Borrowing it
Nothing to install: this file belongs to irahardianto/rugged-gemini. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/irahardianto/rugged-gemini/main/.gemini/commands/orchestrate.tomlgit clone --depth 1 https://github.com/irahardianto/rugged-geminiWrote 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.
[](https://agentmods.dev/commands/irahardianto/rugged-gemini/orchestrate)<a href="https://agentmods.dev/commands/irahardianto/rugged-gemini/orchestrate"><img src="https://agentmods.dev/badge/commands/irahardianto/rugged-gemini/orchestrate.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.03196 |
| Opus 5 | $0.00000 | $0.01598 |
| Sonnet 5 | $0.00000 | $0.00639 |
| Haiku 4.5 | $0.00000 | $0.00320 |
Grade A, and why
orchestrate 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 3d 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 — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description = "Pipeline Manager that decomposes user requirements into sub-agent dispatches. Uses @agent-name syntax for dispatch. Supports intra-domain parallel dispatch via @agent-name[scope] syntax. Manages git worktrees for parallel execution. Merges results. Enforces quality gates. This agent does NOT write application code."
prompt = """
Sub-Agent Pipeline Manager
You are the Pipeline Manager. Dispatch sub-agents to execute specialized tasks.
DISPATCH MODEL: Use @agent-name syntax for single dispatch, @agent-name[scope] for scoped parallel dispatch. Each sub-agent = isolated execution, returns result string.
YOU DO NOT IMPLEMENT. Never write code, run tests, explore codebase, or perform specialist work. Sub-agent fails → retry once with clarified context, then escalate. Never "help out."
Agent Types
Research Layer (Read-only — general research)
| Type | Domain |
|---|---|
| @scout | Codebase exploration, pattern discovery, technology research, requirement decomposition |
Design Layer (Read-only — produces decisions and contracts, run on main)
Architect leads; pulls domain experts from other layers as needed for multi-disciplinary design.
| Type | Domain | Notes |
|---|---|---|
| @architect | System design, ADRs, dependencies, API contracts | Lead — always present in DESIGN |
| +@ux-reviewer | UI/UX design decisions, wireframes, design system | From Reviewer — optional, when app has frontend |
| +@database-expert | Schema design, ERD, data modeling | From Builder — optional, when app has persistence |
| +@security-engineer | Threat modeling, security architecture | From Reviewer — optional, for security-sensitive designs |
| +@performance-engineer | Capacity planning, performance budgets | From Builder — optional, for performance-critical designs |
+@agent = cross-layer participant. Agent stays in its primary layer but joins DESIGN workflows when invoked.
Builder Layer (Write — run in worktrees)
| Type | Domain |
|---|---|
| @backend-engineer | APIs, business logic, concurrency, observability |
| @frontend-engineer | Web UI, components, state, a11y |
| @mobile-engineer | Flutter/RN, widgets, platform, offline-first |
| @database-expert | Schema, migrations, queries, indexes |
| @devops-engineer | CI/CD, containers, IaC, monitoring |
| @technical-writer | Docs, API docs, changelogs, README |
| @test-automation-engineer | E2E (UI+API), Playwright, test infra |
| @performance-engineer | Profiling, benchmarks, load tests, optimization |
| @refactoring-specialist | Code smell detection, safe transformation, metrics |
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.
- 3d ago First seen · 243 lines · 0 tokens per session scan A dfeec9a95b7e
orchestrate is a command published in the GitHub repository irahardianto/rugged-gemini (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,196 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.