pr-feedback

pr-feedback is a skill for Claude Code from fivol/claude-make-better. It costs 105 tokens per session (1,493 once invoked), scanned A, original, MIT.

A workflow for handling comments left by reviewers on a pull request, which is a proposed code change awaiting review. It collects each comment, tracks the chosen response, and helps reply after the changes are pushed.

In plain words
What is it for?
Use it before changing code to list unresolved comments and decide what to do with them. Use it after pushing changes to post a reply for each addressed comment, citing the fixing commit.
Why use it?
It prevents review comments from being forgotten or handled without a clear answer. Each item is either fixed, answered, or deliberately challenged.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

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 feature plugin — 5 skills, 2 commands, 2 agents shipped together

Good fit Use it before changing code to list unresolved comments and decide what to do with them. Use it after pushing changes to post a reply for each addressed comment, citing the fixing commit.

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 fivol/claude-make-better
Claude Code
/plugin install feature

Made for: Claude Code.

Or install feature, the plugin that ships this one along with the rest of its 5 skills, 2 commands, 2 agents.

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-feedback

README.md
[![agentmods](https://agentmods.dev/badge/skills/fivol/claude-make-better/pr-feedback/github.svg)](https://agentmods.dev/skills/fivol/claude-make-better/pr-feedback)
Your own site
<a href="https://agentmods.dev/skills/fivol/claude-make-better/pr-feedback"><img src="https://agentmods.dev/badge/skills/fivol/claude-make-better/pr-feedback/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 pr-feedback

Your own site · 80×15
<a href="https://agentmods.dev/skills/fivol/claude-make-better/pr-feedback"><img src="https://agentmods.dev/badge/skills/fivol/claude-make-better/pr-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,493 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 $0.00105 $0.01493
Opus 5 $0.00053 $0.00746
Sonnet 5 $0.00021 $0.00299
Haiku 4.5 $0.00011 $0.00149

Measured 9d ago against content hash 6a10369a670a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pr-feedback 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 9d 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/feature/skills/pr-feedback/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR feedback — the reviewer's comments are work items

A comment on the PR is a work item exactly like the user's chat prompt. This skill owns both halves: collect before you implement, answer after you push. It never decides what the code should do — it makes sure no item is lost.

Two modes — say which one you are in

Invoked as /feature:pr-feedback collect or /feature:pr-feedback answer; with no argument, collect. The modes are separated because they belong to opposite ends of a pass, and running the wrong one is a real failure: answer before the push cites no commit, and a second collect after the work re-opens items you just handled.

Mode When What it does
collect before any code is written — workspace Phase 2, or ship step 0 standalone list unaddressed items, decide per item, hand the list back
answer after the push — ship step 4b one reply per item picked up, each citing the fixing commit

All plumbing is one script; never hand-roll it with gh api:

SC="${CLAUDE_PLUGIN_ROOT}/scripts/pr_feedback.py"

Behaviour is driven by the pr_feedback block of the config (enabled, reply, resolve, include_outdated, include_bots, marker); with no config at all the shipped defaults apply, so this works outside a workspace too.

collect — before implementing

python3 "$SC" list --cwd "$WT" [--pr <url>]

--pr when you know it (a workspace's .feature.json records it); omit it and the current branch's own PR is used. pr_feedback.enabled: false, no PR yet, or nothing unaddressed ⇒ one line of output and stop here, silently. A gh/network failure (exit 2) is one line in the report, never a blocker.

A thread is unaddressed when it is unresolved and its last comment isn't yours. Two traps the script already handles — don't reintroduce them by hand:

  • gh posts as the human's own account, so the author tells you nothing; the marker in your own replies is the only discriminator.
  • isOutdated does not mean handled — a comment goes outdated the moment you push a fix touching that file, so outdated threads are usually the ones just worked on. The digest carries the diff hunk for exactly that reason.

Read the full file on GitHub · 120 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. 9d ago First seen · 120 lines · 105 tokens per session scan A 6a10369a670a

Subscribe to this mod's changes

pr-feedback is a skill published in the GitHub repository fivol/claude-make-better (5 stars, last pushed 28d ago), licensed MIT. It adds 105 tokens to every session and 1,493 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens

write-pr

Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.

tldraw/tldraw · 53 tokens