gds-code-review

Reviews code changes adversarially using parallel review layers and structured triage.

6|Updated Aug 29, 2026
One-click install
npx skills add https://github.com/HordRicJr/Akomagni --skill gds-code-review-hordricjr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gds-code-review
Source: https://github.com/HordRicJr/Akomagni/tree/main/bmad-core/.agents/skills/gds-code-review
Command: npx skills add https://github.com/HordRicJr/Akomagni --skill gds-code-review-hordricjr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code reviews often miss subtle bugs, edge cases, and deviations from the spec because a single reviewer pass cannot cover every angle. This Skill runs adversarial multi-layer reviews of code changes and triages findings into actionable categories so nothing slips through. ## Core Features & Use Cases - Parallel Adversarial Review Layers: Runs a Blind Hunter (diff-only), Edge Case Hunter (diff plus project access), and Acceptance Auditor (diff plus spec) to catch different classes of issues. - Structured Triage: Normalizes, deduplicates, and classifies findings into decision_needed, patch, defer, or dismiss buckets. - Story and Sprint Integration: Writes findings into story files, updates story status, and syncs sprint-status.yaml tracking. - Use Case: After finishing a feature branch, ask for a code review; the Skill gathers the diff, launches the three review layers, triages the findings, and lets you apply patches or defer items with full traceability. ## Quick Start Run a code review on my current branch changes against main and triage any findings.

Frequently Asked Questions about gds-code-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run an adversarial code review on my changes?

Trigger the review by saying "run code review" or "review this code". The Skill identifies the review target from a PR, commit, branch, staged changes, or sprint status, constructs the diff, and launches parallel review layers automatically.

What review layers does this code review workflow use?

It uses three parallel layers: a Blind Hunter that sees only the diff, an Edge Case Hunter with project read access, and an Acceptance Auditor that checks the diff against the spec. Findings are merged, deduplicated, and triaged.

Can I review code without a spec or story file?

Yes. The workflow supports a no-spec mode where the Acceptance Auditor layer is skipped. Findings that would require a decision are reclassified as patch or defer, and results are presented without writing to a story file.

What diff sources are supported for code review?

Supported sources include uncommitted changes, staged changes only, branch diffs against a base branch, specific commit ranges, user-provided diffs, and explicit file lists. Empty or unparseable diffs halt the workflow with a prompt.

What happens to review findings after triage?

Findings are classified as decision_needed, patch, defer, or dismiss. Patch findings can be applied automatically or left as action items, deferred items go to a deferred-work file, and story status plus sprint-status.yaml are updated.

What happens if a review subagent fails or times out?

The failed layer is recorded in a failed_layers list and the review proceeds with the remaining layers. If no findings remain and layers failed, the user is warned the review may be incomplete rather than told it is clean.