orchestrator

A coordinating agent that manages a development session and sends different problems to specialist agents. It restores project context, checks project health, and offers a small menu of ways to continue.

In plain words
What is it for?
Use it to resume interrupted work, plan features, request advice, run health checks, and coordinate several development tasks.
Why use it?
It reduces the effort of figuring out where work stopped and which specialist should handle the next task. It brings project plans, task status, version-control history, and governance information into one view.

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/nxtg-ai/forge-plugin/orchestrator
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,014 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 $0.00000 $0.02014
Opus 5 $0.00000 $0.01007
Sonnet 5 $0.00000 $0.00403
Haiku 4.5 $0.00000 $0.00201

Measured 2d ago against content hash a0d51d9561fa, 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 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.

docs/agents/orchestrator.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrator

The command center that coordinates your entire development session -- context restoration, agent delegation, health checks, and strategic advice through a single 4-option menu.

Level L1 Vibe Coder
Category Core Workflow
Model Opus

What It Does

The Orchestrator is the conductor of the entire NXTG-Forge experience. It is the first agent you interact with and the one that decides which specialist agents handle which problems. When you activate Forge, the Orchestrator presents a canonical 4-option menu -- Continue/Resume, Review & Plan Features, Soundboard, Health Check -- and then coordinates everything that follows.

What makes the Orchestrator more than a menu is its context intelligence. When you choose "Continue," it does not just show you a file list. It reads your governance state, git history, orchestrator task board, and master plan to reconstruct exactly where you left off. It tells you which tasks are pending, which are blocked, whether your code has drifted from the project vision, and what the smartest next step is. The "pick up where we left off" experience should feel like having a senior engineer who was in the room yesterday.

The Orchestrator is also the delegation layer. When you choose to plan a feature, it invokes the Planner. When you want a health check, it coordinates Detective, Security, and the governance MCP tools. When you want to soundboard an idea, it enters discussion mode and provides strategic advice without executing any changes. It understands natural language -- "let's keep going," "I want to add a new feature," "how is my code quality?" all route to the correct workflow without requiring you to remember option numbers.

When to Use It

  • Starting a development session: When you activate Forge with /enable-forge or similar, the Orchestrator presents the command center and helps you orient.
  • Resuming previous work: When you say "pick up where we left off" or "continue from yesterday," the Orchestrator restores your full context including branch, tasks, and plan state.
  • Needing strategic advice: When you want to discuss approaches, architectural trade-offs, or priorities without committing to implementation.
  • Checking project health: When you want a comprehensive view of code quality, test coverage, security posture, task completion rates, and vision alignment.

Read the full file on GitHub · 148 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 · 148 lines · 0 tokens per session scan A a0d51d9561fa

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,014 tokens. 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