collinzrj/claude-code-auto-safeguard-prompt
AI skill
Can I trust it?
Be careful with this one.
Warnings Check
Very new: it was created 6 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 6 days ago.
Licence Careful
No licence: legally you can't reuse the code, unless the README says otherwise.
Quick checks from public data. They help, but they are no guarantee.
What it is
A system prompt and rule set for a security monitor that evaluates the latest action of autonomous AI coding agents and decides whether to block it. It defines hard and soft block categories covering prompt injection, scope creep and accidental damage, and specifies how user…
Who it's for
Developers and security teams building guardrails or auto-approval classifiers for autonomous AI coding agents
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up collinzrj/claude-code-auto-safeguard-prompt in my project. Follow its README: https://github.com/collinzrj/claude-code-auto-safeguard-prompt. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in AI agents starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/collinzrj/claude-code-auto-safeguard-prompt?ref=badge)Similar repos
- FailproofAI/failproofai
Observability and enforcement layer for AI agent harnesses such as Claude Code, Codex, Hermes and OpenClaw. Records every agent run locally, provides a dashboard, and blocks dangerous tool calls befor
- jmanico/grim-prompter
A threat modeling toolkit of prompts and workflows that an AI coding agent such as Claude Code or Codex follows to review a repository. It covers architecture-specific quick and deep runs, method prom
- dmitribogatenkov/briefproof
A Claude Code plugin that turns a brief into quoted numbered requirements, a spec, a plan and tickets, then has a separate agent check the finished project against the original brief. Includes a live
- AGGIB/Stroq
A local security tool for AI coding agents (Claude Code, Cursor, Codex CLI). It scans existing sessions for known secrets and reports which keys may have left the machine, and installs hooks that deny
- rbartoli/agent-usage-guard
A Claude Code mod that holds subagent fan-out, heavy-context prompts and retry loops before they consume the usage window. It reads the plan's 5-hour and weekly usage percentages, counts agents across
- lordon1a/agents.md
A single Markdown system prompt file (AGENTS.md) for coding agents, meant to be dropped into a project or global config. It sets an operating specification that aims to reduce refusals, disclaimers an