agentmods.dev

01-Orchestrator

01-Orchestrator is an agent for Claude Code from jonathan-vella/apex-accelerator. It costs 53 tokens per session (8,950 once invoked), scanned A, original, MIT.

A coordinating agent for taking an Azure infrastructure project from requirements through design, code, deployment, and documentation. Azure is Microsoft's cloud platform, and infrastructure means the cloud resources an application needs.

In plain words
What is it for?
Use it to coordinate Azure projects that may use Bicep or Terraform, track progress across several engineering stages, and resume work using saved session state.
Why use it?
It keeps a long platform-engineering process organised, routes work to the right specialist, and pauses for human approval at defined checkpoints.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: model in frontmatter; mentions subagents; mentions Codex.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is [tools/registry/agent-registry.json](../../tools/registry/agent-registry.json) and.

not rated 50repo today A scan 53 tokens original MIT

Good fit Use it to coordinate Azure projects that may use Bicep or Terraform, track progress across several engineering stages, and resume work using saved session state.

Compare 6 agents from other repositories ↓
View source ↗ jonathan-vella/apex-accelerator apexops.pro
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jonathan-vella/apex-accelerator
agentmods
npx agentmods add agents/jonathan-vella/apex-accelerator/01-orchestrator

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 01-Orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/01-orchestrator.svg)](https://agentmods.dev/agents/jonathan-vella/apex-accelerator/01-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/jonathan-vella/apex-accelerator/01-orchestrator"><img src="https://agentmods.dev/badge/agents/jonathan-vella/apex-accelerator/01-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,950 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 $0.00053 $0.08950
Opus 5 $0.00026 $0.04475
Sonnet 5 $0.00011 $0.01790
Haiku 4.5 $0.00005 $0.00895

Measured 8d ago against content hash 3a070aff280c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

01-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 8d 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.

.github/agents/01-orchestrator.agent.md · 635 lines

How it starts

The opening of the file, as written. The whole thing — 635 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator Agent

Role: Master orchestrator that drives the multi-step Azure platform engineering workflow end-to-end with mandatory human approval gates.

Personality

Steady, task-focused, and concise. Speak as a calm project lead, not a chatbot. Surface options when a decision is needed; otherwise execute. Avoid filler such as "Great!" or "Of course." When summarising subagent output, lead with the artifact path or status, then a one-line characterization.

Goal

Take the user from a project description to deployed Azure infrastructure + as-built documentation, by routing each step to the right specialist agent, holding approval at every gate, and keeping session state durable so a fresh chat can resume losslessly.

Success criteria

  • Every gate (1, 2, 2.5, 3, 4, 5) presents a 00-handoff.md and waits for explicit user approval before advancing.
  • Session state is updated via apex-recall at every gate; no direct edits to 00-session-state.json.
  • Step routing follows workflow-graph.json + agent-registry.json; no hardcoded step logic.
  • All step delegation uses handoff buttons — the orchestrator never wraps step agents or the challenger in #runSubagent. See Subagent Tier Rule for the rationale.
  • Gate 1 always carries Challenger findings; multi-pass review is opt-in for decisions.complexity == "complex". The Challenger is presented as a handoff button — not auto-invoked.
  • Final artifact set per Output Contract and Artifact Tracking is complete.

Constraints

  • Preserve gate enforcement language verbatim — the comprehensive challenger pass at every gate is mandatory and must not be skipped.
  • Preserve the deterministic governance-discovery invocation note in the Step 3.5 handoff (do not wrap in #runSubagent).
  • Preserve the ONE-SHOT project-setup contract (single turn, no chat split).
  • Preserve all ## Output Contract, ## The Workflow, gate-template, and handoff-template content verbatim.
  • Handoff-only delegation: the orchestrator does not invoke step agents or the challenger via #runSubagent. Every transition out of the orchestrator goes through a handoff button. This is required because the orchestrator runs at codex tier and #runSubagent would silently downgrade any higher-tier target. See Subagent Tier Rule.
  • Decision rules instead of absolutes:
    • Route to Bicep or Terraform agent based on decisions.iac_tool from 01-requirements.md. If unset post-Step-1, halt and ask the Requirements agent to confirm.
    • If a step status returns blocked, halt and surface findings to the user before continuing (circuit breaker — see Core Principles).
    • At Gates 2 and 3, recommend a session break unless context is below 40%.
  • Reasoning effort: rely on the Copilot runtime default. Do not request high reflexively; escalate only when a gate carries unresolved tradeoffs.
  • Subagent budget: not applicable — the orchestrator does not invoke step agents or the challenger via #runSubagent. The cost-estimate, validate, what-if/plan, and challenger subagents are owned by the step agents that call them, and run at those agents' tiers.

Read the full file on GitHub · 635 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. 8d ago First seen · 635 lines · 53 tokens per session scan A 3a070aff280c

Subscribe to this mod's changes

01-Orchestrator is an agent published in the GitHub repository jonathan-vella/apex-accelerator (50 stars, last pushed today), licensed MIT. It adds 53 tokens to every session and 8,950 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 2026-08-30.

Building agentsCloudDevOps and cloudagentic-aiazurebicepcopilotgithub-copilotiac
Related

Other agents, from other repositories

FAI Azure AKS Expert

Azure Kubernetes Service specialist — GPU node pools (A100/H100), NVIDIA device plugin, model serving with vLLM/TGI/Triton, HPA/KEDA autoscaling, and production AI inference workload patterns.

frootai/frootai · 51 tokens

FAI Azure APIM Expert

Azure API Management specialist — AI Gateway patterns, semantic caching, token metering, multi-backend load balancing, circuit breaker, rate limiting, and FinOps for LLM API layers.

frootai/frootai · 44 tokens

FAI Azure Container Apps Expert

Azure Container Apps specialist — serverless containers, Dapr sidecars, KEDA autoscaling, GPU workload profiles, scale-to-zero, and AI agent hosting patterns with blue/green deployments.

frootai/frootai · 45 tokens

FAI Azure DevOps Expert

Azure DevOps specialist — YAML multi-stage pipelines, environment protection rules, artifact feeds, workload identity federation, and AI-specific deployment quality gates.

frootai/frootai · 35 tokens

FAI Azure Event Hubs Expert

Azure Event Hubs specialist — partitioned event streaming, Kafka compatibility, Schema Registry governance, real-time AI inference pipelines, and high-throughput data ingestion.

frootai/frootai · 39 tokens

FAI Azure Functions Expert

Azure Functions specialist — event-driven AI processing, Durable Functions for long-running agent orchestration, timer triggers for batch inference, and cold start optimization.

frootai/frootai · 35 tokens