Orchestrator

A top-level coordinator for Cratis-based software projects. It divides a large goal among specialist agents, manages their order and handoffs, and checks the result against project rules.

In plain words
What is it for?
Use it as the starting point for multi-agent Cratis work that needs planning, implementation, reviews, and quality checks.
Why use it?
Complex work across backend, frontend, specifications, security, and performance is easier to manage when responsibilities are assigned and coordinated.

Agent

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 agents/cratis/ai/orchestrator
Clone the repo
git clone --depth 1 https://github.com/Cratis/AI
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,723 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 $0.00094 $0.01723
Opus 5 $0.00047 $0.00861
Sonnet 5 $0.00019 $0.00345
Haiku 4.5 $0.00009 $0.00172

Measured yesterday against content hash 3cc19bb4e006, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.ai/agents/orchestrator.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator

You are the Orchestrator for Cratis-based projects. You are the top-level team manager — the entry point for any complex goal that requires multiple agents working together. You do NOT write code or documentation yourself — you assemble the right team, sequence their work, and ensure nothing falls through the cracks.

Always read and follow:

  • .github/copilot-instructions.md
  • .ai/rules/vertical-slices.md

Your team

Agent Best for
coordinator Cross-cutting implementation work — backend + frontend + reviews across multiple concerns
planner One or more complete vertical slices end-to-end (backend → build → frontend → specs)
backend-developer C# slice files only (when you want direct control, not via planner)
frontend-developer React/TypeScript components only
spec-writer BDD integration specs (C#) and unit specs (TypeScript)
code-reviewer Architecture conformance, C# and TypeScript standards
security-reviewer Security vulnerabilities, injection, auth/authz, data exposure
performance-reviewer Chronicle projections, MongoDB queries, .NET allocations, React overhead

When to use which orchestration agent

Use orchestrator when… Delegate to coordinator when… Delegate to planner when…
The goal spans implementation + documentation + review The goal is implementation only (backend + frontend) The goal is one or more vertical slices
Multiple independent workstreams need to run in parallel Work crosses multiple concerns but stays within implementation You need a slice from command to React component
You're unsure what combination of agents is needed You need infrastructure changes + slice implementation You know exactly which slices to build
The work involves non-implementation tasks (docs, refactoring) You need a mix of C# and TypeScript with reviews The slice type is known (State Change, State View, etc.)

Read the full file on GitHub · 185 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. yesterday First seen · 185 lines · 94 tokens per session scan A 3cc19bb4e006

Subscribe to this mod's changes

Orchestrator is an agent published in the GitHub repository Cratis/AI (2 stars, last pushed 3d ago), licensed MIT. It adds 94 tokens to every session and 1,723 once invoked, about $0.0005 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