feat(copilot): add multi-agent code review skills#707
Merged
Conversation
Add Copilot review skills, project instructions, and coding agent setup for automated code review on regorus PRs. Files added: - .github/copilot-instructions.md — project context (no_std, 9 bindings, dual execution paths, deny lints, security-critical evaluation) - .github/skills/code-review/SKILL.md — fast single-agent review (~2 min) - .github/skills/deep-review/SKILL.md — multi-agent deep review (~12 min) - .github/copilot-setup-steps.yml — minimal coding agent environment Development and testing methodology: The skills were developed iteratively (v3 through v11.4) against a 460-line SARIF output module on the feature/sarif-output branch, which served as a controlled test bed with 25 known issues of varying severity (correctness, safety, API design, platform, security, performance). Each version was tested by running the skill via the Copilot CLI, then mapping discovered findings against the ground truth set to measure recall and precision. Key iterations: - v3: baseline single-agent (8/25 recall, 32%) - v7: 3 parallel agents + verification (14/25, 56%) - v10c: model diversity + adversarial pass (10/25, 40%) - v11.3: merged adversarial-verifier architecture (12/25 + 2 novel, 0 noise) - v11.4: domain expertise prompting (12/25 + 2 novel, 0 noise, full report) The final architecture uses 3 parallel discovery agents (with cross-model diversity and context asymmetry), risk-triggered micro-passes, and a single adversarial verifier that both validates candidates via disproval and hunts blind spots. Agents are prompted to reason from policy-author perspective across Rego/OPA, Azure Policy, and RVM workloads. Combined CR+DR catches 16-17/25 ground truth with zero false positives and produces verified findings with confidence levels, test gap analysis, and agent performance metrics. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Adds GitHub Copilot “skills” and repo-specific instructions to support automated, multi-agent diff-based code review workflows for regorus PRs.
Changes:
- Add two review skills (
code-review,deep-review) with structured phases, prompts, and reporting formats. - Add repository Copilot instructions capturing key invariants (no_std discipline, FFI panic poisoning, dual execution paths, limits).
- Add minimal Copilot coding agent setup steps with a pinned
actions/checkout.
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated 6 comments.
| File | Description |
|---|---|
| .github/skills/deep-review/SKILL.md | Defines a multi-agent, phased deep-review workflow and orchestration steps. |
| .github/skills/code-review/SKILL.md | Defines a faster, everyday review workflow with triage + 3-pass review guidance. |
| .github/copilot-setup-steps.yml | Adds agent environment setup steps (checkout with full history). |
| .github/copilot-instructions.md | Adds project-specific invariants, constraints, and build/test guidance for Copilot. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Collaborator
Author
|
@copilot re-review |
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 4 out of 4 changed files in this pull request and generated 6 comments.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
dpokluda
approved these changes
May 4, 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.
Add Copilot review skills, project instructions, and coding agent setup for automated code review on regorus PRs.
Files added
.github/copilot-instructions.md— project context (no_std, 9 bindings, dual execution paths, deny lints, security-critical evaluation).github/skills/code-review/SKILL.md— fast single-agent review (~2 min).github/skills/deep-review/SKILL.md— multi-agent deep review (~12 min).github/copilot-setup-steps.yml— minimal coding agent environmentTesting methodology
Skills were developed iteratively (v3→v11.4) against a 460-line SARIF module with 25 known issues. Final architecture: 3 parallel discovery agents + risk-triggered micro-passes + adversarial verifier. Combined CR+DR catches 16-17/25 ground truth with zero false positives.