feat: add per-level ask mode for hooks#12
Open
enzoleonardi wants to merge 1 commit into
Open
Conversation
Add ASK config (per security level) to both pre-tool-use hooks. When ask=true for a level, the hook returns "ask" instead of "deny", letting Claude Code prompt the user instead of blocking outright. Defaults to false (deny) for all levels; override via env vars HOOK_ASK_CRITICAL, HOOK_ASK_HIGH, HOOK_ASK_STRICT. Remove 5 secrets-related patterns from block-dangerous-commands (cat-env, cat-secrets, env-dump, echo-secret, rm-ssh) to avoid conflicts with protect-secrets which owns all secrets patterns.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
ASKmode per security level (critical,high,strict) to bothblock-dangerous-commands.jsandprotect-secrets.jsask=truefor a level, the hook returnspermissionDecision: "ask"instead of"deny", letting Claude Code prompt the user with context instead of blocking outrightfalse(deny) for all levels; users can override via env vars (HOOK_ASK_CRITICAL,HOOK_ASK_HIGH,HOOK_ASK_STRICT) in theirsettings.jsoncommandblock-dangerous-commands.js(cat-env,cat-secrets,env-dump,echo-secret,rm-ssh) to avoid conflicts withprotect-secrets.jswhich is the single owner for all secrets patternsTest plan
npm test)ASKdefaults are allfalseHOOK_ASK_HIGH=true node script.js)denyfor critical/high and correct decision routing🤖 Generated with Claude Code