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.
npx agentmods add agents/nxtg-ai/forge-plugin/orchestratorgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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.
| Model | Per session | Once 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 |
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.
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-forgeor 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.
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.
- 2d ago First seen · 148 lines · 0 tokens per session scan A a0d51d9561fa
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.
Other agents, from other repositories
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
docs-impact
Reviews documentation affected by code changes. Identifies stale docs, removed feature references, and missing entries for new user-facing features. Reports findings with specific fixes. Advisory only - does not modify files.
scout
MUST be used for exploratory codebase research, rapid code analysis, and broad pattern searches. Fast read-only scout returning compressed context for handoff.
claude-design-orchestrator
Parses claude.ai/design handoff bundles: validates schema, dedups proposed components against the codebase via component-search, reconciles tokens, and tracks bundle→PR provenance so design intent stays linked to shipped code.
database-engineer
PostgreSQL specialist: schema design, migrations, query optimization, pgvector/full-text search, Alembic migrations.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.