All Claude Code modsruihe774/cc-bash-guardrails
bash-guardrails
Tool-call guard rules (parser-based), written in CEL; add your own in ~/.claude/bash-guardrails.json or .claude/bash-guardrails.json. On by default: blocks malformed bash and find rooted at /. Opt-in: Monitor, find without -xdev, pgrep/pkill pitfalls, until-grep loops, sudo, run0 confirmation, and pointing cat/head/sed/awk, heredoc writes, sed -i and Python rewrites to the Read, Write and Edit tools
bash-guardrails reaches L1 (reads) and passed claude plugin validate with warnings on Claude Code 2.1.302.
- Events hooked: 2
- API methods referenced: 7
- Access from classified calls: L1, reads: reads files, reads env vars, draws
- Static scan, not a runtime test
Install hint
/plugin install bash-guardrails@anthropic-plugin-directoryFrom Anthropic's plugin directory. Mods need Claude Code 2.1.287 or later.
Access
L1 Reads filesreads files, reads env vars, drawsValidation
Passed with warnings on Claude Code 2.1.302View the source on GitHub Back to the list
What the scan recorded
- Anthropic directory
- Listed as
bash-guardrails@anthropic-plugin-directory - Observed events
- Monitor|Bash calls
- Hooks
session.start, tool.call {tool=Monitor|Bash}- API calls
$.env.get, $.fs.read, $.fs.stat, $.session.root, $.ui.ask, $.ui.log, $.ui.toast- Validation on 2.1.302
- Passed with warnings
- Scanned revision
3094067a26bb
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. How the scan works.
Badge for your README
Authors can show the latest scan result in their README. Each badge links to this page.
[](https://mods.aidojo.si/mods/ruihe774--cc-bash-guardrails--bash-guardrails/)
[](https://mods.aidojo.si/mods/ruihe774--cc-bash-guardrails--bash-guardrails/)