john-wilmes/claude-agentic-coding-playbook
A set of Claude Code hooks plus a few slash-command skills. The hooks block risky actions such as destructive git commands and prompt injection, and warn when context is running out, even when permission prompts are bypassed. The author says the deny rules hold near-perfectly, which is their own claim.
Idea adaptedKey files read, not run
I learnt this repo's idea and adapted it into my own workspace setup.
How we know
We read the README and key files, not every source file, and did not run it, so the most we can say is Idea adapted or Risky.
Good for
Solo Claude Code users who run in bypass mode and want hard guardrails instead of prompts.
Not for
Windows users without WSL, since the hooks are POSIX shell. You install scripts you must read first; it is not a finished app.
Repo
- Stars
- 4
- License
- MITUse it, change it, sell it, closed-source included. Keep the author's copyright notice.
- Maturity
- active
- Last push
- 2026-04-06
- Last checked
- 2026-11-14