orchestrate

orchestrate is a command for coding agents from s3rgiosan/agent-smith. It costs 21 tokens per session (1,365 once invoked), scanned A, original, MIT.

An operating mode for coordinating a task by planning it, delegating execution to less costly agents, and reviewing their results. The coordinator remains focused on decisions, work briefs, and verification.

In plain words
What is it for?
It helps split a task into assignments, send those assignments to other agents, decide which work depends on other work, and check the returned results against the plan.
Why use it?
It limits the time spent by the main reasoning model on routine implementation while keeping planning and quality checks centralized. This is useful when work can be divided into independent pieces.

Command

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/s3rgiosan/agent-smith/orchestrate
Clone the repo
git clone --depth 1 https://github.com/s3rgiosan/agent-smith

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/commands/s3rgiosan/agent-smith/orchestrate.svg)](https://agentmods.dev/commands/s3rgiosan/agent-smith/orchestrate)
Your own site
<a href="https://agentmods.dev/commands/s3rgiosan/agent-smith/orchestrate"><img src="https://agentmods.dev/badge/commands/s3rgiosan/agent-smith/orchestrate.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,365 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 $0.00021 $0.01365
Opus 5 $0.00010 $0.00682
Sonnet 5 $0.00004 $0.00273
Haiku 4.5 $0.00002 $0.00136

Measured 3d ago against content hash 62e5100c7dbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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/orchestrate.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator mode

This turn runs on Fable. Fable time is the scarce resource here, so it buys three things and nothing else:

  • Judgment about what to do — reading the request, choosing an approach, splitting it into pieces, spotting what could go wrong
  • Handing pieces out — writing briefs a fresh subagent can act on, and deciding what runs now versus after something else
  • Judgment about what came back — checking the work against the brief, integrating it, catching the gaps

Any keystroke of actual work belongs to a cheaper model. Dispatch it with the Agent tool and a model override.

The task

$ARGUMENTS

If no task text was substituted above, ask what to orchestrate. Do not pick something plausible and start.

About the model switch

model: fable in this file lasts until the end of this turn. The next prompt goes back to whatever the session was set to.

  • Session already on Fable → nothing to say.
  • Session on something else and the job needs more than one turn → say once that /orchestrate should be re-invoked on the turns that are actually planning or verification turns, and left alone on the rest. Do not suggest /model fable as the default; a session pinned to Fable pays Fable rates for every turn, including the ones that only relay a subagent result.

Never state or imply that the session model itself changed. It did not.

One edge: a session running an extended-context variant (e.g. fable[1m]) drops to the plain fable context window for this turn, because the override wins. Only relevant when the conversation is already enormous; if that bites, /model fable[1m] and skip re-invoking this command.

Who gets what

The work Where it goes
Deciding the approach, breaking the task apart Fable, right here
Checking returned work, integrating it, the final call Fable, right here
Finding things in the codebase, "where does X live", "how does Y work" Explore, sonnet
Building something the brief already specifies precisely general-purpose, sonnet
Work where the shape isn't settled, or a bug that resists the obvious fix general-purpose, opus
Renames, repetitive edits, scaffolding, formatting, boilerplate haiku — most edit volume is mechanical, so this is the default for it
Tests against a spec that already exists sonnet
Running the build, tests, or linter general-purpose, haiku — it returns pass/fail plus the failing lines, so raw output never lands in this turn

Read the full file on GitHub · 73 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. 3d ago First seen · 73 lines · 21 tokens per session scan A 62e5100c7dbe

Subscribe to this mod's changes

orchestrate is a command published in the GitHub repository s3rgiosan/agent-smith (2 stars, last pushed 27d ago), licensed MIT. It adds 21 tokens to every session and 1,365 once invoked, about $0.0001 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 2026-08-31.