guardrails-challenge
by scaso01 · ★ 0 · updated yesterday
Effective challenge: hold answers to evidence under pushback, and check agents' commit claims against git.
Install
/plugin marketplace add scaso01/claude-risk-guardrails/plugin install guardrails-challenge@claude-risk-guardrailsThen run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.
What it hooks into
From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.
- Events
prompt.submittool.callsession.start- API calls
$.clock.now$.env.get$.fs.write$.process.run$.session.cwd- Can see
every promptAgent calls- Reach
- level 2 of 3 runs processeswrites filesreads env vars
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/scaso01/claude-risk-guardrails
- Path in repo
packs/challenge- Source commit
fcefc10the exact code the scan read- Author
- @scaso01
- License
- MIT
- First published
- Last pushed
- First listed here
Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.
More from scaso01/claude-risk-guardrails
guardrails-approval
scaso01/claude-risk-guardrails
A human signs off before anything that can't be undone: publishing, killing protected processes, editing secrets or stale copies.
guardrails-development
scaso01/claude-risk-guardrails
Development standards: look before building, test what changed, pass the repo's checks, keep the rules in view.
guardrails-monitoring
scaso01/claude-risk-guardrails
Ongoing monitoring: keep watching the agent after approval, and watch the controls themselves.
guardrails-outcomes
scaso01/claude-risk-guardrails
Outcomes analysis: check what a reply claims against what the evidence supports.
guardrails-records
scaso01/claude-risk-guardrails
Documentation: leave a trail a reviewer can follow, and keep what can't be rebuilt.