Skip to content
Agentmart
Submit a tool

github-pr-review

Evaluate GitHub CodeQL and Copilot suggestions on PRs — fetch, triage, propose fixes.

Skill by gitricko

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying github-pr-review?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/gitricko-github-pr-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Evaluate GitHub CodeQL and Copilot suggestions on PRs — fetch, triage, propose fixes.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/github-pr-review

What's inside

Skill name
github-pr-review
Description
Evaluate GitHub CodeQL and Copilot suggestions on PRs — fetch, triage, propose fixes.
License
MIT
Instructions
196 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Files (1)

  • SKILL.md

SKILL.md (first lines)

# GitHub PR Review: CodeQL & Copilot Suggestions

Evaluates automated review comments from GitHub Advanced Security (CodeQL)
and GitHub Copilot on pull requests. Fetches comments, triages by severity,
and proposes fixes with a decision framework.

## Prerequisites

- GitHub API access (token via `/proc/PID/environ` or `gh auth`)
- PR number or URL

## Workflow

### Step 1: Fetch Review Comments

```bash
# Get PR review comments (CodeQL + Copilot inline comments)
curl -s "https://api.github.com/repos/{owner}/{repo}/pulls/{PR}/comments" \
  -H "Authorization: token $TOKEN" | python3 -c "
import json, sys
comments = json.load(sys.stdin)
for c in comments:
    author = c.get('user', {}).get('login', '?')
    if 'advanced-security' in author or 'copilot' in author:
        print(f'---')
        print(f'File: {c.get(\"path\", \"?\")}')
        print(f'Line: {c.get(\"line\", \"?\")}')
        print(f'Author: {author}')
        print(f'Body: {c.get(\"body\", \"\")[:500]}')
"
```

### Step 2: Triage by Source

| Source | What It Checks | Typical Findings |
|--------|---------------|------------------|
| `github-advanced-security[bot]` | CodeQL static analysis | Security vulnerabilities, workflow permissions, injection risks |
| `Copilot` | Code quality suggestions | Inconsistent naming, dead code, style issues |
| `copilot-pull-request-reviewer` | PR-level review | Logic errors, missing tests, documentation |

### Step 3: Evaluate Each Suggestion

For each comment, apply this decision framework:

#### ACCEPT if:
- Security issue (CodeQL finding) → always accept or explicitly justify rejection
- Workflow permission too broad → add `permissions:` block
- Actual bug or logic error → fix the code
- Inconsistent naming/branding → fix (e.g., wrong logo on badge)

#### REJECT if:
- False positive (CodeQL misidentification) → document why
- Style preference only (no functional impact) → note but skip
- Would break existing behavior without clear benefit → reject
- Suggestion is overly aggressive (e.g., "rename all variables") → reject

#### DEFER if:
- Requires architectural change → propose in separate PR
- Needs user decision → present options, wait for approval
- Unclear impact → investigate further before acting

### Step 4: Present Proposal

Format as a table for user review:

```
=== CodeQL & Copilot Review: PR #N ===

| # | Severity | Source | File | Suggestion | Proposal | Effort |
|---|----------|--------|------|------------|----------|--------|
| 1 | High     | CodeQL | workflow.yml | Missing permissions block | ACCEPT — add permissions: contents: read | 2 lines |
| 2 | Low      | Copilot | README.md | Wrong badge logo | ACCEPT — fix logo parameter | 1 line |
| 3 | Medium   | CodeQL | script.sh | Unquoted variable | REJECT — variable is intentionally word-split | 0 lines |

Summary: 2 accept, 1 reject, 0 defer
```

### Step 5: Implement Accepted Fixes

After user approval:
1. Make the changes
2. Commit with descriptive message
3. Push and verify CI passes
4. Optionally reply to the review comment with the fix

### Step 6: Seed Export Check (Pre-Merge)

Before merging, check if new high-value Mnemon entries should be added to seed.json:

```bash
scripts/check-seed-export.sh
```

This script:
1. Queries Mnemon for entries with importance >= 4
2. Compares against existing seed.json content
3. Reports any new entries that should be exported

**If new entries found:**
1. Review each entry for relevance
2. Add to `mnemon/seed.json` with proper format
3. Validate: `mnemon import --dry-run mnemon/seed.json`
4. Commit updated seed.json with the PR

**Why this matters:**
- Seed file is the persistent knowledge catalog across sessions
- New wiki articles, key decisions, and architecture facts should be seeded
- Ensures future Codespaces start with all important knowledge

## API Endpoints

| Endpoint | Purpose |
|----------|---------|
| `GET /repos/{owner}/{repo}/pulls/{PR}/comments` | Inline review comments |
| `GET /repos/{owner}/{repo}/issues/{PR}/comments` | Top-level PR comments |
| `GET /repos/{owner}/{repo}/pulls/{PR}/reviews` | Full review objects |
| `POST /repos/{owner}/{repo}/pulls/{PR}/comments/{ID}/replies` | Reply to a comment |

## Common CodeQL Findings

From gitricko/.minions, MIT.

More from gitricko/.minions

Signals

Stars
1
Forks
2
Open issues
3
Last commit (this folder)
Sep 11, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from gitricko

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get github-pr-review running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying github-pr-review?

CallGet help
Cite this page

github-pr-review skill. Agent Mart. https://agentmart.dev/skills/gitricko-github-pr-review (last updated 2026-10-24)