PulseAugur
EN
LIVE 05:13:12

Claude Code's script loading behavior deviates from documentation

By PulseAugur Editorial · [1 sources] ·

A recent analysis of Claude Code revealed that 13 out of 16 runs successfully loaded the skill's bundled scripts into context, contrary to documentation suggesting scripts are executed without being loaded. The study also found that reference files, such as reference.md, were consistently loaded into the model's context, regardless of their size, when referenced in SKILL.md. This contradicts the documented behavior where extra files are supposed to incur no cost until needed and scripts are run rather than read. AI

IMPACT Clarifies the actual context-loading behavior of Claude Code's bundled files, impacting how developers structure their skills.

RANK_REASON Analysis of a specific feature's behavior within a product.

Read on dev.to — Claude Code tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Claude Code's script loading behavior deviates from documentation

How we ranked this

Signal score
15 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Analysis of a specific feature's behavior within a product.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — Claude Code tag TIER_1 English(EN) · Rulestack ·

    When a Claude Code skill's reference.md and scripts actually load (the 'executed, not loaded' script was read in 13 of 16 runs)

    <blockquote> <p>13 of 16 Claude Code runs that executed a skill's bundled <code>scripts/check-entry.sh</code> also loaded its source into context, with <code>Read</code> or <code>cat</code>, although the skills docs label such a script "executed, not loaded". The rest held as doc…

RELATED ENTITIES

RELATED TOPICS