orchestration

orchestration is a skill for Claude Code from kimsanguine/hplan. It costs 99 tokens per session (4,697 once invoked), scanned A, original, MIT.

A guide for choosing how multiple AI agents coordinate their work. It compares sequential work, parallel work, routing tasks to a specialist, and hierarchical coordination between levels of agents.

In plain words
What is it for?
Assess a multi-agent design, select and document an orchestration pattern, plan agent or model routing, and decide when a simple single-agent approach is enough.
Why use it?
The wrong coordination method can add unnecessary complexity, delays, costs, or bottlenecks. The guide helps match the structure to task dependencies, agent count, error handling, and model-selection needs.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; positional $N argument; mentions Claude Code.

Part of the architect plugin — 4 skills shipped together

Good fit Assess a multi-agent design, select and document an orchestration pattern, plan agent or model routing, and decide when a simple single-agent approach is enough.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kimsanguine/hplan/orchestration
Install

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.

Any agent
npx skills add kimsanguine/hplan --skill orchestration
Clone the repo
git clone --depth 1 https://github.com/kimsanguine/hplan

Made for: Claude Code.

Or install architect, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for orchestration

README.md
[![agentmods](https://agentmods.dev/badge/skills/kimsanguine/hplan/orchestration.svg)](https://agentmods.dev/skills/kimsanguine/hplan/orchestration)
Your own site
<a href="https://agentmods.dev/skills/kimsanguine/hplan/orchestration"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/orchestration.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,697 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00099 $0.04697
Opus 5 $0.00049 $0.02348
Sonnet 5 $0.00020 $0.00939
Haiku 4.5 $0.00010 $0.00470

Measured 8d ago against content hash 7c64be195abf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

orchestration 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 8d 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.

architect/skills/orchestration/SKILL.md · 403 lines

How it starts

The opening of the file, as written. The whole thing — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestration Pattern

멀티 에이전트 오케스트레이션 패턴 선택 및 설계

Core Goal

  • 에이전트 간 협력 방식(순차, 병렬, 라우팅, 계층)을 요구사항에 맞게 선택하여 불필요한 복잡성 제거하고 성능 최적화
  • 각 패턴의 장단점을 명확히 이해하고 지연시간, 에러율, 비용을 예측하는 의사결정 프레임워크 제공
  • "가장 간단한 패턴부터 시작"하는 점진적 업그레이드 원칙 적용

Trigger Gate

Use This Skill When

  • 2개 이상의 에이전트가 협력해야 하는 시스템 설계 또는 평가
  • 기존 오케스트레이션이 성능 문제(지연, 비용)를 보이는 경우
  • 패턴 선택의 의사결정을 문서화하고 정당화해야 하는 경우

Route to Other Skills When

  • 선택한 패턴의 세부 구현 (3-tier 위계 구조) → orchestration (Hierarchical pattern 상세 섹션 참조)
  • 작업별 LLM 모델 선택/비용 최적화 → orchestration --pattern router (Model Routing 상세 섹션 참조)
  • 멀티 에이전트 간 메모리 공유 → memory-arch (저장소 전략)
  • 패턴의 경제성 분석 → strategy --focus biz-model (비용 모델)

Boundary Checks

  • 단일 에이전트로 충분하면 → 오케스트레이션 패턴 불필요, 단일 prompt 또는 routing만 고려
  • 패턴이 너무 복잡하면 → "가장 간단한 패턴"으로 시작 원칙 위반, 재평가 필요
  • 에러 복구 전략이 없으면 → 선택한 패턴을 안전하게 구현 불가, 먼저 에러 처리 정의

개념

에이전트 시스템의 복잡도와 요구사항에 따라 적절한 오케스트레이션 패턴을 선택한다. 잘못된 패턴 선택은 불필요한 복잡성이나 성능 병목을 만든다.

Instructions

You are selecting and designing an orchestration pattern for: $ARGUMENTS

Step 1 — Assess Requirements

Answer these questions to determine pattern fit:

  • How many distinct tasks are involved?
  • Are tasks dependent on each other's outputs?
  • Is the workflow deterministic or dynamic?
  • What is the latency tolerance?
  • What is the error tolerance?

Step 2 — Pattern Selection Matrix

Pattern When to Use Complexity Latency
Sequential Chain Tasks have strict dependencies Low High (sum of all)
Parallel Fan-out Independent tasks, same input Medium Low (max of all)
Router Input determines which agent Medium Low (single path)
Hierarchical Complex, multi-level workflows High Variable
Event-Driven Reactive, async workflows High Variable

Step 3 — Pattern Deep Dive

Sequential Chain
Input → Agent A → Agent B → Agent C → Output
  • Best for: pipelines where each step transforms data
  • Risk: single point of failure, high total latency
  • PM Example: Research → Analysis → Report Draft → Review

Read the full file on GitHub · 403 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 8d ago First seen · 403 lines · 99 tokens per session scan A 7c64be195abf

Subscribe to this mod's changes

orchestration is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 22d ago), licensed MIT. It adds 99 tokens to every session and 4,697 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

codex-setup

Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.

sd0xdev/sd0x-harness · 65 tokens

smart-rebase

Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…

sd0xdev/sd0x-harness · 131 tokens

recap-doc

Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…

sd0xdev/sd0x-harness · 114 tokens

runbook

Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).

sd0xdev/sd0x-harness · 59 tokens

test-review

Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.

sd0xdev/sd0x-harness · 56 tokens

debug

Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.

sd0xdev/sd0x-harness · 67 tokens