jev-guard
Skill2 starsChanged 53 days agoMITView on GitHub
Use before running a shell command that might delete data, print a secret, force-push, or do something the user did not ask for. Jev scores the harm. You still decide whether to run it. Runs @aitofy/jev-awesome-skills.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- styrir/skillstheir own version, first seen Oct 17, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- styrir/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms-full.txtllms.txt
- llms.txtllms.txt
- jev-actSkill
- jev-awesome-skillsSkill
- jev-gateSkill
- jev-reviewSkill
- jev-routeSkill
- jev-triageSkill
- jev-verifySkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
If you already know the command can destroy data, leak a secret, or leave the task, stop and ask the user.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Guard
If you already know the command can destroy data, leak a secret, or leave the task, stop and ask the user. Do not use Jev to talk yourself into it.
Otherwise put the exact command, cwd, and task in state and run:
jev questions guard
jev --file request.jsonThe package is @aitofy/jev-awesome-skills. Do not write a second client. Preset labels are allow, ask_user, and refuse.
Stop when harm.score is at or above 1.5. Proceed when the chosen label's probability is at or above 0.9 and determined.noul is at or above 0.9. Otherwise ask. Stop wins. Proceed means you may run that exact command, then check the result. It does not permit a second command.
On "source": "fallback", fail open: ask the user before anything hard to undo. Do not invent a probability.
Template: examples/guard.request.json. Offline sample: examples/guard.response.json returns stop.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.