aunx Agent Hygiene Bundle: 6 Skills for Reliable AI Agents
Six skills that fix things AI agents quietly get wrong: false 'not found' claims, preferences saved as rules, incomplete renames, noisy tickets, client details left in templates, and the same corrections repeated every session. Works with Claude Code, Codex CLI, Cursor and Gemini CLI. Source: https://github.com/aunysillyme-dev/aunx-skills
Works with any agent that signs in to Agensi, such as Claude, ChatGPT, Claude Code, Cursor and Codex CLI.
One payment, lifetime access. 6 skills unlock instantly in your library.
What's included
6 skillsGive agents a clear way to verify missing results, pending jobs, and skipped checks before reporting a conclusion.
Help your agent preserve the difference between a passing idea, a preference, a working habit, and a firm rule.
Map a rename across code, docs, configuration, tests, and project notes, then check the old name in the same scope.
Turn recurring feedback into evidenced proposals, then save the changes you approve.
Turn findings into startable, deduplicated issues and verify the evidence before closing them.
Turn completed client work into a reusable method and blank template, with an explicit scan for identifying details.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads these skills and uses them on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle goes through our trust checks.
Security scanned
Checked by our 8-point scan before listing
2 uses
Times these skills were used to date
Money-back guarantee
Doesn't do what its page promises? You get your money back.