VerifiedPlugin
impeccable
Design guidance for AI coding agents. 1 skill, 24 commands, live browser iteration, and 61 deterministic detector rules for AI-generated frontend design.
1 skill4 agents+171k
@pbakausCode Review
Plugin
agent-reviews
Manage GitHub PR review comments from the terminal and from AI coding agents. PR review bots (Copilot, Cursor Bugbot, CodeRabbit, etc.) leave inline comments on your pull requests.
Plugin Signal71/100Solid
maintained98
capable29
documented100
adopted52
Install on Claude Code
> /plugin marketplace add pbakaus/agent-reviews
Stats
284
Stars
25
Forks
Active
Maintenance
JavaScript
Language
MIT
License
5d ago
Last commit
7mo ago
Created
Repo: pbakaus/agent-reviews
What's inside
Skill(3 skills)
/resolve-agent-reviewsResolve PR review bot findings on current PR. Fetches unanswered bot comments, evaluates each finding, fixes real bugs, dismisses false positives, replies to every comment, and watches for new findings until bots go quiet./resolve-human-reviewsResolve human PR review comments on current PR. Fetches unanswered human comments, evaluates each piece of feedback, applies fixes, and replies to every comment with the outcome./resolve-reviewsResolve all PR review comments (human and bot) on current PR. Fetches unanswered comments, evaluates each one, fixes real issues, dismisses false positives, and replies to every comment with the outcome.
README
agent-reviews
Manage GitHub PR review comments from the terminal and from AI coding agents.
PR review bots (Copilot, Cursor Bugbot, CodeRabbit, etc.) leave inline comments on your pull requests. agent-reviews gives you a CLI to list, filter, reply to, and watch those comments, plus agent skills that automate the entire triage-fix-reply loop.
Why
gh CLI is fragile for review comments. Agents frequently get the syntax wrong, fail to paginate, and can't reliably detect whether a comment has been replied to. agent-reviews provides a single, purpose-built interface that handles all of this correctly.
Bot reviews create a doom loop. You fix one round of findings, push, and new comments appear. Fix those, push again, more comments. This cycle can eat hours. The included skills solve this with an integrated watcher that keeps fixing and replying until the bots go quiet.
Works in cloud environments. Most solutions rely on local tooling that isn't available in cloud or remote agent environments. agent-reviews works everywhere, so you can kick off a session, let the agent resolve all findings autonomously, and come back to a clean PR.
Install
CLI (npm)
npm install -g agent-reviews
Agent Skills
Three skills are available, each as a slash command (no npm install required):
| Skill | What it resolves |
|---|---|
resolve-reviews | All comments (human + bot) |
resolve-agent-reviews | Bot comments only (Copilot, Cursor, etc.) |
resolve-human-reviews | Human comments only |
Works with any agent that supports Agent Skills (Claude Code, Cursor, Codex, etc.):
npx skills add pbakaus/agent-reviews@resolve-agent-reviews
Replace resolve-agent-reviews with whichever skill you want. Skills use npx agent-reviews at runtime, so the CLI is fetched automatically.
You can also use both: install the CLI globally for direct terminal use, and a skill for the agent workflow.
Authentication
The simplest method is the GitHub CLI. If you're logged in with gh auth login, agent-reviews picks up the token automatically. No configuration needed.
For cloud/remote environments or HTTPS proxy setups, set GITHUB_TOKEN or GH_TOKEN directly. agent-reviews includes undici ProxyAgent support and will route requests through HTTPS_PROXY automatically when set.
Resolution order (first match wins):
GITHUB_TOKENenvironment variableGH_TOKENenvironment variable.env.localin the repo rootgh auth token(GitHub CLI)
Fork pull requests
Branch discovery keeps the head repository separate from the PR's base repository. It uses the branch push remote, remote.pushDefault, tracking remote, or origin (in that order), and looks for the current branch in configured GitHub repositories and the fork's parent/source repositories. The selected remote's push URL determines the head repository, including when its fetch URL points upstream. An upstream remote is not required. A single GitHub remote with another name also works.
GH_REPO=organisation/project restricts the target repository without changing the head owner. Use GH_REPO=organisation/project agent-reviews --pr 123 to select a PR explicitly, including from detached HEAD. Malformed GH_REPO values fail explicitly. If multiple open PRs match, or a matching PR has a deleted/inaccessible head repository that cannot be verified, the CLI asks for an explicit target instead of choosing one. Discovery uses the GitHub API and works with token authentication without requiring gh.
Custom API host
Set GITHUB_API_URL to point agent-reviews at a GitHub Enterprise host or any API-compatible server (useful for testing, recording, or routing through a local mediator). Defaults to https://api.github.com.
# GitHub Enterprise Server
GITHUB_API_URL=https://github.example.com/api/v3 agent-reviews
# Local API-compatible server
GITHUB_API_URL=http://127.0.0.1:8080 agent-reviews
GraphQL endpoint resolution: agent-reviews uses ${GITHUB_API_URL}/graphql by default. For GitHub Enterprise Server, where REST lives under /api/v3 and GraphQL under /api/graphql on the same origin, the trailing /api/v3 is rewritten to /api/graphql automatically. Set GITHUB_GRAPHQL_URL directly if you need full control over the GraphQL endpoint.
CLI Usage
# List all review comments on the current branch's PR
agent-reviews
# Only unresolved comments
agent-reviews --unresolved
# Only unanswered bot comments
agent-reviews --unanswered --bots-only
# Full detail for a specific comment (diff hunk + replies)
agent-reviews --detail 12345678
# Reply to a comment
agent-reviews --reply 12345678 "Fixed in abc1234"
agent-reviews --reply 12345678 --body-file body.md
# JSON output for scripting / AI agents
agent-reviews --json
# Watch for new comments (polls every 30s, exits after 10 min idle)
agent-reviews --watch --bots-only
# Target a specific PR (otherwise auto-detects from branch)
agent-reviews --pr 42
Unknown options, unexpected arguments, and invalid numeric values fail before authentication or network requests. To pass an inline reply starting with a dash, put options first and use agent-reviews --reply 12345 -- "- Fixed the issue". Everything after -- is literal text.
Options
| Flag | Short | Description |
|---|---|---|
--unresolved | -u | Only unresolved/pending comments |
--unanswered | -a | Only comments without any replies |
--reply <id> "msg" | -r | Reply to a comment |
--body-file <path> | Read reply text from a UTF-8 file instead of a positional message | |
--resolve | Resolve the review thread after replying (use with --reply) | |
--detail <id> | -d | Full detail for a comment |
--pr <number> | -p | Target a specific PR |
--json | -j | JSON output |
--bots-only | -b | Only bot comments |
--humans-only | -H | Only human comments |
--ignore-author <login> | Exclude an author from listing and watching; repeat for multiple authors | |
--expanded | -e | Show full detail for each listed comment |
--watch | -w | Poll for new comments |
--interval <sec> | -i | Poll interval in seconds (default: 30) |
--timeout <sec> | Inactivity timeout in seconds (default: 600) |
To hide workflow status comments, use agent-reviews --ignore-author 'github-actions[bot]'. Repeat the flag for multiple authors, including with --watch. Matching is case-insensitive and uses the full GitHub login, including [bot] when present. Excluded authors' top-level findings are hidden, but their replies remain visible as context in other authors' threads. Explicit --detail lookups and replies are unaffected. No authors are excluded by default.
Agent Skills
The skills automate the full PR review resolution workflow:
- Fetch unanswered comments (all, bot-only, or human-only depending on skill)
- Evaluate each finding (true positive, false positive, actionable, etc.)
- Fix real issues and run lint/type-check
- Dismiss false positives with an explanation
- Reply to every comment with the outcome
- Watch for new comments and repeat until quiet
- Report a summary of all actions taken
Skill behavior
- True positives / actionable feedback get fixed and replied with
Fixed in {commit} - False positives get replied with
Won't fix: {reason} - Uncertain findings prompt the user for guidance
- All fixes are batched into a single commit before polling begins
- Watch mode loops until no new comments appear for 10 minutes
How It Works
Comment types
agent-reviews fetches three types of GitHub PR comments:
| Type | Label | Description |
|---|---|---|
| Review comment | CODE | Inline comment attached to a specific line |
| Issue comment | COMMENT | General PR-level comment |
| Review | REVIEW | Review summary (approved, changes requested) |
Meta-comment filtering
Bot review bodies (REVIEW type) are always filtered out since actionable findings come through as inline comments. Additionally, these bot issue comments are filtered:
| Bot | What's filtered |
|---|---|
| Vercel | Deployment status ([vc]:...) |
| Supabase | Branch status ([supa]:...) |
| Cursor Bugbot | Review summary ("Cursor Bugbot has reviewed your changes...") |
| Copilot | PR review summary ("Pull request overview") |
| CodeRabbit | Walkthrough, summary, and "review skipped" comments |
| Sourcery | Reviewer's guide and PR summary |
| Codacy | Analysis summary and coverage summary |
| SonarCloud | Quality Gate pass/fail summary |
| Gemini Code Assist | "Summary of Changes" issue comment |
Reply status
Each comment displays its reply status:
| Status | Meaning |
|---|---|
no reply | No one has replied |
replied | A human has replied |
bot replied | Only bots have replied |
Watch mode
Polls the GitHub API at a configurable interval and reports new comments as they appear. Outputs both formatted text and JSON for AI agent consumption. Exits automatically after a configurable inactivity timeout (default: 10 minutes).
Reply files preserve Markdown and newlines exactly. For multiline or complex replies, write the text to a file and pass --body-file body.md to avoid shell quoting and command substitution. Both absolute and relative paths are supported; relative paths are resolved from the current directory. Prefer uniquely named temporary files outside the repository so later commits cannot accidentally include reply text. Use either a positional message or --body-file, not both; empty or whitespace-only replies are rejected. The flag works with --resolve and --json.
Changelog
1.1.0 (September 10, 2026)
- Read exact UTF-8 reply text with
--body-file, without shell command substitution. - Reject unknown flags and invalid arguments before posting; use
--for replies beginning with a dash. - Discover fork PRs across upstream repositories, separate push URLs, and GitHub Enterprise hosts.
- Exclude selected authors from listing and watching with repeatable
--ignore-author. - Reduce duplicate replies with fresh reply checks and watcher-startup reconciliation in all three skills.
- Update development dependencies to Vitest 5 and refresh website dependencies and audit fixes.
Development tests now require Node.js 22.12+, 24, or 26+ as supported by Vitest 5. CLI runtime support remains Node.js 18+.
1.0.2
- GitHub Enterprise Server support via
GITHUB_API_URLenv var (also works for local API-compatible servers used in testing). REST and GraphQL endpoints both honor it, with GHES/api/v3automatically rewritten to/api/graphql. OptionalGITHUB_GRAPHQL_URLfor unusual setups. - Gemini Code Assist meta-comment filtering: the bot's
## Summary of Changesissue comment is now dropped, while inline severity-badged findings are preserved.
1.0.0
Three skills instead of one. The single agent-reviews skill has been split into three, each tailored for different workflows:
resolve-reviewsresolves all comments (human + bot)resolve-agent-reviewsresolves bot comments onlyresolve-human-reviewsresolves human comments only
Thread resolution. The new --resolve flag marks GitHub review threads as resolved after replying. Uses the GraphQL resolveReviewThread mutation. Works with --reply in any argument order.
Expanded bot support. Added detection and meta-comment filtering for CodeRabbit, Sourcery, Codacy, SonarCloud/SonarQube Cloud, and Copilot PR reviewer, in addition to the existing Cursor Bugbot, Vercel, and Supabase filters.
Agent-harness universal. Skills now work with any agent that supports Agent Skills (Claude Code, Cursor, Codex, etc.), not just Claude Code.
File tree
More plugins by @pbakaus.
View @pbakaus’s profile@pbakausFAQ
agent-reviews is a Claude Code plugin with 3 hand-picked skills for code review work, indexed on Flowy. Install it with the command on its page. It includes resolve-agent-reviews, resolve-human-reviews, resolve-reviews. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is agent-reviews?
- Manage GitHub PR review comments from the terminal and from AI coding agents. PR review bots (Copilot, Cursor Bugbot, CodeRabbit, etc.) leave inline comments on your pull requests.
- How do I install agent-reviews?
- Run these in Claude Code: /plugin marketplace add pbakaus/agent-reviews. Then prompt normally.
- Does agent-reviews auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is agent-reviews free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it