A multi-session coordinator that turns one natural-language goal into several planned coding tasks run in parallel terminal sessions. It coordinates planning, implementation, review, integration testing, and merging with your approval at key points.

Splitting a larger development goal into independent tasks, assigning them to separate sessions, reviewing their results, testing the combined changes, and merging them.

It organizes work that is too large or parallel for one coding session and keeps task coordination, review, and final integration in one workflow.

orchestrate — Skill for Claude Code by choiyounggi/dev-loop

Install

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.

Claude Code

/plugin marketplace add choiyounggi/dev-loop

Claude Code

/plugin install dev-loop

Made for: Claude Code.

Or install dev-loop, the plugin that ships this one along with the rest of its 9 skills, 11 agents, 6 hooks, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/choiyounggi/dev-loop/orchestrate/github.svg)](https://agentmods.dev/skills/choiyounggi/dev-loop/orchestrate)

Your own site

<a href="https://agentmods.dev/skills/choiyounggi/dev-loop/orchestrate"><img src="https://agentmods.dev/badge/skills/choiyounggi/dev-loop/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/choiyounggi/dev-loop/orchestrate"><img src="https://agentmods.dev/badge/skills/choiyounggi/dev-loop/orchestrate.svg" alt="Reviewed on agentmods" width="80" 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 25,567 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.25567
Opus 5.5	$0.00028	$0.10227
Sonnet 5.5	$0.00014	$0.05113
Haiku 4.5	$0.00007	$0.02557

Measured yesterday against content hash df6c890060fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

orchestrate scanned grade D with 2 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 yesterday.

The scan reads SKILL.md. This mod also ships 24 executable files (scripts/ask-coordinator.sh, scripts/collect-status.sh, scripts/escalation-dir.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

pre-approve the four worker-management scripts in ~/.claude/settings.json?"

Recursive force deletehighDestructive command

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

routine in-worktree work (`rm -rf ./build`, `git checkout .`) turns into a

skills/orchestrate/SKILL.md · 1,461 lines

How it starts

The opening of the file, as written. The whole thing — 1,461 lines — stays where its author put it; the contents beside it link to each section on GitHub.

orchestrate — multi-session orchestrator

You are the orchestrator. You do not implement — sessions do. You clarify, decompose, distribute, review, integrate, and merge. Autonomy lives inside the implementation loop; two human gates bracket it (task-split, pre-merge).

Scripts referenced below live in ${CLAUDE_PLUGIN_ROOT}/skills/orchestrate/scripts/. Communication: session→orchestrator via each worker's OWN worktree-local .orchestration/status/<task>.json (never the coordinator's checkout — a worker writing there can hit a guardrails permission prompt no human is watching, issue #167), collected into the canonical .orchestration/status/ by scripts/collect-status.sh (Phase 3 step 1, and automatically each poll via watch-status.sh — see Session knobs); orchestrator→session via launch-session.sh (the first prompt) then send-prompt.sh (every later one), carrying templates/session-prompt.md §1–§4 on tmux, or the Task --spec (same file, §O1–§O4) on Orca.

Asking the user — every question is a chooser (REQUIRED)

Every question this skill puts to the user is delivered with the AskUserQuestion tool, so they answer by selecting an option instead of typing a reply. Prose in the turn is the briefing (task list, graph, slot count, cost note, diff); the decision is always the tool call. This covers Phase 0 frontier rounds, Gate 1 (task split and substrate), Gate 2, a Phase 3 deadlock, and any worker escalation that needs a human verdict.

Required shape

One call per round, up to 4 questions in it. A frontier wider than 4 → back-to-back calls of ≤4 questions, numbering continuous across them; never one question per turn.
Each question carries 2–4 options; the recommended answer is option 1, its label suffixed (Recommended). header ≤12 chars.
Options are the concrete outcomes ("approve as proposed", "drop task 3", "Orca"), not a yes/no restatement of the prose.
multiSelect: true when the items are independent (e.g. which optional tasks to include).
Free-text is already available to the user as "Other" — never author an "Other" option.

Read the full file on GitHub · 1,461 lines

Files

What ships with it

27 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.

yesterday Changed · +47 lines df6c890060fa
8d ago Changed · +5 lines 5d403eade2fd
10d ago Changed · +86 lines 8ad7813c7b6c
29d ago Changed · +62 lines 478786adb630
1mo ago Changed · +132 lines 6cd25a585a71
1mo ago Changed · +37 lines c0a17c3386ff
1mo ago Changed · +82 lines e5939a23f058
1mo ago First seen · 1,010 lines · 71 tokens per session scan D 486f0e036911

Subscribe to this mod's changes

orchestrate is a skill published in the GitHub repository choiyounggi/dev-loop (6 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 25,567 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Claude Code Planning best-practices claude-code-plugin developer-tools knowledge-base llm-agents

learn

Use when users /learn, save, remember, or distill lessons.

tigerless-labs/autoharness · 17 tokens

building

Use when writing production code test-first: the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns.

romiluz13/cc10x · 43 tokens

cc10x-guide

Answers questions about cc10x itself — what it is, how to install and configure it, how the router, workflows, memory, and hooks operate, and how to troubleshoot. Use this skill when: the user asks ABOUT cc10x — "what is cc10x", "how do I configure cc10x", "why isn't cc10x activating", "how do cc10x workflows work"…

romiluz13/cc10x · 231 tokens

memory-and-handoff

Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.

romiluz13/cc10x · 70 tokens

plan-review-gate

Use after saving a non-trivial plan or decision RFC when a fail-closed feasibility, completeness, and alignment review must block execution.

romiluz13/cc10x · 32 tokens

codebase-design

Canonical deep-module vocabulary (module, interface, depth, seam, adapter, leverage, locality) for designing a module's shape — a lot of behaviour behind a small interface at a clean seam, testable through that interface. The single source of truth for these terms; other skills (architecture, codebase-hygiene) point…

romiluz13/cc10x · 109 tokens

orchestrate