feat: add HOL Guard workflow safety skill - #14
Open
kantorcodes wants to merge 1 commit into
Open
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds
reflex-hol-guard, a focused Agent Skill for protecting agent-driven Reflex workflows with HOL Guard on the local coding-agent boundary.The skill directly installs and invokes HOL Guard (
pipx install hol-guard,hol-guard detect,hol-guard install <detected-harness>,hol-guard run <detected-harness>,hol-guard doctor) before state-changing work, while preserving Reflex-native validation and platform controls. It explicitly does not claim HOL Guard runs inside the Reflex server.The Claude marketplace manifest is updated so the skill is included in the existing
reflex@reflex-agent-skillsplugin install surface.Testing
AI-assisted contribution. I validated the changed paths against the repository's current skill structure, marketplace manifest, and sanity-test discovery model. I did not run an interactive agent-host protection session in this environment, so I am not claiming that runtime test.
Scope
Two files only: the new skill and the existing marketplace skill list. No Reflex framework/runtime code changes.