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.
npx agentmods add skills/ivy00johns/skill-madness/git-pr-feedbacknpx skills add ivy00johns/Skill-Madness --skill git-pr-feedbackgit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWrote 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.
[](https://agentmods.dev/skills/ivy00johns/skill-madness/git-pr-feedback)<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/git-pr-feedback"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/git-pr-feedback.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00122 | $0.01662 |
| Opus 5 | $0.00061 | $0.00831 |
| Sonnet 5 | $0.00024 | $0.00332 |
| Haiku 4.5 | $0.00012 | $0.00166 |
Grade A, and why
git-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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Feedback Handler
Fetch review comments on a GitHub PR, triage them, fix what's clear, ask about what's ambiguous, and reply to each comment on GitHub with what was done.
Workflow
1. Identify the PR
Determine the PR number from context:
# Current branch's PR
gh pr view --json number -q .number
# Or from a URL the user provided
# Or from a specific PR number they mentioned
2. Fetch All Comments
Pull both review comments (inline on code) and issue-level comments:
# Inline review comments (from Copilot and reviewers)
gh api --paginate repos/{owner}/{repo}/pulls/{pr}/comments
# General PR comments (not on specific lines)
gh api --paginate repos/{owner}/{repo}/issues/{pr}/comments
# Review summaries
gh api --paginate repos/{owner}/{repo}/pulls/{pr}/reviews
Use --paginate to ensure all comments are returned — the default page size
is 30, which can silently miss comments on large PRs.
Parse each comment to extract:
- who:
user.login— distinguishCopilot,copilot-pull-request-reviewer[bot], and human reviewers - where:
pathandline— the file and line the comment targets - what:
body— the feedback text - id:
id— needed for replying - replied: to detect already-handled comments, scan all comments for
replies where
in_reply_to_id == <top_level_id>and the reply author is the PR author.
3. Triage Each Comment
Classify every comment into one of these categories:
| Category | Action | Example |
|---|---|---|
| Bug | Fix immediately | "This glob won't match broken symlinks" |
| Improvement | Fix if straightforward, ask if complex | "Exit code should be non-zero for errors" |
| Doc issue | Fix immediately | "The doc says X but the code does Y" |
| Style/nit | Fix if trivial, skip if subjective | "Consider renaming this variable" |
| Noise/false positive | Dismiss with explanation | "This is intentional because..." |
| Ambiguous/tricky | Present to user with options | "This could be fixed multiple ways..." |
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.
- 6d ago First seen · 196 lines · 122 tokens per session scan A 1843767e654e
git-pr-feedback is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed 26d ago), licensed MIT. It adds 122 tokens to every session and 1,662 once invoked, about $0.0006 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…