Skip to main content
Integrate CodeAnt AI into Cursor to resolve PR review comments, review local changes, and generate custom review rules - driven by Cursor’s AI agent.

What You Get

Four Cursor Skills that teach the AI agent how to use the CodeAnt CLI:

Prerequisites

  1. Cursor 2.4 or later - the new Skills system requires this minimum version (download)
  2. CodeAnt CLI installed and authenticated - follow the CLI setup guide

Installation

Run these commands from your project root:
Commit to share with your team:

Option 2: Create Manually

Create the skill files under .cursor/skills/ - see the full skill content in the skills repository. Each skill is a SKILL.md file inside its own directory:
If you previously installed the .mdc rule file to .cursor/rules/codeant.mdc, you can migrate to the new Skills format:
  1. Install the new skills using the instructions above
  2. Delete the old rule file: rm .cursor/rules/codeant.mdc
  3. Restart Cursor
The new Skills format provides slash command invocation, better discoverability, and feature parity with the Claude Code integration.

Usage

/codeant-resolve-pr-comments - Resolve PR Review Comments

Fetch all unresolved CodeAnt AI review comments on a pull request and fix them. With a PR number:
Auto-detect from current branch:
Or use natural language:
The fix flow:
  1. Find the PR - detects from current branch or uses the provided PR number
  2. Fetch comments - runs codeant pr comments --pr-number <N> --codeant-generated true and filters to unresolved comments
  3. Categorize - separates inline code comments (actionable) from general PR-level comments (informational, skipped)
  4. Analyze and assign verdicts - for each comment:
    • Reads the file with 30 lines of surrounding context
    • Checks the code still matches what the comment describes
    • Extracts code suggestions from the comment body
    • Validates syntax, variable scope, imports, and that existing logic is not broken
    • Assigns a verdict: ACCEPT, LIKELY ACCEPT, DO NOT ACCEPT, or STALE
  5. Present summary - shows all comments grouped by verdict with before/after code diffs
  6. Apply safe fixes - applies ACCEPT fixes, asks about LIKELY ACCEPT, skips DO NOT ACCEPT and STALE
  7. Resolve threads - marks applied comments as resolved on the PR via codeant pr resolve
  8. Offer to commit - lists changed files and offers to commit and push
Changes are not committed automatically - you review the diffs and decide.

/codeant-resolve-quality-gates - Fix CI/CD Quality Gate Failures

Locate the CodeAnt Quality Gate comment posted by CI on the current branch’s PR and fix the listed findings. With a PR number:
Auto-detect from current branch:
Or use natural language:
The fix flow:
  1. Find the PR - detects from current branch or uses the provided PR number
  2. Locate the comment - fetches CodeAnt comments and picks the most recent one whose body starts with CodeAnt Quality Gate Results
  3. Parse failures - extracts the list of failed gates from the summary table and the per-finding rows from the View Failure Result block (SAST, Secrets, Duplicate Code)
  4. Analyze and assign verdicts - for each finding:
    • Reads the file at the indicated line with 30 lines of context
    • Drafts a minimal fix (the comment contains no inline suggestion - the skill designs the fix from the rule / type / window)
    • Validates syntax, scope, error handling, and that existing behavior is preserved
    • Assigns a verdict: ACCEPT, LIKELY ACCEPT, DO NOT ACCEPT, or STALE
  5. Present summary - groups findings by verdict and gate type, shows before/after diffs
  6. Apply safe fixes - ACCEPT automatically, LIKELY ACCEPT with confirmation, skip the rest
  7. Offer to commit - pushing the fix commit re-triggers CI, which updates the quality gate comment
Coverage by gate: Changes are not committed automatically - you review the diffs and decide.

/codeant-review - Review and Fix Local Changes

Run a CodeAnt AI code review on your local changes and fix all issues found.
You can specify the review scope:
The skill selects the right flag based on your request: The fix flow:
  1. Run review - executes codeant review <scope-flag>
  2. Present findings - shows issues grouped by file with category labels (Security, Code Quality, Performance, Maintainability)
  3. Analyze and assign verdicts - classifies each issue as ACCEPT, LIKELY ACCEPT, DO NOT ACCEPT, or STALE
  4. Present summary with verdicts - shows before/after code diffs, highlights Security issues first
  5. Apply safe fixes - minimal changes only, skips anything that could break existing logic
  6. Verify - re-runs the review to confirm fixes are clean
  7. Report - initial findings, fixes applied, fixes skipped (and why), and verification results
Changes are not committed automatically - you review the diffs and commit when ready.

/codeant-implement-repo-learnings - Generate Custom Review Rules

Analyze your team’s PR review history to generate custom CodeAnt review rules.
The workflow:
  1. Fetch PR history - retrieves the last 100 merged PRs
  2. Extract human feedback - fetches review comments, filters out bots and non-actionable replies
  3. Analyze bug-fix commits - mines git history for recurring fix patterns
  4. Read project guidelines - extracts conventions from .cursorrules, CLAUDE.md, CONTRIBUTING.md, etc.
  5. Cluster patterns - groups feedback into rule candidates with confidence levels (HIGH/MEDIUM)
  6. Interactive confirmation - presents each rule with evidence for your approval
  7. Write rules - generates .codeant/review.json with your approved rules
Rules are merged with any existing .codeant/review.json - nothing is overwritten without confirmation.

Verdict System

All fix workflows use a verdict system to classify each suggestion before applying:

Example Workflows

Resolve PR Comments

Review → Fix → Ship

How It Works

Each skill is a SKILL.md file inside .cursor/skills/ - part of Cursor’s Agent Skills system. Skills teach the Cursor agent specialized workflows through detailed step-by-step instructions. Skills are automatically discovered by Cursor and can be invoked via /skill-name slash commands or triggered automatically when the agent determines they’re relevant. You can also reference them naturally in conversation (e.g., “review my changes with CodeAnt”).

Troubleshooting

“codeant: command not found” Ensure the CLI is installed globally and accessible from Cursor’s terminal:
If using nvm, ensure the correct Node version is active in Cursor’s integrated terminal. “Not authenticated” or “Could not detect remote”
Skills not appearing
  • Verify .cursor/skills/codeant-review/SKILL.md exists (and similar for other skills)
  • Restart Cursor after adding skills
  • Check Settings → Rules to see if skills appear under “Agent Decides”
  • Be explicit: “Use CodeAnt to review my changes” or use /codeant-review