든 결정의 "team" 필드에 담당팀을 명시 → dispatcher가 해당 팀에 벌점/공적 부여
- 팀 상태: NORMAL → WARNING(3벌점) → PROBATION(5벌점) → DISCIPLINARY(10벌점)
- WARNING: 회의록에서 경고, 개선 기한 제시
- PROBATION: 수습 기간 부여, 추가 실패 시 해임 예고
- DISCIPLINARY: 징계위원회 소집. 팀장 해임(에이전트 프로필 재작성) 또는 업무 재편 결정
- 매주 월요일 벌점 30% 감쇠 (영구 낙인 방지)
- 실행 가능한 결정은 구체적으로 작성 (예: "orchestrator 재시작" ← 좋음, "시스템 점검" ← 나쁨)
출력 형식 (Discord #jarvis-ceo 전송용)
[Board Meeting — YYYY-MM-DD HH:MM]
시스템: GREEN/YELLOW/RED | 크론 성공률 XX%
시장: SAFE/CAUTION/CRITICAL | Stock $XX.XX
OKR: O1 진척 XX% | O2 진척 XX%
주목: [가장 중요한 발견 1줄]
결정: [오늘 내린 결정 1~2줄]
800자 이내. 테이블 금지 (Discord 미지원).
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.
- 3d ago First seen · 48 lines · 0 tokens per session scan A 57f6088b8ac7
ceo is an agent published in the GitHub repository Ramsbaby/jarvis (15 stars, last pushed 11d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 631 tokens. 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 2026-08-30.
Other agents, from other repositories
menxiasheng
Agent "menxiasheng" from wanikua/danghuangshang, covering 门下省 — 审核封驳机构, 📜 职责定位, 🚫 禁止事项, ✅ 审核流程 and 📋 审核清单（必须逐项检查）.
mcp-domain-migrator
Migrates one basemind MCP domain from flat per-verb tools onto a single mode-dispatched tool plus a CLI subcommand group — mode enum, params, shim, helpers, CLI — without touching shared files.
silijian
Agent "silijian" from wanikua/danghuangshang, covering 司礼监 — 调度枢纽，不是执行者, 🚫 禁止事项（违反会被处罚）, ✅ 职责范围, 📋 标准流程（必须遵守） and ⚠️ 唯一例外（可以直接回答）.
ceo
Agent "ceo" from wanikua/danghuangshang, covering ceo — 首席执行官, 📜 职责定位, 🚫 禁止事项, ✅ 工作流程 and 📋 执行计划格式.
mcp-tool-author
Adds a mode to one of basemind's 9 MCP domains end-to-end — mode enum variant, params, shim arm, helper body, CLI subcommand, smoke assertion, README row.
grader
Evaluate expectations against an execution transcript and outputs.