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 YoungjaeDev/my-claude-plugins --skill orchestrategit clone --depth 1 https://github.com/YoungjaeDev/my-claude-pluginsWrote 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/youngjaedev/my-claude-plugins/orchestrate)<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/orchestrate"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/orchestrate/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/youngjaedev/my-claude-plugins/orchestrate"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/orchestrate.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 | $0.00227 | $0.04913 |
| Opus 5.5 | $0.00091 | $0.01965 |
| Sonnet 5.5 | $0.00045 | $0.00983 |
| Haiku 4.5 | $0.00023 | $0.00491 |
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 23d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
orchestrate
Conduct a task through subagents without giving up ownership of the result.
Overview
The main agent conducts; it never becomes one of the workers. Three invariants hold for the whole
run: every delegation is a job card, every returned result passes a quality gate before anything
is built on it, and the orchestrator alone verifies and answers the user. Model and effort are
chosen per job through the worker presets bundled in plugins/dev/agents/, because the Agent
tool overrides model per call but reads effort only from the agent definition
(https://code.claude.com/docs/en/sub-agents#supported-frontmatter-fields, #choose-a-model).
On Codex, check whether subagent spawning is exposed in the session (the subagents page under
https://developers.openai.com/codex/llms.txt describes it). Claude's dev:worker-* presets and
isolation: worktree do not exist there, so the run is either Codex subagents with a hand-made
git worktree add per writing slice, or, when no delegation tool is exposed, inline work that
still uses the job card as its checklist. Inline, steps 4 to 7 read differently: with no worker to
attribute, isolation: worktree and the branch check in step 5 do not apply. An inline run can
still take the same isolation by hand
— git worktree add per writing slice, then the identical step 5 command against that branch — and
should when a slice is large enough that its scope is worth proving. Where it does not, the card's
Paths bound the agent's own edits and the report names every path it wrote; that report is the
completion criterion in place of the gate.
When to use
Delegate when at least one of these holds:
- the task splits into two or more slices that need no result from each other
- one slice would pull so many files into the main context that coordination afterwards suffers
- the task mixes cheap mechanical work with accuracy-critical work that deserves a stronger model
Do the work inline when the change is one known file or location, or when writing the job card
would take longer than the job. A written implementation plan with numbered tasks goes to
superpowers:subagent-driven-development instead.
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.
- 23d ago Changed · +14 lines 5ae9b77bab3f
- 25d ago Changed · +1 lines e366919d2819
- 1mo ago Changed · +94 lines dddc14b04a17
- 1mo ago Changed · +3 lines c048615f515f
- 1mo ago First seen · 143 lines · 227 tokens per session scan A 91e90dc6ede6
orchestrate is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed today), licensed MIT. It adds 227 tokens to every session and 4,913 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-09-16.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…