Agent Audit
elliotjlt/agent-audit
| When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, without degrading quality?" The goal is the leanest agent that still works.
3k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
1
copies elsewhere
how many repositories repackaged it
60
stars on the repo
on the repository, not the skill itself
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/ElliotJLT/Claude-Skill-Potions --skill agent-auditMCP servers it needs
declared by the author in the skill headerTask
io.github.rog0x/task
Todo, priority, estimation, burndown for AI agents
Repackaged in 1 other repositories
same content, different owner
majiayu000/claude-skill-registry
open on GitHub →
How to use it
Copy the folder
Take elliotjlt/agent-audit from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
Check the name does not clash
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.