Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add divyamrastogi/model-orchestration/plugin install model-orchestrationWrote 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/divyamrastogi/model-orchestration/orchestrating-model-workers)<a href="https://agentmods.dev/skills/divyamrastogi/model-orchestration/orchestrating-model-workers"><img src="https://agentmods.dev/badge/skills/divyamrastogi/model-orchestration/orchestrating-model-workers.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 5.1 | $0.00124 | $0.02206 |
| Opus 5 | $0.00062 | $0.01103 |
| Sonnet 5 | $0.00025 | $0.00441 |
| Haiku 4.5 | $0.00012 | $0.00221 |
Grade A, and why
orchestrating-model-workers scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -o /dev/null -w '%{http_code}\n' <base-url>/v1/messages -X POST How it starts
The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrating Model Workers
Run the smartest model as a manager (plans, judges, reviews) and dispatch
implementation and token-hungry work to workers — isolated headless Claude
Code instances backed by any Anthropic-compatible API. One claude binary,
many identities: each worker owns a config dir under ~/.claude-workers/<name>/
with its own settings, auth, and history, so the user's main Anthropic setup is
never touched.
When NOT to use
- Provider has no Anthropic-compatible endpoint (GUI apps like ZCode have no CLI; OpenAI-format-only APIs need a translating proxy such as LiteLLM first).
- Single quick task — dispatch overhead beats the savings; just do it.
Setting up a worker
Optional pre-flight — sanity-check the endpoint before creating anything (expect an HTTP 4xx auth error, NOT 404 or a DNS failure):
curl -s -o /dev/null -w '%{http_code}\n' <base-url>/v1/messages -X POST
Run the bundled script (every command prints its next steps; create refuses
to overwrite an existing worker — on "already exists", use list to inspect
and remove to rebuild, don't retry blindly). Prefer a preset — run
setup-worker.sh presets for known providers, and when the user hasn't named
one, offer them the preset list as a choice instead of asking for URLs:
"${CLAUDE_PLUGIN_ROOT}/scripts/setup-worker.sh" create glm --provider zai
# or fully manual, for any Anthropic-compatible endpoint:
"${CLAUDE_PLUGIN_ROOT}/scripts/setup-worker.sh" create glm \
--base-url https://api.z.ai/api/anthropic \
--sonnet glm-5.3 --opus glm-5.3 --haiku glm-5.3-flash
Providers ship new models but expose no "latest" alias, so mappings go stale. To re-sync an existing worker to the provider's newest models (newest full-size model → sonnet/opus, newest fast-tier model → haiku):
"${CLAUDE_PLUGIN_ROOT}/scripts/setup-worker.sh" refresh-models glm --dry-run # preview
"${CLAUDE_PLUGIN_ROOT}/scripts/setup-worker.sh" refresh-models glm # apply
What ships with it
1 file 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.
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.
- 8d ago First seen · 162 lines · 124 tokens per session scan A b28c71c3ff66
orchestrating-model-workers is a skill published in the GitHub repository divyamrastogi/model-orchestration (4 stars, last pushed 9d ago), licensed MIT. It adds 124 tokens to every session and 2,206 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…