frontier-orchestrator: Skill for Claude Code

.claude/skills/orchestrate-specialists/SKILL.md

orchestrate-specialists is a skill for Claude Code, Codex from luckeyfaraday/frontier-orchestrator. It costs 77 tokens per session (889 once invoked), scanned A, original, MIT.

A coordination workflow for splitting software work among several coding agents, with Claude Code acting as the lead.

In plain words
What is it for?
Use it for feature work, refactoring, code reviews, bug fixes, migrations, APIs, databases, user interfaces, and related testing or tooling.
Why use it?
It helps divide a large or mixed task into clear pieces and assigns backend, frontend, or maintenance work to the appropriate specialist.

Skill for Claude CodeCodex

Written for Claude Code and Codex: installed under .claude/, but also agents/openai.yaml present. Also seen: mentions Claude Code; mentions Codex.

This is luckeyfaraday/frontier-orchestrator's own configuration. It tells Claude Code and Codex how to work on frontier-orchestrator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything frontier-orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to luckeyfaraday/frontier-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/luckeyfaraday/frontier-orchestrator/main/.claude/skills/orchestrate-specialists/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/luckeyfaraday/frontier-orchestrator

Made for: Claude Code, Codex.

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 orchestrate-specialists

README.md
[![agentmods](https://agentmods.dev/badge/skills/luckeyfaraday/frontier-orchestrator/orchestrate-specialists/github.svg)](https://agentmods.dev/skills/luckeyfaraday/frontier-orchestrator/orchestrate-specialists)
Your own site
<a href="https://agentmods.dev/skills/luckeyfaraday/frontier-orchestrator/orchestrate-specialists"><img src="https://agentmods.dev/badge/skills/luckeyfaraday/frontier-orchestrator/orchestrate-specialists/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for orchestrate-specialists

Your own site · 80×15
<a href="https://agentmods.dev/skills/luckeyfaraday/frontier-orchestrator/orchestrate-specialists"><img src="https://agentmods.dev/badge/skills/luckeyfaraday/frontier-orchestrator/orchestrate-specialists.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 889 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 $0.00077 $0.00889
Opus 5 $0.00039 $0.00445
Sonnet 5 $0.00015 $0.00178
Haiku 4.5 $0.00008 $0.00089

Measured 9d ago against content hash 099f2dad8d25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

orchestrate-specialists 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 9d 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.

.claude/skills/orchestrate-specialists/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrate Specialists

Act as the lead engineer. Decompose work, define contracts, delegate bounded tasks, inspect the resulting changes, and own final integration and verification.

Use these MCP tools:

  • mcp__frontier-orchestrator__specialist_status: verify all three CLIs are available.
  • mcp__frontier-orchestrator__delegate_backend: send backend work to Codex.
  • mcp__frontier-orchestrator__delegate_frontend: send design and frontend work to Kimi.
  • mcp__frontier-orchestrator__delegate_build: send domain-neutral tooling and mechanical maintenance work to Grok Build.

Read routing-contract.md when the task is mixed, the ownership boundary is unclear, or parallel implementation is being considered.

Route work

Send to Codex:

  • APIs, services, databases, migrations, auth, queues, jobs, infrastructure
  • security, backend performance, data integrity, backend-focused tests
  • server-side architecture and implementation review

Send to Kimi:

  • product and interaction design, information architecture, visual direction
  • components, styling, responsiveness, accessibility, animation, client state
  • frontend architecture, implementation, and visual/frontend review

Send to Grok Build:

  • build configuration, dependency and toolchain upgrades
  • CI, release automation, and generated boilerplate
  • mechanical repository-wide transformations and test or lint cleanup

Route by ownership before optimizing for speed:

  • backend behavior belongs to Codex, even when the change is straightforward
  • frontend or UX behavior belongs to Kimi, even when the change is straightforward
  • Grok is eligible only for the domain-neutral work above, unless the user explicitly requests Grok
  • never select Grok solely because it is faster

Keep with Claude:

  • task decomposition and priorities
  • shared contracts and cross-stack decisions
  • resolving contradictory specialist advice
  • reviewing diffs, integrating changes, and final verification
  • user communication

Read the full file on GitHub · 89 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 89 lines · 77 tokens per session scan A 099f2dad8d25

Subscribe to this mod's changes

orchestrate-specialists is a skill published in the GitHub repository luckeyfaraday/frontier-orchestrator (7 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 889 once invoked, about $0.0004 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 2026-08-31.