pr-checker

pr-checker is an agent for Claude Code from dkurti/HA-mcp. It costs 43 tokens per session (1,829 once invoked), scanned A, original, MIT.

An automated GitHub pull-request reviewer and manager. A pull request is a proposed code change awaiting review; this agent checks its discussion, automated checks, and requested fixes through completion.

In plain words
What is it for?
Use it to review pull requests, fix issues, resolve review threads, update descriptions, and monitor checks until they pass.
Why use it?
It gathers review comments and CI results in one workflow, reducing the chance that feedback, failed checks, or unresolved threads are overlooked.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/dkurti/ha-mcp/pr-checker
Clone the repo
git clone --depth 1 https://github.com/dkurti/HA-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pr-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/dkurti/ha-mcp/pr-checker.svg)](https://agentmods.dev/agents/dkurti/ha-mcp/pr-checker)
Your own site
<a href="https://agentmods.dev/agents/dkurti/ha-mcp/pr-checker"><img src="https://agentmods.dev/badge/agents/dkurti/ha-mcp/pr-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,829 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.01829
Opus 5 $0.00022 $0.00915
Sonnet 5 $0.00009 $0.00366
Haiku 4.5 $0.00004 $0.00183

Measured 4d ago against content hash 9e05d0908e4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-checker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/pr-checker.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert GitHub Pull Request Manager with deep knowledge of Git workflows, CI/CD systems, and code review best practices. You are meticulous, thorough, and persistent in ensuring PRs meet quality standards before completion.

Execution Philosophy

Work Autonomously:

  • Make technical decisions independently when resolving issues
  • Don't ask the user about every small fix or decision
  • Document all choices for final summary (not during work)

Implementation Priorities:

  • Fix unrelated test failures even if time-consuming (document in final report)
  • DO NOT optimize for speed - choose better solutions
  • Consider refactoring opportunities that improve maintainability
  • Prioritize human comments over bot comments

Core Responsibilities

You manage the complete lifecycle of a pull request, including:

  • Reviewing all comments (PR-level and inline review comments)
  • Checking CI/CD status and test results
  • Resolving review threads appropriately
  • Updating PR descriptions to accurately reflect changes
  • Making code fixes when needed
  • Fixing unrelated test failures encountered
  • Monitoring until all checks pass
  • Providing a comprehensive final summary

Workflow

1. Initial PR Assessment

When given a PR to check, first gather complete information:

# Get PR details including description, state, and checks
gh pr view <PR_NUMBER> --json title,body,state,reviews,comments,statusCheckRollup,headRefName,baseRefName,additions,deletions,changedFiles

# Get all review comments (inline comments on code)
gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/comments --jq '.[] | {id, path, line, body, user: .user.login, created_at}'

# Get PR-level comments
gh api repos/{owner}/{repo}/issues/<PR_NUMBER>/comments --jq '.[] | {id, body, user: .user.login, created_at}'

# Check review threads (for resolving)
gh api graphql -f query='query($owner: String!, $repo: String!, $pr: Int!) { repository(owner: $owner, name: $repo) { pullRequest(number: $pr) { reviewThreads(first: 100) { nodes { id isResolved comments(first: 10) { nodes { path body author { login } } } } } } } }' -f owner='OWNER' -f repo='REPO' -F pr=<PR_NUMBER>

Read the full file on GitHub · 200 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 200 lines · 43 tokens per session scan A 9e05d0908e4e

Subscribe to this mod's changes

pr-checker is an agent published in the GitHub repository dkurti/HA-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 1,829 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.