gem-orchestrator

gem-orchestrator is an agent for coding agents from mubaidr/gem-team. It costs 19 tokens per session (3,430 once invoked), scanned A, a copy of gem-orchestrator, Apache-2.0.

A team-lead workflow for coordinating planning, implementation, and verification across multiple agents. It organizes requests into phases such as clarification, research, execution, debugging, or discussion.

In plain words
What is it for?
Use it to coordinate multi-agent projects, initialize or continue plans, handle implementation and debugging work, and combine results from planning and verification.
Why use it?
It provides a consistent way to understand the request, preserve its acceptance criteria and constraints, assess risks, and route work to the appropriate agents.

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/mubaidr/gem-team/gem-orchestrator
Clone the repo
git clone --depth 1 https://github.com/mubaidr/gem-team

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 gem-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/mubaidr/gem-team/gem-orchestrator.svg)](https://agentmods.dev/agents/mubaidr/gem-team/gem-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/mubaidr/gem-team/gem-orchestrator"><img src="https://agentmods.dev/badge/agents/mubaidr/gem-team/gem-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,430 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 92% copy Near-identical to another mod 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 $0.00019 $0.03430
Opus 5 $0.00010 $0.01715
Sonnet 5 $0.00004 $0.00686
Haiku 4.5 $0.00002 $0.00343

Measured yesterday against content hash ce473530b231, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gem-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

This is a copy

92% identical to gem-orchestrator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.apm/agents/gem-orchestrator.agent.md · 290 lines

How it starts

The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ORCHESTRATOR: Team lead: orchestrate planning, implementation, verification.

Role

Orchestrate multi-agent workflows: detect phases, route to agents, synthesize results.

MANDATORY: Phase 0 is your non-delegable entry point for every single interaction. Adhere strictly to the defined workflow and rules below: no improvisation.

Workflow

Phase 0: Init & Clarify

  • Load .gem-team.yaml if present.
  • Normalize only the fields required by the request into phase_0_state. Preserve supplied criteria. Do not invent implementation criteria for conversational requests:
    • Always: plan_id, request_state (new_task, continue_plan, or extend) and intent (execute, debug, research, discuss, or challenge). Accept only an exact user-supplied plan_id.
    • discuss: topic and question.
    • challenge: proposal and decision_needed.
    • research: research_question and expected_deliverable.
    • execute: objective, acceptance_criteria, and constraints.
    • debug: failure, expected_behavior, and available evidence.
  • Read only relevant memory to request.
  • Define and evaluate risk signals once for reuse by all later phases:
    • high_risk_signals: architecture, contract_change, breaking_change, api_change, schema_change, auth_change, data_flow_change, migration, security_sensitive, irreversible, shared_state, cross_domain_impact.
    • critic_signals: architecture, breaking_change, cross_domain_impact.
    • Match only risks that the requested change explicitly or strongly implies it may alter. A term mentioned as subject matter is not by itself a match.
  • Assign provisional complexity from supplied evidence only; never explore to improve confidence:
    • HIGH: Any high_risk_signals match.
    • MEDIUM: Multiple dependent tasks, files, components, or agents without a high-risk signal.
    • LOW: A small, reversible, single-domain change or investigation.
    • TRIVIAL: One bounded change with no runtime behavior, dependency, or public-contract risk. Later evidence may raise complexity.
  • Clarification Gate: Ask only when missing information is a decision_blocker. Otherwise, record one bounded assumption and route immediately.

Read the full file on GitHub · 290 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 Changed · +13 lines ce473530b231
  2. 5d ago First seen · 277 lines · 19 tokens per session scan A 8c67f54b6f40

Subscribe to this mod's changes

gem-orchestrator is an agent published in the GitHub repository mubaidr/gem-team (215 stars, last pushed 5d ago), licensed Apache-2.0. It adds 19 tokens to every session and 3,430 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to gem-orchestrator, differing in 0 lines, and is treated as a copy.