fix-pr

A command for fixing a GitHub pull request, which is a proposed set of code changes, using review comments, automated checks, and CI failures.

In plain words
What is it for?
Use it with a pull request number or URL to inspect comments and status checks, then fix the reported issues.
Why use it?
It gathers feedback and failed checks in one workflow so problems blocking the pull request can be addressed systematically.

Command

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 commands/jeffh/claude-plugins/fix-pr
Clone the repo
git clone --depth 1 https://github.com/jeffh/claude-plugins
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,044 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 $0.00014 $0.01044
Opus 5 $0.00007 $0.00522
Sonnet 5 $0.00003 $0.00209
Haiku 4.5 $0.00001 $0.00104

Measured 2d ago against content hash 782fe7292e25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fix-pr 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 2d 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.

gh/commands/fix-pr.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix PR

You are tasked with fixing issues on a Pull Request based on review feedback, status checks, and CI failures.

Input

The user will provide either:

  • A PR number (e.g., 123)
  • A PR URL (e.g., https://github.com/owner/repo/pull/123)

If just a number is provided, assume it's for the current repository.

Process

1. Gather PR Information

First, collect all relevant information about the PR:

# Get PR details (number, title, state, base branch)
gh pr view {PR} --json number,title,state,baseRefName,headRefName,body

# Get review comments (code review feedback)
gh api repos/{owner}/{repo}/pulls/{PR}/comments --jq '.[] | {path: .path, line: .line, body: .body, user: .user.login, created_at: .created_at}'

# Get PR review summaries (approved, changes requested, etc.)
gh api repos/{owner}/{repo}/pulls/{PR}/reviews --jq '.[] | {state: .state, body: .body, user: .user.login}'

# Get issue comments (general discussion on the PR)
gh api repos/{owner}/{repo}/issues/{PR}/comments --jq '.[] | {body: .body, user: .user.login, created_at: .created_at}'

# Get status checks
gh pr checks {PR} --json name,state,conclusion,description

# Get workflow run details for failed checks
gh run list --branch {head_branch} --limit 5 --json databaseId,name,conclusion,status

For failed workflow runs, get the logs:

gh run view {run_id} --log-failed

2. Analyze Feedback

Categorize all gathered feedback into:

  1. CI Failures: Failed status checks, workflow errors, test failures
  2. Review Comments: Code review feedback with specific file/line references
  3. Change Requests: Reviews marked as "changes requested" with specific asks
  4. General Comments: Discussion comments that may contain actionable feedback
  5. Unclear Feedback: Comments that don't have a clear action item

3. Create Task List

Use the TodoWrite tool to create a task list of all issues to fix. Each task should be specific and actionable:

  • For CI failures: "Fix [test name] in [file]" or "Resolve [error type] in CI"
  • For review comments: "Address review comment on [file:line] - [summary]"
  • For change requests: "Implement requested change: [description]"

Read the full file on GitHub · 134 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. 2d ago First seen · 134 lines · 14 tokens per session scan A 782fe7292e25

Subscribe to this mod's changes

fix-pr is a command published in the GitHub repository jeffh/claude-plugins (12 stars, last pushed 18d ago), licensed Apache-2.0. It adds 14 tokens to every session and 1,044 once invoked, about $0.0001 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 2026-08-30.