github-pr-feedback

github-pr-feedback is a skill for Claude Code, Codex from mfmezger/ai_agent_dotfiles. It costs 88 tokens per session (1,710 once invoked), scanned A, original, MIT.

A guide for sorting GitHub pull-request feedback into comments that need code changes and comments that can be declined, deferred, or answered. GitHub is a service where teams host code and review proposed changes.

In plain words
What is it for?
Use it to triage reviewer comments, automated review output, or pasted suggestions before deciding what to change in a pull request.
Why use it?
It helps distinguish concrete bugs or unclear assumptions from speculative requests and unnecessary refactoring. The result is a concise table that supports a clear response to each comment.

Skill for Claude CodeCodex

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 skills/mfmezger/ai_agent_dotfiles/github-pr-feedback
Any agent
npx skills add mfmezger/ai_agent_dotfiles --skill github-pr-feedback
Clone the repo
git clone --depth 1 https://github.com/mfmezger/ai_agent_dotfiles

Made for: Claude Code, Codex.

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,710 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 $0.00088 $0.01710
Opus 5 $0.00044 $0.00855
Sonnet 5 $0.00018 $0.00342
Haiku 4.5 $0.00009 $0.00171

Measured 3d ago against content hash a2e60cca9fe8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

github-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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fetch_pr_feedback.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

shared/skills/github-pr-feedback/SKILL.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub PR Feedback Triage

Turn GitHub pull request feedback into a concise, defensible markdown triage report. The goal is to help the user decide which comments require code changes and which can be safely declined, deferred, or answered without changing code.

Review Lens

Always keep the karpathy-guidelines skill in mind when judging PR feedback. Bias toward simple, surgical fixes with clear success criteria:

  • Do not accept feedback that adds speculative abstractions, broad refactors, or configurability the PR does not need.
  • Do not reject feedback that identifies a concrete bug, unclear assumption, or missing verification just because the fix is inconvenient.
  • Prefer the smallest code or documentation change that resolves the reviewer concern.
  • Surface uncertainty directly in the reasoning instead of pretending the answer is more certain than the evidence supports.

Prerequisites

  • Use gh when feedback must be fetched from GitHub.
  • gh must be installed and authenticated for live PR access.
  • Run bundled Python scripts with uv run when available. Use uvx only for external Python command-line tools; this skill's local helper script should be run with uv run.
  • If the user pasted the feedback directly, do not fetch from GitHub unless they ask you to verify the current PR state.

Input Sources

Prefer the most direct available input:

  1. Pasted feedback in the conversation.
  2. A PR URL or PR number provided by the user.
  3. The PR associated with the current branch.

If no PR or feedback is available, ask the user for either a PR URL/number or the feedback text.

Fetching GitHub Feedback

Prefer the bundled fetch script because it collects the PR summary, top-level comments, reviews, inline review comments, review thread resolution state, file list, and checks in one repeatable command.

Run the bundled fetch script with uv run:

uv run scripts/fetch_pr_feedback.py <pr-url-or-number> --out /tmp/pr-feedback.json --summary

Read the full file on GitHub · 198 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 198 lines · 88 tokens per session scan A a2e60cca9fe8

Subscribe to this mod's changes

github-pr-feedback is a skill published in the GitHub repository mfmezger/ai_agent_dotfiles (5 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,710 once invoked, about $0.0004 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

embedded-dev

Use when developing firmware on ESP32/STM32/RP2040/nRF52, experiencing DMA overflow, SPI timeout, LCD blank display, frame corruption, GPIO conflicts, sensor reading errors, Wi-Fi disconnect, or needing driver configuration, hardware debugging, display/GUI setup, protocol implementation, serial monitoring. Use even if…

lhbsaa/embedded-dev-skill · 93 tokens

embedded-dev

Guide for embedded systems development on ESP32, STM32, RP2040, nRF52 chips. Use this skill whenever the user mentions embedded systems, firmware development, MCU programming, hardware drivers, sensors, LCD displays, IMU devices, SPI/I2C/UART interfaces, compilation, debugging, remote monitoring, Wi-Fi/BLE/MQTT…

lhbsaa/embedded-dev-skill · 131 tokens

embedded-gui-feedback

Use for LCD/GUI projects after verification passes - captures display via camera, analyzes layout/font/color, detects display issues.

lhbsaa/embedded-dev-skill · 28 tokens

embedded-verification

Use after implementation complete - runs build-flash-monitor loop, verifies runtime behavior, no completion claims without fresh evidence.

lhbsaa/embedded-dev-skill · 26 tokens

embedded-brainstorming

Use before any embedded development - explores hardware requirements, confirms configuration, validates feasibility, saves design spec.

lhbsaa/embedded-dev-skill · 25 tokens

embedded-driver-design

Use when hardware configuration confirmed - creates detailed implementation plan with bite-sized tasks, exact file paths, complete code steps.

lhbsaa/embedded-dev-skill · 26 tokens