orchestrate

orchestrate is a skill for Claude Code from AcKeskin/contexture. It costs 71 tokens per session (5,191 once invoked), scanned A, original, MIT.

A coordinator for splitting one goal across several coding agents and bringing their work back into one result.

In plain words
What is it for?
It helps break down work, place tasks in separate Git worktrees, keep the work scoped, and verify the final combined result.
Why use it?
It addresses the coordination problems that arise when parallel tasks depend on one another and must be combined consistently.

Skill for Claude Code

Written for Claude Code: SubagentStop hook event. Also seen: mentions subagents; mentions Codex.

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.

agentmods
npx agentmods add skills/ackeskin/contexture/orchestrate
Any agent
npx skills add AcKeskin/contexture --skill orchestrate
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

Made for: Claude Code.

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/ackeskin/contexture/orchestrate.svg)](https://agentmods.dev/skills/ackeskin/contexture/orchestrate)
Your own site
<a href="https://agentmods.dev/skills/ackeskin/contexture/orchestrate"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/orchestrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,191 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00071 $0.05191
Opus 5 $0.00036 $0.02596
Sonnet 5 $0.00014 $0.01038
Haiku 4.5 $0.00007 $0.00519

Measured 2d ago against content hash 343afc4219c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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 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.

skills/orchestrate/SKILL.md · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrate

Overview

You own the convergence discipline for goal-directed concurrency: one objective decomposed into interdependent units that several workers handle in parallel and then reconverge into one coherent result. This is the coordination job the existing organs leave open.

  • using-git-worktrees isolates one branch into one worktree. It says nothing about N concurrent workspaces or which work belongs in a worktree vs the shared tree.
  • dispatch fans out subagents for independent failures and synthesizes by collection ("read each summary, check for conflicts"). That is the wrong shape for a single goal decomposed into interdependent parts, where the hard work is convergence, not collection.

/orchestrate is a caller of both — it adds decompose (Q1), place (Q2), keep-on-track (Q3.5), and converge (Q4) around them. It never re-implements dispatch mechanics or worktree setup.

Two research findings constrain the entire protocol:

  1. No mid-flight window. A dispatched subagent returns one final result — the parent cannot stream its progress. So keep-on-track is prevent-at-dispatch, never live supervision.
  2. Prompt scope fences have ~0% deterrent effect. A unit told "do not write outside X" attempts out-of-scope writes at the same rate as one told nothing. Hard placement (a worktree / allowlist) is the only real scope enforcement — it outperforms prompt instruction 2.6–7.6×. Positive scope in the prompt is supplementary attention-guidance; negative "do NOT" fences are dropped from the boilerplate entirely.

Announce at start: "I'm using the orchestrate skill to fan this goal out and converge it."

When to run

Mode A — manual only. Never auto-fires. Fanning a goal across agents or worktrees is expensive; the user must opt in.

  • User types /orchestrate.
  • Natural language: "split this across agents", "set up worktrees for these branches", "fan this goal out", "run these in parallel and combine".

Read the full file on GitHub · 359 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. 2d ago First seen · 359 lines · 71 tokens per session scan A 343afc4219c7

Subscribe to this mod's changes

orchestrate is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 5,191 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 2026-09-03.

Related

Other skills, from other repositories

core-workflow

Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, testing, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, testing strategy, and communication standards.

travisjneuman/.claude · 53 tokens

commit-context

Trace a file, function, or line back to the agent session that produced its current commit. Use when the user asks "why is this code here", "what was the agent doing when this changed", "who wrote this", or wants context on a specific location in the codebase.

rohitg00/agentmemory · 61 tokens

commit-history

List recent git commits linked to agent sessions, optionally filtered by branch or repo. Use when the user asks "show agent commits", "what has the agent shipped", "list linked commits", or wants commits with their session context.

rohitg00/agentmemory · 49 tokens

workflow-patterns

Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.

wshobson/agents · 35 tokens

git-commit

Analyze changes with Git only and auto-generate conventional commit messages with optional emoji; suggests splitting commits when needed, runs local Git hooks by default (use --no-verify to skip).

UfoMiao/zcf · 41 tokens

install-skill

Install a community skill pack into this fork from a GitHub repo and ship it as an auto-merged PR.

aeonfun/aeon · 26 tokens