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/ramsbaby/jarvis/claude-mdgit 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/instructions/ramsbaby/jarvis/claude-md)<a href="https://agentmods.dev/instructions/ramsbaby/jarvis/claude-md"><img src="https://agentmods.dev/badge/instructions/ramsbaby/jarvis/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 | $0.01997 | $0.01997 |
| Opus 5 | $0.00999 | $0.00999 |
| Sonnet 5 | $0.00399 | $0.00399 |
| Haiku 4.5 | $0.00200 | $0.00200 |
Grade A, and why
jarvis 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data privacy comes first, always.
All user-facing command line output should make use of emojis for visual hierarchy.
AI Navigation (Start Here)
Any AI agent or human touching this repo for the first time should read in this order:
- infra/docs/MAP.md — 1-minute entry point: purpose, layout, subsystems, "where to find what"
- infra/docs/TASKS-INDEX.md — Auto-generated catalog of scheduled tasks (count in
tasks-index.json.totalTasks), grouped by team - infra/docs/TEAMS-CRONS.md — Reverse index: team → owned crons
- infra/docs/CONFIG.md — Config inventory and safe-edit checklist
- infra/docs/ARCHITECTURE.md — Deep design (message flow, Discord runner, session mgmt)
- infra/docs/OPERATIONS.md — Incident response, cron schedules, log paths
면접봇 작업 시 반드시 먼저 읽을 것:
- infra/docs/INTERVIEW-BOT.md — 면접봇 풀 기획 문서 (아키텍처·불변식·버전 히스토리)
runtime/context/interview-bot-profile.md— Jarvis 세션 주입용 압축본 (불변식·파라미터·상태 파일 경로)
Regenerate TASKS-INDEX.md + tasks-index.json after any ~/jarvis/runtime/config/tasks.json change:
node ~/jarvis/infra/scripts/gen-tasks-index.mjs
Development Rules
- No hardcoded user paths — use environment variables (
BOT_HOME,JARVIS_RAG_HOME) - No hardcoded secrets — use
.envfiles, never commit tokens/webhooks - No hardcoded language patterns — keep prompts language-agnostic
- Shell scripts:
set -euo pipefail, quote all variables, trap cleanup - Naming:
[domain]-[target]-[action](e.g.,rag-index-safe.sh)
Golden Path — 작업 착수 전 고정 순서 (2026-04-21)
크고 모호한 요청을 받으면 다음 순서를 기본 흐름으로 삼습니다. 2026-04-15 메이커 에반 유튜브("GStack + Superpowers 후기")의 워크플로우를 Jarvis 철학(Iron Laws · SSoT · 집사 페르소나)으로 재구성한 것.
/brainstorm— 아이디어 인터뷰 (역질문 15~20개로 암묵 공백 선제 노출) + UI mockup 3안- 필요 시
/office-hours— 옵션 A vs B 트레이드오프 매트릭스 의사결정 /autoplan— 단계별 계획 분해 (Writing Plans = 설계 도면)/plan-review— 11섹션 체크리스트 엄격 리뷰/verify— 7-Gate + Contrarian Challenge (독립 감사관 Agent)- worktree 분리 →
/codex또는/orchestrate병렬 구현 - 완료 후
/design-review— AI slop 감식 (생산 후 시각 감사) /ship→/retro+ 필요 시/oops로 오답노트 실시간 기재
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 · 100 lines · 1,997 tokens per session scan A 12ab82ec1b13
jarvis CLAUDE.md is an instructions file published in the GitHub repository Ramsbaby/jarvis (16 stars, last pushed 14d ago), licensed MIT. It adds 1,997 tokens to every session, about $0.0100 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 2026-08-30.
Other instructions, from other repositories
artbot AGENTS.md
Instructions for ArtBlocks/artbot, covering artbot — agent & maintainer guide, what this is, quick commands, two production flags (critical) and architecture (actual).
goclaw AGENTS.md
AGENTS.md instructions for nextlevelbuilder/goclaw, covering goclaw gateway, language, tech stack, project structure and key patterns.
goclaw CLAUDE.md
Claude Code instructions for nextlevelbuilder/goclaw, covering goclaw gateway, language, tech stack, project structure and key patterns.
Snaptium AGENTS.md
AGENTS.md instructions for jetyu/Snaptium, covering snaptium agent instructions, reference rule files, core behavior, snaptium architecture rules and typescript rules.
Snaptium GEMINI.md
Gemini CLI instructions for jetyu/Snaptium, a project described as: A modern markdown AI note-taking application.
DiscordMCP CLAUDE.md
Claude Code instructions for Rastrian/DiscordMCP, covering discord mcp platform — claude project instructions, project identity, core framing, strict non-goals and product goal.