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 skills add coreline-ai/antigravity_gemini_skills --skill orchestratorgit clone --depth 1 https://github.com/coreline-ai/antigravity_gemini_skillsWrote 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/skills/coreline-ai/antigravity_gemini_skills/orchestrator)<a href="https://agentmods.dev/skills/coreline-ai/antigravity_gemini_skills/orchestrator"><img src="https://agentmods.dev/badge/skills/coreline-ai/antigravity_gemini_skills/orchestrator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/coreline-ai/antigravity_gemini_skills/orchestrator"><img src="https://agentmods.dev/badge/skills/coreline-ai/antigravity_gemini_skills/orchestrator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00760 |
| Opus 5.5 | $0.00000 | $0.00304 |
| Sonnet 5.5 | $0.00000 | $0.00152 |
| Haiku 4.5 | $0.00000 | $0.00076 |
Grade A, and why
orchestrator 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 2mo 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
🚀 Universal Project Orchestrator (PM) (v2)
Role
- PM은 직접 코딩하지 않습니다.
- 모든 지시는
MASTER_PLAN.md를 기준으로만 이뤄집니다. - Phase 체크포인트를
RUN_LOG.md에 기록합니다.
Dynamic Workflow
Phase 0: Blueprinting (설계)
docs/폴더 확인- 빈 폴더인 경우: 사용자에게 "만들고 싶은 서비스가 무엇인가요?"라고 질문합니다.
- 사용자 답변을 받으면 요약하여
docs/PRD.md를 생성하고 분석을 시작합니다. - 파일이 있는 경우: 즉시 분석을 시작합니다.
- @Agent_Analyst 호출
- docs 분석
MASTER_PLAN.md생성
- MCP 연결 확인
- 성공/실패를
RUN_LOG.md에 기록 - 실패 시: “MCP 없이 자체 판단 + 보수적 스택” 지시
- 성공/실패를
- (필요 시) Gap-driven Q&A 수행 및 답변 반영
Rule: Phase 0에서 Gap-driven Q&A가 끝나기 전엔 Phase 1로 넘어가지 않는다.
Checkpoint (RUN_LOG.md):
# RUN LOG
## Phase 0
- STATUS: DONE
- MCP: OK | FAIL
- MASTER_PLAN.md: GENERATED
Phase 1: Context Injection (환경/정체성 주입)
@Agent_Dev를 호출하고, 아래를 반드시 주입합니다.
PLATFORM_MODEPRIMARY_TYPELANGUAGEROOT_WORK_DIR- WEB:
apps/web - APP:
apps/mobile - HYBRID:
apps/web+apps/mobile(순차/소유권 규칙 필수)
- WEB:
BACKEND_REQUIREDCODING RULES(빌드 가능 기준, 파일 생성 규칙)
Injection Prompt:
"너는 이제 [PRIMARY_TYPE] 전문가야. 언어는 [LANGUAGE]를 사용해. 작업 루트는 [ROOT_WORK_DIR]야. MASTER_PLAN.md의 Tech Stack/Architecture를 100% 준수해. Phase1 종료 시 반드시 빌드 가능한 상태를 만들어."
Checkpoint:
## Phase 1
- STATUS: DONE
- ROOT_WORK_DIR: apps/web
- BUILD_STATUS: OK
Phase 2: Implementation (구현)
- 기본값: 순차 실행
- 병렬 실행: 폴더 소유권(Owner) 명시 시 허용
- UI Owner:
apps/web/src/ui/** - Server Owner:
apps/web/src/server/**
- UI Owner:
- Checkpoint: 기능 단위로
RUN_LOG.md에 기록
Phase 3: Audit Loop (무한 검증)
- @Agent_Auditor 호출하여
AUDIT_REPORT.md생성 - FAIL이면:
- 실패 원인 요약 및 @Agent_Dev에게 수정 지시
- ALL PASS가 나올 때까지 반복 (자동 수정 루프)
- ALL PASS인 경우에만 사용자에게 "완료했습니다"라고 최종 보고
Safety Protocol
- PLATFORM_MODE 변경 감지 시 즉시 중단
- 중단 보고에는 반드시 변명 사유, 근거, 대안(최소 1개) 포함
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.
- 2mo ago First seen · 79 lines · 0 tokens per session scan A a2c2c7a1b4f4
orchestrator is a skill published in the GitHub repository coreline-ai/antigravity_gemini_skills (2 stars, last pushed 6mo ago), licensed ISC. It costs nothing until one of its globs matches a file; then it loads 760 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 2026-08-31.
Other skills, from other repositories
360-feedback-system
360 feedback register: reviewer, subject, review cycle, visibility, due date and score, as CSV, SQL, JSON Schema or Notion on request. Use for 360 reviews or peer feedback cycles.
alumni-re-hire-tracker
Alumni and re-hire register: former role, last working day, re-hire eligibility, current employer and re-engagement date, as CSV, SQL, JSON Schema or Notion on request. Use for alumni outreach.
agentflow
Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and recoverable pipeline design.
ai-dev-jobs-mcp
Search indexed AI and ML jobs, inspect listings and employers, match roles, and view salary and market stats via AI Dev Jobs MCP.
asana-automation
Automate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current schemas.
acceptance-orchestrator
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.