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/ryanb/dotfiles/pr-feedbacknpx skills add ryanb/dotfiles --skill pr-feedbackgit clone --depth 1 https://github.com/ryanb/dotfilesWhat 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 | $0.00030 | $0.03805 |
| Opus 5 | $0.00015 | $0.01903 |
| Sonnet 5 | $0.00006 | $0.00761 |
| Haiku 4.5 | $0.00003 | $0.00380 |
Grade A, and why
pr-feedback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pr-feedback — Triage and address unresolved PR review comments
The goal: look at every unresolved review comment on the PR for the current branch, evaluate each one independently, split them into ones that can simply be addressed (or skipped) and ones that need discussion, work through the discussion comments one at a time, and — only after all discussions are resolved and the user confirms — address each, one commit per comment (simple ones inline, involved ones via a sub-agent).
Unlike pending feedback, these comments come from other reviewers, so recommending to skip a comment (stale, already done, out of scope, or you disagree) is a legitimate outcome — but anything ambiguous, subjective, or a design call should go to discussion so the user decides, not be silently skipped.
Step 1: Find the PR for the current branch
pr_number=$(gh pr view --json number --jq .number)
pr_url=$(gh pr view --json url --jq .url)
repo=$(gh repo view --json nameWithOwner --jq .nameWithOwner)
base_branch=$(gh pr view --json baseRefName --jq .baseRefName)
me=$(gh api user --jq .login)
If gh pr view fails, stop and tell the user there is no open PR for the current branch.
Step 2: Fetch unresolved review comments
GitHub's REST API exposes review comments but not the isResolved flag — that lives on the review thread in GraphQL. Use GraphQL to pull threads with their resolution state and comments:
gh api graphql -f query='
query($owner:String!, $repo:String!, $number:Int!) {
repository(owner:$owner, name:$repo) {
pullRequest(number:$number) {
reviewThreads(first:100) {
nodes {
id
isResolved
isOutdated
path
line
comments(first:50) {
nodes {
author { login }
body
url
diffHunk
originalLine
path
}
}
}
}
}
}
}' -F owner="$(echo $repo | cut -d/ -f1)" \
-F repo="$(echo $repo | cut -d/ -f2)" \
-F number="$pr_number"
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.
- yesterday First seen · 255 lines · 30 tokens per session scan A 98551dc45aa7
pr-feedback is a skill published in the GitHub repository ryanb/dotfiles (2,399 stars, last pushed 12d ago), licensed MIT. It adds 30 tokens to every session and 3,805 once invoked, about $0.0002 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…