TheBotique

AI Coding Token Optimizer

Make any repository cheap for an AI agent to work in. Measure the instruction file every session loads, cut it to the rules that bind every task, and move reference material behind short task routers (docs/map/ plus a README next to each code area) that agents open only when a task needs them. Use i

as observed 2026-09-30T05:46:36.144Z
Identifier
ai-coding-token-optimizer
Source
ClawHub
Version observed
1.2.0
Source repository
not published
Repository observation
No source repository listed
First observed here
2026-09-21T23:20:53.854Z
Observations recorded
3
Installs (reported upstream)
2
Weekly downloads (upstream)
230
Declared license
MIT-0

Observation history

2026-09-30T05:46:36.144Z

Fields that differed: changelog latestVersion

FieldBeforeAfter
changelog "v1.1.0: measure and slim per-host always-loaded agent instructions; add two-level project routers, operations guidance, and hardened verification." "v1.2.0 adds an explicit, privacy-preserving feedback handoff: a redacted result report can be prepared for the maintainer, but nothing is sent automatically."
latestVersion "1.1.0" "1.2.0"
2026-09-29T04:47:03.526Z

Fields that differed: changelog latestVersion summary

FieldBeforeAfter
changelog "Agent-neutral project mapping explanation, simple adoption and ProSkills primary homepage." "v1.1.0: measure and slim per-host always-loaded agent instructions; add two-level project routers, operations guidance, and hardened verification."
latestVersion "1.0.2" "1.1.0"
summary "Help any repository-capable AI agent spend less time rediscovering files and loading unnecessary context. Create concise project maps for code, content and operations, linked from "Make any repository cheap for an AI agent to work in. Measure the instruction file every session loads, cut it to the rules that bind every task, and move reference material behin

Correction

If you maintain this extension and believe anything above is inaccurate, request a correction. Corrections are published, and disputed entries are marked as disputed while under review.