Sign InOpen Brain
AI EngineerVideoSource Linked

How long can your skills be before your agent forgets what you told it? — Laurie Voss, Arize AI

Instruction capacity rose sharply, but long skill files still need evals. Current models can track thousands of constraints, with large differences by model, wording, and order.

AI Engineer · Sep 9, 2026
Open Source Open MarkdownOpen JSON
Source Summary

A rerun of IFScale reproduced the old failure point around **200–300 rules**. Current frontier models reached roughly **2,000–5,000 rules** before major decline; GPT-5.5 reportedly held **99% accuracy at 5,000 rules** on this proxy task.

Practical Implication

Revisit prompt-length assumptions before splitting a style guide or policy into many agents. Capacity is less likely to be the first constraint now, so test whether one coherent skill is cheaper and easier to maintain than a handoff-heavy design.

Agent-Ready Context
A rerun of IFScale reproduced the old failure point around **200–300 rules**. Current frontier models reached roughly **2,000–5,000 rules** before major decline; GPT-5.5 reportedly held **99% accuracy at 5,000 rules** on this proxy task.

Revisit prompt-length assumptions before splitting a style guide or policy into many agents. Capacity is less likely to be the first constraint now, so test whether one coherent skill is cheaper and easier to maintain than a handoff-heavy design.

IFScale checks whether required words appear in a synthetic report, not whether an agent reasons well. Reported limits ranged from **750 to 9,000-plus rules**, and performance can shift with instruction wording or order, making output verification essential.
Connected Context · Feed7 Judgment

This weakens raw instruction count as the default reason to split a coherent skill across agents: frontier-model capacity on this proxy appears far higher than older assumptions. It shifts the practical constraint toward regression, ordering sensitivity, and output verification, while the synthetic word-inclusion task leaves real reasoning capacity unresolved.

Context Map
benchmarkcoding#skills#agent-evals#agent-reliability
Uncertainty
IFScale checks whether required words appear in a synthetic report, not whether an agent reasons well. Reported limits ranged from **750 to 9,000-plus rules**, and performance can shift with instruction wording or order, making output verification essential.