Add agent-guard to Tools & Frameworks#26
Open
yui-stingray wants to merge 1 commit into
Open
Conversation
Author
|
Disclosure: I maintain agent-guard. It is still alpha, and the current benchmark is self-authored rather than independently validated; I included that caveat in the README/PR text. Happy to adjust the wording or placement if you prefer a more neutral entry. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adding agent-guard, a vendor-neutral static evidence and conformance layer for repositories maintained with coding agents.
What it does: inventories agent-facing repository surfaces such as instruction files, skills, MCP metadata, policies, and workflows; checks reviewed static rules and digests; and emits deterministic, sanitized JSON, Markdown, SARIF, and evidence-pack metadata for CI and maintainer review.
Boundary: it does not execute agents, skills, or MCP servers, run LLM review, validate live OAuth flows, or replace a dedicated secret scanner. Its role is to make reviewed repository configuration and drift inspectable through stable evidence contracts.
Project status: MIT-licensed Python package on PyPI with a GitHub Action and pre-commit integration. The project is alpha. Its published Agent-Guard Bench results are a self-authored static regression corpus and are explicitly not presented as independent product validation.
Disclosure: I maintain agent-guard. Happy to adjust the wording or placement to match this list's conventions.