fix-pr

fix-pr is a skill for Claude Code, Cursor from theam/claude-dev-kit. It costs 66 tokens per session (1,565 once invoked), scanned A, original, Apache-2.0.

A workflow for finishing an existing pull request, a proposed code change submitted for review, by handling review comments, failed checks, and self-found problems.

In plain words
What is it for?
Use it to fix valid findings, defer work to tracked issues, dismiss irrelevant comments, reply to reviewers, and recheck automated tests.
Why use it?
It turns scattered feedback into clear decisions and verifies the changes again after fixes or new feedback.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: $CLAUDE_PLUGIN_ROOT variable, but also shipped in a Cursor plugin. Also seen: names the AskUserQuestion tool; mentions Claude Code; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the fullstack-dev-kit plugin — 13 skills shipped together

Good fit Use it to fix valid findings, defer work to tracked issues, dismiss irrelevant comments, reply to reviewers, and recheck automated tests.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add theam/claude-dev-kit
Claude Code
/plugin install fullstack-dev-kit

Made for: Claude Code, Cursor.

Or install fullstack-dev-kit, the plugin that ships this one along with the rest of its 13 skills.

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 fix-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/theam/claude-dev-kit/fix-pr/github.svg)](https://agentmods.dev/skills/theam/claude-dev-kit/fix-pr)
Your own site
<a href="https://agentmods.dev/skills/theam/claude-dev-kit/fix-pr"><img src="https://agentmods.dev/badge/skills/theam/claude-dev-kit/fix-pr/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fix-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/theam/claude-dev-kit/fix-pr"><img src="https://agentmods.dev/badge/skills/theam/claude-dev-kit/fix-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,565 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00066 $0.01565
Opus 5.5 $0.00026 $0.00626
Sonnet 5.5 $0.00013 $0.00313
Haiku 4.5 $0.00007 $0.00156

Measured 1mo ago against content hash 1450a91bb810, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

plugins/fullstack-dev-kit/skills/fix-pr/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fix PR

Drive a PR's feedback to done: run a review, triage every item to a decision, fix what deserves fixing, file what deserves doing later, discard what deserves nothing, answer every reviewer, and re-check after pushing in case late feedback (bots, CI) arrives. The bar for correctness is high; the bar for new machinery is low — fix the defect, don't redesign around it.

0. Confirm the PR exists and is open (before anything else)

Resolve the PR from the current branch — never trust a PR number carried over from earlier in the session (it may be stale; acting on the wrong one, or claiming you did, is a false report). Run gh pr view --json number,state,url,headRefName (no argument = the current branch's PR), or gh pr view <pr> --json number,state,url when the user named one, and read state:

  • OPEN → proceed.
  • CLOSED / MERGED → stop. Do not push commits, comment, resolve threads, or "post" anything to it — a closed or merged PR won't take the work. Tell the user the PR is closed/merged and offer the real options: reopen it (if that's the intent), open a fresh PR from the current branch (create-pr), or point you at the correct open PR. Never claim you posted changes to it.
  • No PR for the branch → there's nothing to fix; that's create-pr, not fix-pr.

For bitbucket/gitlab, do the equivalent state check (/pullrequests/{id} → state; glab mr view <id>). Never report having pushed to, commented on, or updated a PR you didn't first confirm is open.

1. Establish the PR intent (the scope ruler)

Write one or two sentences: what this PR is for, and what it deliberately does not change — derived from the title, body, linked issue, and the diff. Every scope call below is measured against it. If the intent is genuinely ambiguous, ask the author before triaging.

2. Gather the findings

Collect from every surface, deduplicated. Commands below are for github (prHost in .claude/dev-kit.json); for bitbucket use the REST API (/pullrequests/{id} comments, /statuses), for gitlab glab mr view/checks.

Read the full file on GitHub · 69 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. 1mo ago Changed · +10 lines 1450a91bb810
  2. 2mo ago First seen · 59 lines · 66 tokens per session scan A 6c975cd3d6d5

Subscribe to this mod's changes

fix-pr is a skill published in the GitHub repository theam/claude-dev-kit (16 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,565 once invoked, about $0.0003 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

draft-pr

Writes a PR title and description to .workflow/ /pr.md from the branch's commits, the plan and the recorded verification. Use when opening a PR or asked for a PR description.

matheusPavaneli/workbench · 42 tokens

address-review

Turns PR review comments into a triaged change list, applies the accepted ones, and drafts replies to .workflow/ /review-response.md. Use when a PR has feedback to work through.

matheusPavaneli/workbench · 42 tokens

write-commit

Writes a commit message in the repo's own convention, validated and saved to .workflow/ /commit.txt. Use when asked to commit, or to write or fix a commit message.

matheusPavaneli/workbench · 42 tokens

run

The single lifecycle entry point — take one or more tickets and drive each through its whole lifecycle (investigate, red tests, implement, gates, review, PR, merge, archive), interleaving them. Lean by default — one worker per ticket runs red tests, implementation and the gate scripts in one worktree, then…

iansmith/slopstop · 113 tokens

release

Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…

hyhmrright/brooks-lint · 135 tokens

pr

Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.

umputun/cc-thingz · 51 tokens