frontier

A local command-line tool that sends one prompt to several local AI command-line programs, compares their answers with a judge model, and produces a combined answer.

In plain words
What is it for?
Use it to view available local models, choose a group of them, and run a prompt through that group from the terminal.
Why use it?
It helps when you want several local AI opinions in one place instead of running and comparing each one yourself. The selected mode is only saved; you must explicitly run the tool for each prompt.

Skill for Claude CodeCodex

Part of the maestro plugin — 8 skills, 6 commands, 7 hooks shipped together

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 skills/mbanderas/maestro/frontier
Any agent
npx skills add mbanderas/maestro --skill frontier
Clone the repo
git clone --depth 1 https://github.com/mbanderas/maestro

Made for: Claude Code, Codex.

Or install maestro, the plugin that ships this one along with the rest of its 8 skills, 6 commands, 7 hooks.

Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,102 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 $0.00023 $0.01102
Opus 5 $0.00012 $0.00551
Sonnet 5 $0.00005 $0.00220
Haiku 4.5 $0.00002 $0.00110

Measured 2d ago against content hash a3679477de98, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

frontier 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.

integrations/cline/skills/frontier/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drive the Maestro Frontier engine — a zero-dependency local multi-CLI fusion engine (a parallel panel of local CLIs → a judge model's analysis → a grounded synthesis). It is the same engine the Claude Code plugin ships; here it runs through the maestro CLI with --scope cline.

Install path (pick one):

  • Project-scoped: .cline/skills/frontier/SKILL.md
  • Global: ~/.cline/skills/frontier/SKILL.md

This is a typing shortcut, not the Claude Code plugin. Cline has no prompt hook, so arming a mode does not auto-run the engine on later prompts — it only persists the mode. To actually fuse a prompt, invoke run explicitly (step 4).

When the user invokes this skill, map their request to one engine CLI call and run it in the terminal (Cline will request approval before executing). Do not edit the engine's state file by hand.

1. Inspect or compose

frontier catalog is the source of truth for locally selectable models, named presets (including legacy presets), aliases, and readiness. It does not print secrets or configured model IDs. compose validates ready models and arms the resolved custom panel unless --dry-run is supplied:

maestro frontier catalog
maestro frontier compose --models <model-a>,<model-b> --scope cline
maestro frontier compose --models <model-a>,<model-b> --judge <model> --synth <model> --effort <level> --save my-panel --scope cline
maestro frontier compose --models <model-a>,<model-b> --dry-run --scope cline
maestro frontier effort <auto|low|medium|high|xhigh|max|ultra> --scope cline

2. Switch mode

Persists under Maestro's platform-specific config directory: $XDG_CONFIG_HOME/maestro when set; otherwise %APPDATA%\maestro on Windows or ~/.config/maestro; default off. --scope cline keeps Cline's armed mode independent from Claude Code, Codex, Cursor, and Gemini on the same machine:

maestro frontier mode off --scope cline
maestro frontier mode single --model <model> --effort <level> --scope cline
maestro frontier mode fusion --preset <preset> --effort <level> --scope cline
maestro frontier mode fusion --preset custom --models <a,b,c> --scope cline
maestro frontier mode fusion --preset <preset> --judge <model> --synth <model> --scope cline

Read the full file on GitHub · 99 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 · 99 lines · 23 tokens per session scan A a3679477de98

Subscribe to this mod's changes

frontier is a skill published in the GitHub repository mbanderas/maestro (5 stars, last pushed 6d ago), licensed MIT. It adds 23 tokens to every session and 1,102 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

etsy-category-listing

Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…

browser-act/skills · 209 tokens

human-approval

Request human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs /…

Prismer-AI/PrismerCloud · 168 tokens

firebase-analytics

Use when logging analytics events, setting user properties, configuring default event parameters, building funnels, or adding screen-view tracking.

evanca/flutter-ai-rules · 28 tokens

firebase-remote-config

Use when implementing feature flags, running A/B tests, setting parameter defaults, fetching/activating config, or enabling real-time config updates.

evanca/flutter-ai-rules · 33 tokens

git-master

MUST USE whenever a task needs a commit or git-history investigation. Covers atomic commits, staging, commit-message style, rebase, squash, fixup/autosquash, blame, bisect, reflog, git log -S/-G, and questions like who wrote this or when was this added. Do not use for ordinary code edits unless the user asks for git…

code-yeongyu/oh-my-openagent · 81 tokens

prismer-evolve-record

Record the outcome of applying an evolution strategy. Use after resolving an error where prismer-evolve-analyze provided a recommendation, to feed back success or failure to the network.

Prismer-AI/PrismerCloud · 41 tokens