orchestrate

orchestrate is a skill for Claude Code from EternallLight/tgc-skills. It costs 61 tokens per session (2,332 once invoked), scanned C, original, MIT.

A coordinator for carrying out a locked implementation plan by splitting it into separate phases handled by fresh coding agents.

In plain words
What is it for?
Executing multi-phase plans, dispatching one agent per phase, and checking that each phase stops at its defined boundary.
Why use it?
It keeps large builds manageable and gives each phase a clean context grounded in the plan and repository history.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

Part of the tgc-skills plugin — 9 skills shipped together

Good fit Executing multi-phase plans, dispatching one agent per phase, and checking that each phase stops at its defined boundary.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eternalllight/tgc-skills/orchestrate
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 EternallLight/tgc-skills --skill orchestrate
Clone the repo
git clone --depth 1 https://github.com/EternallLight/tgc-skills

Made for: Claude Code.

Or install tgc-skills, the plugin that ships this one along with the rest of its 9 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 orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/skills/eternalllight/tgc-skills/orchestrate/github.svg)](https://agentmods.dev/skills/eternalllight/tgc-skills/orchestrate)
Your own site
<a href="https://agentmods.dev/skills/eternalllight/tgc-skills/orchestrate"><img src="https://agentmods.dev/badge/skills/eternalllight/tgc-skills/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.

agentmods 80×15 button for orchestrate

Your own site · 80×15
<a href="https://agentmods.dev/skills/eternalllight/tgc-skills/orchestrate"><img src="https://agentmods.dev/badge/skills/eternalllight/tgc-skills/orchestrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,332 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00061 $0.02332
Opus 5 $0.00030 $0.01166
Sonnet 5 $0.00012 $0.00466
Haiku 4.5 $0.00006 $0.00233

Measured 10d ago against content hash 4b9f23d48d0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

orchestrate scanned grade C 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 10d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$SESSION_DIR"
skills/orchestrate/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrate — execute a plan via fresh-context agents, one phase at a time

You are the orchestrator (manager). You do NOT write the implementation yourself. You split a locked plan into context-window-sized phases and dispatch one fresh subagent per phase (Agent tool, general-purpose). A new subagent IS a pristine context, so every phase starts clean and re-grounds from disk (the plan + the brief + git log) instead of inheriting a lossy summary.

Three non-negotiables:

  1. One phase per subagent. A phase is a coherent slice of the plan sized to fit one context window (it may be several commits). Split anything bigger; cluster anything trivially small. Never bundle "do phase N then N+1" into one dispatch.
  2. Every phase re-grounds from disk. The phase prompt is self-contained: absolute plan path + this phase's scope + explicit stop point. The agent reads the plan, the brief, and git log fresh — it inherits nothing from you or the previous phase.
  3. Keep the orchestrator's context clean. Never read implementation source files into your own window. Verify phases with git plumbing and narrow greps; delegate deeper checks to a throwaway read-only agent that returns one-line PASS/FAIL.

Prerequisite: a locked plan file exists (written and reviewed — not a vague idea). If there is no plan, write one first and get it approved before orchestrating.

Phase 0 — Inputs

Resolve the absolute path to the plan file and the target repo directory(ies). Read the plan ONCE to derive the phase list — after that, rely on disk, not memory.

Phase 1 — Split the plan into phases (+ detect parallel lanes)

Parse the plan into an ordered list of phases. For each phase record:

  • number + one-line title and which plan section(s) it covers;
  • repo it touches (its lane);
  • a description: concrete scope + an explicit stop point ("…and nothing else");
  • GATED? — true if irreversible or outward-facing (deletes code, deploys, runs migrations, hits staging/prod). Gated phases need explicit human OK before they run;
  • any watch-items (risks to carry into later phase prompts).

Read the full file on GitHub · 200 lines

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. 10d ago First seen · 200 lines · 61 tokens per session scan C 4b9f23d48d0f

Subscribe to this mod's changes

orchestrate is a skill published in the GitHub repository EternallLight/tgc-skills (8 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 2,332 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 83 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens