Clooks
Runs TypeScript hooks in Claude and Codex to intercept and block dangerous agent actions.
not read yet
Use
- For
- Developers using Claude Code or Codex who want to guard against destructive agent actions
- Price
- Open sourcepricing page, read 2026-09-19
- Activity
- Activity not read yet
- Company
- founding year not on record
- Runs as
- SDK
- Block dangerous bash commands like rm -rf before execution
- Rewrite commands to preserve git history instead of destructive moves
- Enforce team policies on destructive operations across repositories
- #72
CodeRabbit
Automatically reviews pull requests, prioritizes them by risk, and scans for security vulnerabilities.
24.4knot readFrom $24/user/mo2023 - #112
Greptile
Reviews pull requests and tests code changes using agent swarms to catch bugs and style violations across codebases.
8.5knot readFrom $30/user/mo - #117
Fluid Attacks
Scans applications for vulnerabilities using automated analysis and human penetration testing, prioritizes findings by exploitability, and generates remediation guidance.
4.3knot readFree plan - #123
Hacktron AI
Analyzes pull requests to find exploitable vulnerabilities and generates working proofs of concept before code ships.
68not readFrom $40/user/mo - #127
Whisper Internet Infra AI Context
Resolves IP addresses and domains to real owners, networks, and jurisdictions to block unauthorized connections.
65Active— - #159
KushoAI
Generates API tests from specifications, scans for security vulnerabilities, and validates complete workflows across services.
906not readFree plan
What is Clooks?
Runs TypeScript hooks in Claude and Codex to intercept and block dangerous agent actions.
Who is Clooks for?
Developers using Claude Code or Codex who want to guard against destructive agent actions
How much does Clooks cost?
Clooks is open source, per its pricing page on 2026-09-19.
Do people use Clooks?
Emerging.
What are alternatives to Clooks?
In Developer tools, by use: CodeRabbit, Greptile, Fluid Attacks, Hacktron AI, Whisper Internet Infra AI Context, KushoAI.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one row at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.