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 commands/ramsbaby/jarvis/orchestrategit 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/commands/ramsbaby/jarvis/orchestrate)<a href="https://agentmods.dev/commands/ramsbaby/jarvis/orchestrate"><img src="https://agentmods.dev/badge/commands/ramsbaby/jarvis/orchestrate.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 | $0.00052 | $0.00493 |
| Opus 5 | $0.00026 | $0.00246 |
| Sonnet 5 | $0.00010 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
orchestrate 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 4d 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
/orchestrate — 병렬 멀티에이전트 태스크 실행
복잡한 태스크를 3개 전문 에이전트로 분해해서 병렬 실행합니다.
사용법
/orchestrate <태스크 설명>
실행 단계
1. 태스크 분석
입력된 태스크를 분석해서 3개 독립 서브태스크로 분해하세요:
- Research: 조사/분석이 필요한 부분 (brave-search, WebFetch)
- Code: 코드 작성/수정이 필요한 부분 (serena, 파일 편집)
- Validation: 검증/테스트가 필요한 부분 (Bash 실행, 결과 확인)
2. 파일 소유권 체크
⚠️ 동일 파일을 두 에이전트가 동시에 수정하면 충돌 발생. Code 에이전트에게 수정할 파일 목록을 명시적으로 배정하고, 다른 에이전트는 해당 파일을 Read-only로만 접근.
3. 병렬 실행
3개 Agent 도구 호출을 하나의 메시지에 담아 동시 실행:
- Research Agent: 조사 담당, 결과를 /tmp/research-result.md 에 저장
- Code Agent: 구현 담당, 지정된 파일만 수정
- Validation Agent: 검증 담당, Bash로 테스트 실행
4. 결과 합성
3개 에이전트 결과를 수집해서:
- 성공/실패 요약
- Research 인사이트 → Code에 반영된 내용
- Validation 통과 여부
- 다음 단계 권장사항
적합한 태스크 예시
- "RAG 시스템 성능 분석 후 개선점 구현"
- "Discord bot 명령어 추가 + 테스트"
- "API 엔드포인트 설계 + 구현 + 통합테스트"
부적합한 태스크
- 단일 파일 수정 → 그냥 직접 편집
- 순서가 중요한 태스크 → 순차 실행 사용
- 30초 이내 완료 가능한 태스크 → 오버킬
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.
- 4d ago First seen · 47 lines · 52 tokens per session scan A f72b004dec72
orchestrate is a command published in the GitHub repository Ramsbaby/jarvis (15 stars, last pushed 11d ago), licensed MIT. It adds 52 tokens to every session and 493 once invoked, about $0.0003 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 commands, from other repositories
bm
Ask basemind anything about the current codebase — outlines, refs, callers, git history, blame, diffs, docs, memory.
bm-scan
Build or refresh the basemind index by running basemind scan via the CLI — works without the MCP server (use it when basemind reports "no index" / "no indexed files").
harden
Run the real-OSS harden harness against the 8 canary repos.
serve
Start the basemind MCP stdio server.
bm-doctor
Diagnose and recover basemind when it isn't working (MCP tools missing/erroring, "no index", dead server) — runs CLI checks and gives the client-specific way to reconnect the server.
dream
Memory dream pass — judge undreamed days, promote durable signal to long-term, then sweep.