Rulestack (@rulestack)

@rulestackJoined July 2026

I maintain Rulestack — ready-to-use rule packs and skills for Cursor, Claude Code, and OpenAI Codex, written and updated against each tool's current spec. Store: rulestack.gumroad.com / Articles: dev.to/rulestack

@rulestackJoined July 2026

Rulestack

About

Available for

Rulestack's blogs

Recently published

We cut CLAUDE.md to 33KB. Eighteen days later it was 45KB again: what a size cap missed and a structure test caught

Tool search hid 40,170 tokens from our first request. auto:5 put them all back

The reply-length check existed for three weeks. The batch a human flagged never touched it: guarding the wrong path

/skill-doctor: 40 skills, 3,060 tokens a turn, and the wrong ones to cut

One rule set, four places: inline +3,330 tokens, @import +3,442, paths +0 until read

Rulestack

About

Available for

Rulestack's blogs

Recently published

We cut CLAUDE.md to 33KB. Eighteen days later it was 45KB again: what a size cap missed and a structure test caught

Tool search hid 40,170 tokens from our first request. auto:5 put them all back

The reply-length check existed for three weeks. The batch a human flagged never touched it: guarding the wrong path

/skill-doctor: 40 skills, 3,060 tokens a turn, and the wrong ones to cut

One rule set, four places: inline +3,330 tokens, @import +3,442, paths +0 until read

Rulestack

About

Available for

Rulestack's blogs

Recently published

We cut CLAUDE.md to 33KB. Eighteen days later it was 45KB again: what a size cap missed and a structure test caught

Tool search hid 40,170 tokens from our first request. auto:5 put them all back

The reply-length check existed for three weeks. The batch a human flagged never touched it: guarding the wrong path

/skill-doctor: 40 skills, 3,060 tokens a turn, and the wrong ones to cut

One rule set, four places: inline +3,330 tokens, @import +3,442, paths +0 until read

Search Hashnode

Rulestack

About

Available for

Rulestack's blogs

Recently published

We cut CLAUDE.md to 33KB. Eighteen days later it was 45KB again: what a size cap missed and a structure test caught

Tool search hid 40,170 tokens from our first request. auto:5 put them all back

The reply-length check existed for three weeks. The batch a human flagged never touched it: guarding the wrong path

/skill-doctor: 40 skills, 3,060 tokens a turn, and the wrong ones to cut

One rule set, four places: inline +3,330 tokens, @import +3,442, paths +0 until read