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 skills/chama-x/groundrules/frontier_delegationnpx skills add chama-x/GroundRules --skill frontier_delegationgit clone --depth 1 https://github.com/chama-x/GroundRulesWrote 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/skills/chama-x/groundrules/frontier_delegation)<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>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 | $0.00070 | $0.03893 |
| Opus 5 | $0.00035 | $0.01946 |
| Sonnet 5 | $0.00014 | $0.00779 |
| Haiku 4.5 | $0.00007 | $0.00389 |
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.
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
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.
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.
- 5d ago First seen · 377 lines · 70 tokens per session scan A 3a926e39929f
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.
Other skills, from other repositories
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-pagerank-analyzer
Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer.
agent-neural-network
Agent skill for neural-network - invoke with $agent-neural-network.
worker-integration
Worker-Agent integration for intelligent task dispatch and performance tracking.
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.