SUMMARY AI summary by gpt-5-mini
bash-guardrails is a PreToolUse hook for Claude Code’s Bash tool that reduces repetitive permission prompts by auto-approving patterns judged safe. It’s intended for users whose Claude Code permissions.allow list is small or empty (less useful if you already allow broad patterns like Bash(git *)). Key features: - Auto-approves safe pipelines and find -exec invocations when stages are known-safe - Allows shell compound operators, loops and conditionals if all subcommands are safe - Allows ANSI-C quoted strings ($'...') when the outer command is trusted - Provides an allowlist check against permissions.allow (settings.json / settings.local.json) - Strips comment-only lines and trims whitespace; denies risky heredoc patterns and interpreter heredocs - Includes tests and a canary audit to detect CC permission drift Install by enabling the plugin in Claude Code settings. Requires jq, awk, and Bash 4+. Notes warn about pitfalls in parsing and rewriting shell commands.
DETECTED Detected AI stack
AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.
Language breakdown (by bytes)
Why this is classified AI-related
The AI relevance score checks four places for AI keywords and adds the weight of each one that matches. Full methodology
Total AI relevance score: 75 / 100
Position among AI repos in the same language
We track 962 Shell repos, of which 847 score 40 or above on AI relevance. 243 have more stars than this one (top 25.4%), and 86 score higher (top 9.0%).
Owner
Data scientist/ML engineer; entrepreneur; PhD in cognitive psychology and neuroscience
Dates
| Created on GitHub | 2026-05-27 |
| Last push | 2026-06-11 |
| First seen here | 2026-05-27 |
| Last fetched | 2026-08-19 16:21 |
Similar repos (same language)
Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.
99xAgency/GodModeSkillMulti-LLM cross-review workflow for Claude Code. /work orchestrates plan/implement/bug-fix with 3 different model families voting on every gate.
Heoooooon/lazy-starter-kitA signed GUI and one safe command to turn macOS, Linux, or Windows into a complete AI development environment — dry-run first, repeatable, and tested.
Avanderheyde/levelsio-vps-setup-skillA Claude Code skill to deploy and operate a web app on a single cheap, hardened VPS the levels.io way — Hetzner/DigitalOcean + Next.js + SQLite + Caddy + systemd.
MeherBhaskar/agent-rigorSkill repository to enforce Engineering disclipline in coding assistants
alicicek/tale-modeA discipline plugin for Claude Code + OpenAI Codex — plan first, verify against the real code, receipts on every decision, independent adversarial review, and a self-armed loop that keeps going until a real check passes. Built by Fable to make any Claude work like a careful senior engineer.
anzy-renlab-ai/pronounce🔊 Pronounce developer jargon out loud. 1,650+ entries (kubectl, GIF, JSON, JWT, …), sourced with confidence levels. Bash CLI + VS Code extension + interactive quiz + voice search + MCP server + Claude Code skill.
AbuZar-Ansarii/All-AgentsInstall and run every AI agent on your phone locally