By jakozloski
Manage GitHub pull requests from the terminal with CI/CD status indicators, reviews, comments, and merge actions. Also monitors bash command errors to identify failures in shell output.
A Claude Code plugin that displays GitHub PR status, CI/CD checks, and merge capability directly in your terminal.
git clone https://github.com/jakozloski/claude-code-gh-dash.git
claude --plugin-dir /path/to/claude-code-gh-dash
Add to your shell config for permanent use:
alias claude="claude --plugin-dir /path/to/claude-code-gh-dash"
Add to your project's .claude/plugins.json:
{
"plugins": ["github:jakozloski/claude-code-gh-dash"]
}
GitHub CLI - The plugin uses gh CLI for all GitHub operations:
brew install gh
gh auth login
/gh-dash:pr
┌────────────────────────────────────────────────────────────┐
│ PR #98: test: add test comment for PR plugin testing v7 │
│ test/pr-plugin-test-7 → main │
├────────────────────────────────────────────────────────────┤
│ Status OPEN · Mergeable ✅ │
│ Changes 3 files · +45 −12 │
├────────────────────────────────────────────────────────────┤
│ CI/CD [████████░░░░░░░░░░░░] 40% (8/20) │
│ ✅ 6 passed ⏳ 6 running ⏭️ 8 skipped │
├────────────────────────────────────────────────────────────┤
│ ⏳ Running Lint, Type Check, Unit Tests, Vercel │
├────────────────────────────────────────────────────────────┤
│ 💬 Comments │
│ 🐛 Bugbot: Removed test comment (diff now empty) │
│ 🐰 CodeRabbit: ✅ LGTM - Trivial │
│ 📊 Coverage: 20.31% (1991/9802 lines) │
├────────────────────────────────────────────────────────────┤
│ 🔗 Links │
│ PR: https://github.com/owner/repo/pull/98 │
│ Preview: https://your-preview-url.vercel.app │
├────────────────────────────────────────────────────────────┤
│ ⚡ Actions │
│ /gh-dash:pr --merge (squash - default) │
│ /gh-dash:pr --merge merge (merge commit) │
│ /gh-dash:pr --merge rebase (rebase) │
└────────────────────────────────────────────────────────────┘
# Squash merge (default)
/gh-dash:pr --merge
# Merge commit
/gh-dash:pr --merge merge
# Rebase
/gh-dash:pr --merge rebase
| Icon | Meaning |
|---|---|
| ✅ | Success / Approved / LGTM |
| ❌ | Failed / Changes requested |
| ⏳ | In Progress / Pending |
| ⏭️ | Skipped / Neutral |
| ⚠️ | Merge conflicts |
| Icon | Bot |
|---|---|
| 🐰 | CodeRabbit |
| 🐛 | Cursor Bugbot |
| 📊 | Coverage reports |
| ▲ | Vercel |
The plugin includes a PostToolUse hook that automatically suggests running the PR dashboard after creating a PR with gh pr create.
The hook is located at hooks/hooks.json and uses a shell script (hooks/pr-trigger.sh) to detect when a PR is created.
Note: If using the plugin via --plugin-dir, the hook is automatically loaded. If you want to add it manually to your project, add to .claude/settings.json:
{
"hooks": {
"PostToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "/path/to/claude-code-gh-dash/hooks/pr-trigger.sh"
}
]
}
]
}
}
Requires: jq for JSON parsing (brew install jq)
MIT
Executes bash commands
Hook triggers when Bash tool is used
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub jakozloski/claude-code-gh-dashConsult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Production-grade academic research pipeline for Claude Code: research → write → review → revise → finalize. 4 skills, 27 modes, 39-agent ensemble, v3.7.3 + v3.8 L3 claim-faithfulness gate, v3.9.0 cross-index triangulation, v3.10 triangulation policy layer, v3.11 deterministic citation verification gate (#182).