cat ~/.vault/notes.mdContinueEnd…Manage at agent speed
Your agents run hundreds of steps you never see. Excellent holds every one to your rules, and stops the risky ones or asks you first.
- FreeSee what they did. The free scan shows every leak, push and broken rule.
- ProStop it as it happens.
Unless you share usage stats or pair it with our team, nothing about you or your agents is sent to us.
For Claude Code, Codex and other AI agents. Excellent for Mac today; a version for Linux servers comes next, then Windows.
Recognizes 43 agents. Checks actions in 9, reads logs from 6.
Claude Code
Codex
Grok Build
Cursor
GitHub Copilot CLI
Gemini CLI
Qwen Code
Factory Droid
Devin
Antigravity
OpenCode
Kilo Code CLI
Hermes Agent
OpenClaw
GitLab Duo CLI
Amp
Auggie CLI
Codebuff
Junie CLI- Rovo Dev CLI
goose
Kimi Code CLI
Cline
Kiro
Amazon Q Developer CLI- Crush
Open Interpreter
Windsurf (Devin Desktop)
Mistral Vibe- OpenHands CLI
Zed Agent
Grok Bot- Roo Code
Sourcegraph Cody CLI- Continue CLI
Jules Tools
Aider
Pi
SWE-agent
mini-SWE-agent
Trae Agent- Plandex
Warp Oz
Understand how your environment works
Excellent does the checking, so you and your agents can get on with your best work.
Overview
It reads the logs your agents already keep
Your agents keep a diary of what they did, helpers included. Press Scan Now, and Excellent reads those of Claude Code, Codex, Grok Build, Copilot CLI, Gemini CLI and Qwen Code, on your Mac. A first scan takes seconds.
Findings
See what your agents did
Your email sent to websites or typed into forms. Keys sitting in logs. Secrets files read. History overwritten. Checks skipped. Each one says which agent and where.
What you can do
Fix some of it with a button
Have your own Claude Code or Codex take your email out of scripts, three files at a time. Clear keys from logs. Repair hooks whose Node version is gone. Excellent backs up a settings file before it changes it. Clearing keys from logs can't be undone.
NotificationsPro
Stop it before it happens
With Pro, Excellent checks each action before it runs, in 9 agents. It blocks your email on its way to a website and asks before a force push or a look at your keys. It can pause an agent until you decide.
Rules
Give Claude Code and Codex the same rules
A rule written for one often never reaches the other. Excellent shows which rules reach only one, and on your OK adds them to a file the other reads.
SandboxPro
Let your Mac enforce your rules
If you choose, Pro writes your file and folder rules into the macOS sandbox for Claude Code and Codex. Then the Mac itself keeps them out of the folders you closed, however a command is worded. Undo takes it out.
Privacy
Unless you share usage stats or pair it with our team, nothing about you or your agents is sent to us
The free app needs no account. No analytics unless you turn on usage stats, which send counts, never your logs. Apart from a daily check for updates, which you can turn off, Excellent goes online only for things you start: Check GitHub and GitLab, Protect Main, and the Servers preview. Once on, the preview checks your servers every 5 minutes. Explain and agent fixes run your own agent, which talks to its provider.
Observer notices what your agents don't tell you Pro
Observer is Excellent Pro watching your agents' logs as they write them, helpers included, for as long as the app runs. When an agent sends your email to a website, deletes a folder you said never to touch, force-pushes to main or leaves a key in a log, you hear about it. It also checks each action before it runs and can pause an agent until you decide.
Observer comes with Pro- Your email, sent to a websiteAlerts you
- A never-delete folder, deletedAlerts you
- A force push to mainAlerts you
- A key, left in a logAlerts you
- A rule only one agent was toldAlerts you
Watching
- 6agents whose logs it reads, helpers included
- 9agents whose actions it checks before they run
- 43agents it recognizes
Not ready for an app? Ask your agent to check
Paste one prompt into Claude Code or Codex. Your agent saves a small script, checks its fingerprint, tells you what it does, and runs it. The script reads your agent logs and writes one page on your Mac. Your agent is told not to read the logs itself, so what's in them stays on your Mac. Only a short summary passes through it: counts, agent names, dates and where the page is.
Needs Python 3.9 or later. Reads only. Makes no network calls. Writes one file: ~/excellent-free-scan/report.html.
SHA-256 of scan.py, the script the prompt saves9d60d631193cb0e796e4066d8fc4f2752c0e93c373a2919695eb2fe21c44810fRead the source
- 6requests carried my email to websites
- 2API keys sitting in plain-text logs
- 3force pushes
- 4hooks failing silently
- 5breaks of rules I wrote for my agents
- 0deletes of folders I marked never-delete
Get Excellent, free to scan on your Mac
Excellent for Mac
- Free to scan. No account needed.
- For Macs with Apple silicon, macOS 14 or later.
Open it and press Scan Now to see what your agents did. With Pro, it also checks risky actions before they run, and it lists what it will change in your agents' settings before it changes anything.
One email when Excellent for Mac is ready to download. Nothing else.
Questions: help@excellent.so
Excellent Pro
Pro protects. It blocks or asks before risky actions, turns your rules into the Mac's own sandbox, scans in the background and alerts you. It unlocks the moment you pay. Pro is $6 a month or $60 a year.
See Free and ProQuestions
What does Excellent do?
It reads the logs of Claude Code, Codex and four other agents on your Mac and shows what they did: your email sent to websites, keys in logs, secrets files read, history overwritten, rules that never reached the agent. It can fix some of it: clear keys from logs, take your email out of scripts, share rules and repair broken hooks. With Pro, a button turns on a check for next time, and Excellent checks each action before it runs, in 9 agents. Excellent for Mac today; a version for Linux servers comes next, then Windows.
Does anything leave my Mac?
Unless you share usage stats or pair it with our team, nothing about you or your agents is sent to us. Excellent reads your agents' logs on your Mac and keeps what it finds there. The free app needs no account. No analytics unless you turn on usage stats, which send counts, never your logs. It checks for updates about once a day, which you can turn off. A few things leave when you start them, such as Explain, agent fixes, Check GitHub and GitLab, Protect Main and the Servers preview. Explain hands a masked finding to your own Claude Code or Codex, on your plan. An agent fix gives it the file's path, and it reads and edits that file itself. Replace this key opens the provider's key page in your browser. You make the new key there. The check's replies, which can quote your rules, reach your agent's provider.
Which agents does it work with?
It reads the logs of Claude Code, Codex, Grok Build, GitHub Copilot CLI, Gemini CLI and Qwen Code. Its live check runs in those and in Cursor, Factory Droid and Devin. It recognizes 43 agents in all.
What does it change on my Mac?
A scan changes nothing. Protection, with Pro, changes nothing until you say so: before you turn it on, it lists what it will change. It adds one check to each agent's settings, backing up each file first. It also tells Codex to trust it and starts at login. Turn it off and it takes its check back out of each agent's settings, and changes nothing else. Codex trust, shared rules, a sandbox and commit watching stay until you undo each. It never opens your Documents, Desktop, Downloads or iCloud folders.
Is it free?
Scanning is free. Free shows what your agents did: scan any time, read every finding and its history, and get every app update, with no account needed. Pro protects: it blocks or asks before risky actions, turns your rules into the Mac's own sandbox, scans in the background and alerts you. Pro is $6 a month or $60 a year. Join the list by 11:59 p.m. PT on Monday, Nov 30, and you can get your first year for $40 (then $60 a year) until Dec 31. Pro unlocks the moment you pay. In January, Pro adds your other Macs and servers in one view, and alerts on your phone or in Slack.
Can an agent get around it?
Pro's live check reads what a command says. An agent set on getting around it sometimes can. For the file and folder rules that matter most, Pro can turn them into Claude Code's and Codex's macOS sandbox, if you choose. The sandbox doesn't care how a command is worded.
Put Excellent on watch
Free to scan on your Mac. No account needed. A first scan takes seconds.
Latest from the blog
All articlesAI agents leak keys, rewrite main and skip your checks
Five things coding agents do on a Mac that cost you: leaked keys, force pushes to main, skipped git hooks, deleted folders and rules the other agent never got. What stops each one, today.
Check what your AI agent actually did
Where Claude Code and Codex keep their logs on a Mac, how to read one session, and five searches that find leaked keys, secrets files read, force pushes, skipped git hooks and deletes.
Claude Code and Codex don't read the same rules
Claude Code reads CLAUDE.md. Codex reads AGENTS.md. If you use both, some of your rules reach only one of them, often the global ones. How to check in a minute, and three ways to fix it.


