Add exact-bound agent action verification skill 🤖🤖🤖 - #2476
Merged
aaronpowell merged 1 commit intoAug 5, 2026
Merged
aaronpowell merged 1 commit into
aaronpowell merged 1 commit into
Conversation
Copy link
Copy Markdown
Contributor
Sorry, something went wrong.
Add a non-executing review workflow for recomputation, exact action binding, replay, reviewer dependence, evidence conflict, and monitoring freshness.\n\nAssisted-by: OpenAI Codex
Copy link
Copy Markdown
Contributor
🔒 PR Risk Scan ResultsScanned 1 changed file(s).
✅ No matching risk patterns were detected in changed files.
|
Sorry, something went wrong.
Copy link
Copy Markdown
Contributor
|
🔴 Contributor Reputation Check: HIGH risk
Maintainers: please review this contributor before merging. |
Sorry, something went wrong.
Copy link
Copy Markdown
Contributor
🔍 Vally Lint Results✅ All checks passed
Summary
### Linting skills/verify-agent-action
✅ verify-agent-action (2/2 checks passed)
✓ [spec-compliance] All 1 skill(s) are spec-compliant.
✓ spec-compliance: All spec checks passed.
✓ [valid-refs] All file references across 1 skill(s) are valid.
✓ valid-refs: All file references resolve to existing files within the skill directory.
1 skill(s) linted, 1 passed
|
Sorry, something went wrong.
aaronpowell
approved these changes
Aug 5, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 verify-agent-action, an opt-in, non-executing skill for reviewing consequential AI-agent actions before a human or external enforcement point decides whether to act.
The workflow checks six linked failure classes:
Why this is distinct
Existing governance, compliance, evaluation, and security-review skills cover broader system design or code posture. This skill is narrowly focused on the final pre-execution packet: whether the exact action presented now is the same action supported, assessed, and approved earlier.
It preserves supporting and refuting evidence separately, includes six hostile mutations, and produces one of four review outcomes without turning any outcome into execution authority.
Safety boundary
Scope
Validation
A model-response smoke could not be completed because the account's Copilot CLI policy denied the request before evaluation. No behavior beyond successful installation and discovery is claimed from that check.
Assisted-by: OpenAI Codex
Human verification: VrtxOmega