Frontier Delegation (Split-Brain Architecture)

Frontier Delegation (Split-Brain Architecture) is a skill for Claude Code, Codex from chama-x/GroundRules. It costs 70 tokens per session (3,893 once invoked), scanned A, original, MIT.

A work-sharing method between a reasoning model that designs algorithms and an IDE agent that edits files, runs code, and verifies builds. The constraint surface is the set of interfaces and rules that keeps the implementation aligned with the design.

In plain words
What is it for?
Use it for novel algorithms, mathematically demanding work, major architecture choices, and designs that need compiler and runtime verification.
Why use it?
It separates deep design decisions from hands-on coding while giving the engineer a precise specification to follow.

Skill for Claude CodeCodex

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/chama-x/groundrules/frontier_delegation
Any agent
npx skills add chama-x/GroundRules --skill frontier_delegation
Clone the repo
git clone --depth 1 https://github.com/chama-x/GroundRules

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 Frontier Delegation (Split-Brain Architecture)

README.md
[![agentmods](https://agentmods.dev/badge/skills/chama-x/groundrules/frontier_delegation.svg)](https://agentmods.dev/skills/chama-x/groundrules/frontier_delegation)
Your own site
<a href="https://agentmods.dev/skills/chama-x/groundrules/frontier_delegation"><img src="https://agentmods.dev/badge/skills/chama-x/groundrules/frontier_delegation.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,893 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 5.1 $0.00070 $0.03893
Opus 5 $0.00035 $0.01946
Sonnet 5 $0.00014 $0.00779
Haiku 4.5 $0.00007 $0.00389

Measured 5d ago against content hash 3a926e39929f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Frontier Delegation (Split-Brain Architecture) 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 5d 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.

.agents/skills/frontier_delegation/SKILL.md · 377 lines

How it starts

The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Frontier Delegation: The Split-Brain Protocol

v2 — Calibrated for frontier-grade reasoning models with adaptive thinking, XML-native processing, and sustained long-context coherence.


The Core Principle

This skill governs a cognitive division of labor between two AI modalities:

Role Strengths Weaknesses
Frontier Model (The Architect) Deep sustained reasoning, novel algorithms, mathematical rigor, spec-first design, long-context coherence, adaptive self-verification No file access, no compiler, no runtime, cannot verify infrastructure details
IDE Agent (The Engineer) File system mastery, live compilation, surgical edits, dependency tracing, iterative debugging, build verification Limited reasoning depth for novel algorithms, prone to architectural shortcuts

The handshake protocol between them is the Constraint Surface: the set of TypeScript interfaces, branded types, readonly annotations, and design-rationale comments that the Architect exports. The Engineer treats this surface as an unbreakable specification.

The Architect's most valuable output is NOT the algorithm implementations. It IS the interface definitions and type contracts. The types ARE the spec.

Key Insight: Frontier Models Changed

Legacy prompting patterns (imperative commands, step-by-step forcing, capitalized directives) were designed for earlier generation models that needed explicit scaffolding. Current frontier-grade models with adaptive thinking:

  • Reason internally and deeply — explicit chain-of-thought prompts are redundant and can degrade output
  • Process XML natively — XML tags create structural boundaries the model uses to separate context from instructions from output specs
  • Respond better to spec-as-interface — describe the system contract clearly, not the execution steps
  • Self-correct over long outputs — they maintain coherence across 2000+ line outputs without degrading
  • Need permission to go long — without explicit license to produce a complete implementation, they self-limit

Read the full file on GitHub · 377 lines

Files

What ships with it

3 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. 5d ago First seen · 377 lines · 70 tokens per session scan A 3a926e39929f

Subscribe to this mod's changes

Frontier Delegation (Split-Brain Architecture) is a skill published in the GitHub repository chama-x/GroundRules (5 stars, last pushed 22d ago), licensed MIT. It adds 70 tokens to every session and 3,893 once invoked, about $0.0003 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.