Whitelist-based permission system for Claude Code skills. Declare what a skill is allowed to do in its SKILL.md frontmatter; anything not whitelisted falls through to the normal permission flow. Includes a dangerous-command safety net and desktop notifications when human input is needed.
Plugin permitcrab from marketplace utilitry in brennacodes/utilitry. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
auditReview permitcrab permissions: blocks for anti-patterns - overly broad regexes, missing anchors, permissions declared but no body step requires them. Use when the user asks to audit, lint, or validate permissions, review a skill's permissions block, or check a plugin for over-permissioned or unneces
doctorDiagnose permitcrab install health - script presence, version drift, hook wiring, common misconfigurations. Use when permitcrab isn't working as expected, the user asks to debug, troubleshoot, verify, or validate permitcrab, after upgrading the plugin, or to check status of a fresh install. Read-onl
installInstall or reinstall permitcrab's runtime scripts to ~/.permitcrab/ so other plugins can reference them via a stable path. Use when the user asks to install, reinstall, fix, repair, or bootstrap permitcrab, or after a plugin upgrade. Idempotent. Distinct from permitcrab:setup, which declares permiss
setup-testTest harness invoked by permitcrab:setup to verify that a candidate permissions block produces the intended approve / passthrough / deny outcomes. Replays each case in test-plan.json against the same resolver script that the live PermissionRequest hook runs, passing this skill's own directory as the
setupUse when the user asks to set up permissions for a system, repo, plugin, or skill, when they want to whitelist or allowlist a command, auto-approve a tool call, tighten or narrow existing permissions, or stop being prompted about something a skill always does. Distinct from permitcrab:install, which
uninstallRemove permitcrab's runtime scripts from ~/.permitcrab/. Use when the user asks to uninstall, remove, or clean up permitcrab. Does not remove the plugin itself; uninstall that via your plugin manager.
${CLAUDE_PLUGIN_ROOT}/scripts/auto-deny-dangerous.js
${CLAUDE_PLUGIN_ROOT}/scripts/resolve-permissions.js auto
${CLAUDE_PLUGIN_ROOT}/scripts/permission-notification.js
Capture and act on todos, reminders, and notes. Items live as markdown files with YAML frontmatter under ~/.notably/. Reminders can fire via SessionStart surfacing, scheduled remote agents, or local macOS notifications. Slash-only, no model auto-triggering.
8 skills · hooks
Capture, browse, and consume agentic blindspots - default tendencies that produce bad outputs in specific contexts. Records live as markdown files with YAML frontmatter under ~/.blindspots/.
6 skills · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
Claude Skills for Obsidian
6 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.