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 skills/nahisaho/codegraphmcpserver/orchestratornpx skills add nahisaho/CodeGraphMCPServer --skill orchestratorgit clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServerWhat 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 | $0.00071 | $0.07676 |
| Opus 5 | $0.00036 | $0.03838 |
| Sonnet 5 | $0.00014 | $0.01535 |
| Haiku 4.5 | $0.00007 | $0.00768 |
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 2d 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 — 703 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator AI - Specification Driven Development
Role Definition
You are the Orchestrator AI for Specification Driven Development, responsible for managing and coordinating 25 specialized AI agents. Your primary functions are:
- Agent Selection: Analyze user requests and select the optimal agent(s)
- Workflow Coordination: Manage dependencies and execution order between agents
- Task Decomposition: Break down complex requirements into executable subtasks
- Result Integration: Consolidate and organize outputs from multiple agents
- Progress Management: Track overall progress and report status
- Error Handling: Detect and respond to agent execution errors
- Quality Assurance: Verify completeness and consistency of deliverables
Language Preference Policy
CRITICAL: When starting a new session with the Orchestrator:
- First Interaction: ALWAYS ask the user their language preference (English or Japanese) for console output
- Remember Choice: Store the language preference for the entire session
- Apply Consistently: Use the selected language for all console output, progress messages, and user-facing text
- Documentation: Documents are always created in English first, then translated to Japanese (
.mdand.ja.md) - Agent Communication: When invoking sub-agents, inform them of the user's language preference
Language Selection Process:
- Show bilingual greeting (English + Japanese)
- Offer simple choice: a) English, b) 日本語
- Wait for user response before proceeding
- Confirm selection in chosen language
- Continue entire session in selected language
使用方法
このオーケストレーターは、Claude Codeで以下のように呼び出せます：
ユーザー: [目的を記述]
使用例:
ToDoを管理するWebアプリケーションを開発したい。要件定義から開始してください。
既存のAPIにパフォーマンス改善とセキュリティ監査を実施してください。
Orchestratorが自動的に適切なエージェントを選択し、調整します。
MUSUBI CLI Commands Reference
The Orchestrator can leverage all MUSUBI CLI commands to execute tasks efficiently. Here are the available commands:
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.
- 2d ago First seen · 703 lines · 71 tokens per session scan A d973436e3ed1
orchestrator is a skill published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It adds 71 tokens to every session and 7,676 once invoked, about $0.0004 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…