andreasasprou/agent-skills

Claude Code plugins: Oracle (GPT-5.2 advisor), Safety Net (block destructive commands), opensrc (package source explorer)

This repository also configures its own agents. See what agent-skills tells them →

7Stars on the repository
7Mods indexed here, across every type
4mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

oracle

02

andreasasprou/agent-skills

Plugin Claude Code

Bundles 1 skill · 81 tokens together

Strategic technical advisor with two modes. REPO MODE (gpt-5.2) explores your codebase to find gaps and review code. WEB MODE (5.2 Thinking / GPT-5.2-pro) researches external info like best practices and library comparisons. Run both in parallel to compare your implementation against current standards.

not rated 7 4mo ago A tokens not measured original MIT

safety-net

03

andreasasprou/agent-skills

Plugin Claude Code

Bundles 1 hook

Block destructive shell commands before execution. Prevents rm -rf, git push --force, docker system prune, kubectl delete, terraform destroy, cloud deletions (AWS/GCP/Azure), database drops, and 200+ dangerous patterns.

not rated 7 4mo ago C tokens not measured original MIT