orchestrate

A coordinator command for requests that span several specialist areas. It breaks the request into parts, sends them to specialist agents, resolves overlaps, and combines the results into one deliverable.

In plain words
What is it for?
Use it for multi-domain work that needs decomposition, specialist assignments, conflict resolution, and a synthesized result.
Why use it?
It helps prevent gaps and contradictions when one task needs expertise from multiple domains. It requires a host that can create subagents, such as Claude Code.

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/emtcmca/promptsmith/orchestrate
Clone the repo
git clone --depth 1 https://github.com/emtcmca/promptsmith
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 763 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 $0.00043 $0.00763
Opus 5 $0.00022 $0.00381
Sonnet 5 $0.00009 $0.00153
Haiku 4.5 $0.00004 $0.00076

Measured 2d ago against content hash ee537f683f92, 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 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.

commands/orchestrate.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the promptsmith coordinator on a request that spans more than one specialist. Output is a single synthesized deliverable plus the decomposition, seam owners, resolved conflicts, and any coverage gaps. Layer 2 — this dispatches live subagents, so it needs a host that can spawn them (Claude Code). For a single-domain task, use /promptsmith:sharpen instead.

Step 1 — Load the engine

Read ${CLAUDE_PLUGIN_ROOT}/skills/orchestration/SKILL.md in full. It defines the coordinator pipeline. (That engine itself loads the Layer 1 prompt-engineering skill in its Step 1.)

Paths. ${CLAUDE_PLUGIN_ROOT} is this plugin's install directory, substituted automatically — never a literal folder in the user's project. If promptsmith was installed standalone (README Option B, no plugin root), read from ~/.claude/ instead: ~/.claude/skills/…, ~/.claude/promptsmith-templates/, ~/.claude/promptsmith-lenses/, ~/.claude/promptsmith-agents/. Never resolve these against the user's working directory.

Step 2 — Parse arguments

Parse $ARGUMENTS:

  • --dry — stop after the decomposition + plan (Step 5). Show slices, slice→agent map, seams, conflicts, coverage gaps, and fan-out size. Do not dispatch. Useful for inspecting routing.
  • --gate — always pause for approval before fan-out (override the smart threshold).
  • --no-gate — never pause for approval; run autonomously through dispatch + synthesis. Does not waive the intent gate (Step 0) or the adversarial-verify gate (Step 6.5) — those always apply.
  • (default) — smart threshold: auto-run small/low-risk plans (≤ 3 agents, nothing irreversible); gate larger or risky fan-outs. See engine Step 5.
  • Everything else = the multi-domain request to coordinate.

If the request is empty, ask what to coordinate and stop.

Step 3 — Run the pipeline

Execute the orchestration pipeline (engine Steps 0–8): 0. Gate — if it's really single-domain, fall back to /promptsmith:sharpen or the one agent.

  1. Sharpen the query (Layer 1 engine).
  2. Decompose into non-overlapping slices.
  3. Route slices to gallery agents; log uncovered slices as coverage gaps.
  4. Identify seams + conflicts; assign owners; resolve or flag conflicts.
  5. Approval gate (unless --no-gate).
  6. Dispatch each slice's agent as a subagent (parallel where independent).
  7. Assemble + curate into one coherent deliverable.
  8. Report.

Read the full file on GitHub · 56 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 · 56 lines · 43 tokens per session scan A ee537f683f92

Subscribe to this mod's changes

orchestrate is a command published in the GitHub repository emtcmca/promptsmith (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 763 once invoked, about $0.0002 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.