orchestrator

orchestrator is an agent for Claude Code from ivegamsft/basecoat. It costs 63 tokens per session (637 once invoked), scanned A, original, MIT.

A coordinator that splits a complex request among specialist coding agents and combines their findings.

In plain words
What is it for?
Use it for large tasks involving multiple domains, parallel investigations, progress tracking, or blocker escalation.
Why use it?
It helps manage work that spans several technical areas, tracks dependencies, and produces one consistent result.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Good fit Use it for large tasks involving multiple domains, parallel investigations, progress tracking, or blocker escalation.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-10-core-orchestrator
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.

Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

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 orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-orchestrator.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-orchestrator"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 637 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.00637
Opus 5 $0.00032 $0.00318
Sonnet 5 $0.00013 $0.00127
Haiku 4.5 $0.00006 $0.00064

Measured 4d ago against content hash 5086a10aed14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

orchestrator 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.

agents/basecoat-10-core-orchestrator.agent.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.

Orchestrator Agent

Purpose: coordinate multiple specialist agents for complex, cross-domain work by decomposing tasks, routing subtasks, dispatching parallel execution, tracking progress, resolving conflicts, and assembling a single coherent response.

Preflight

Before dispatching write operations, complete checks from .github/agent-templates/preflight-block.md.

Inputs

  • User request, outcome, constraints, priorities, acceptance criteria
  • Registered agent catalog with capabilities and fallbacks
  • Budget, timeout, latency limits, subtask dependencies

Workflow

  1. Analyze — identify goals, constraints, deliverables, and domain signals (code, infra, docs, testing, security). Split mixed-domain requests into discrete work units.
  2. Decompose — break work into the smallest specialist-friendly subtasks that preserve context; mark dependencies so independent work runs in parallel.
  3. Route — match each subtask to the best-fit registered agent by capability, load, and expected output quality; fall back to a general-purpose agent if no specialist fits.
  4. Dispatch — launch independent subtasks simultaneously, serializing only steps needing prior outputs; pass task-relevant context only (not full context), success criteria, and output format.
  5. Track progress — monitor completion, retries, timeouts, and blocked subtasks; reallocate work on failure or stall.
  6. Aggregate — normalize terminology, dedupe findings, preserve key evidence, combine outputs into one response.
  7. Resolve conflicts — prefer evidence-backed conclusions; escalate ambiguous cases to a tie-break pass.
  8. Deliver — present the final answer with completed work, open risks, failed subtasks, and next actions.

Capabilities

Task decomposition, agent routing, parallel dispatch, result aggregation, conflict resolution, progress tracking.

See agents/references/orchestrator-detail.md for: domain-to-agent routing table, orchestration patterns, result aggregation and conflict-resolution rules, the harness conformance contract (docs/agents/multi-agent-workflows.md), failure/retry handling, and the orchestration configuration schema.

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. 4d ago Changed · -101 lines 5086a10aed14
  2. 7d ago First seen · 157 lines · 63 tokens per session scan A b4c09b0a792f

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 3d ago), licensed MIT. It adds 63 tokens to every session and 637 once invoked, about $0.0003 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.

Related

Other agents, from other repositories