orchestrate-tasks

orchestrate-tasks is a command for Claude Code from adawalli/nexus. It costs 0 tokens per session (1,729 once invoked), scanned A, original, MIT.

A command that coordinates implementation of a feature from an existing tasks.md file, assigning each task group to a dedicated agent in several ordered phases.

In plain words
What is it for?
Use it to create an orchestration roadmap and run the task groups for a spec. A spec is a written description of a feature and its requirements.
Why use it?
It removes the need to manage task groups and implementation order manually. It also tells you when a tasks.md file is missing and how to create the required planning files.

Command for Claude Code

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 commands/adawalli/nexus/orchestrate-tasks
Clone the repo
git clone --depth 1 https://github.com/adawalli/nexus

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-tasks

README.md
[![agentmods](https://agentmods.dev/badge/commands/adawalli/nexus/orchestrate-tasks.svg)](https://agentmods.dev/commands/adawalli/nexus/orchestrate-tasks)
Your own site
<a href="https://agentmods.dev/commands/adawalli/nexus/orchestrate-tasks"><img src="https://agentmods.dev/badge/commands/adawalli/nexus/orchestrate-tasks.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,729 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 $0.00000 $0.01729
Opus 5 $0.00000 $0.00864
Sonnet 5 $0.00000 $0.00346
Haiku 4.5 $0.00000 $0.00173

Measured 4d ago against content hash b8e0fb1821ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

orchestrate-tasks 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 4d 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.

.claude/commands/agent-os/orchestrate-tasks.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Process for Orchestrating a Spec's Implementation

Now that we have a spec and tasks list ready for implementation, we will proceed with orchestrating implementation of each task group by a dedicated agent using the following MULTI-PHASE process.

Follow each of these phases and their individual workflows IN SEQUENCE:

Multi-Phase Process

FIRST: Get tasks.md for this spec

IF you already know which spec we're working on and IF that spec folder has a tasks.md file, then use that and skip to the NEXT phase.

IF you don't already know which spec we're working on and IF that spec folder doesn't yet have a tasks.md THEN output the following request to the user:

Please point me to a spec's `tasks.md` that you want to orchestrate implementation for.

If you don't have one yet, then run any of these commands first:
/shape-spec
/write-spec
/create-tasks

NEXT: Create orchestration.yml to serve as a roadmap for orchestration of task groups

In this spec's folder, create this file: agent-os/specs/[this-spec]/orchestration.yml.

Populate this file with with the names of each task group found in this spec's tasks.md and use this EXACT structure for the content of orchestration.yml:

task_groups:
  - name: [task-group-name]
  - name: [task-group-name]
  - name: [task-group-name]
  # Repeat for each task group found in tasks.md

NEXT: Ask user to assign subagents to each task group

Next we must determine which subagents should be assigned to which task groups. Ask the user to provide this info using the following request to user and WAIT for user's response:

Please specify the name of each subagent to be assigned to each task group:

1. [task-group-name]
2. [task-group-name]
3. [task-group-name]
[repeat for each task-group you've added to orchestration.yml]

Simply respond with the subagent names and corresponding task group number and I'll update orchestration.yml accordingly.

Using the user's responses, update orchestration.yml to specify those subagent names. orchestration.yml should end up looking like this:

Read the full file on GitHub · 181 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. 4d ago First seen · 181 lines · 0 tokens per session scan A b8e0fb1821ec

Subscribe to this mod's changes

orchestrate-tasks is a command published in the GitHub repository adawalli/nexus (23 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,729 tokens. 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 2026-08-30.