Works with the AI tools you already use
Agents md Token Auditor
by Timoranjes
Audits AGENTS.md, CLAUDE.md, and .cursorrules files for per-turn token waste, classifies every section as always-on vs on-demand, estimates the real cost of a bloated context file, and produces a step
Free
See it in action
You say
The agent has edited parser.py four times with the same error. It seems stuck. Diagnose and fix the loop.
Your agent does
Diagnosis: Edit Loop. Recovery: Stop editing parser.py. Read the entire file and the test suite. Identify the gap between implementation and test expectations. Do not edit until you explain the root cause in one sentence.
About this skill
Audits AGENTS.md, CLAUDE.md, and .cursorrules files for per-turn token waste, classifies every section as always-on vs on-demand, estimates the real cost of a bloated context file, and produces a step-by-step migration plan that moves task-specific content into skills using progressive disclosure. For developers whose coding agent feels dumber deep in a session, burns tokens on every turn, or hits compaction early because their instruction file is overloaded.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean today
- Free to download with an account
Creator
127+ total installs · 83 skills on Agensi
Frequently Asked Questions
Popular in AI Agents & LLM Ops
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
instruction-layer-auditor
Audit and de-conflict complex agent instruction stacks to fix inconsistent behavior and logic bloat.
AI Coding Prompt Refiner for Better Developer Results
Transforms vague coding requests into precise, scoped, testable, AI-ready prompts for Cursor, Claude Code, Codex CLI, Replit, and other coding agents.
codex-grade-coding
Turn your AI agent into a senior engineer with strict task classification and verification-driven coding protocols.