Borrowing it
Nothing to install: this file belongs to theimaginaryfoundation/what-iff. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/theimaginaryfoundation/what-iff/main/.agents/skills/address-pr-feedback/SKILL.mdgit clone --depth 1 https://github.com/theimaginaryfoundation/what-iffWrote 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/theimaginaryfoundation/what-iff/address-pr-feedback)<a href="https://agentmods.dev/skills/theimaginaryfoundation/what-iff/address-pr-feedback"><img src="https://agentmods.dev/badge/skills/theimaginaryfoundation/what-iff/address-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.
<a href="https://agentmods.dev/skills/theimaginaryfoundation/what-iff/address-pr-feedback"><img src="https://agentmods.dev/badge/skills/theimaginaryfoundation/what-iff/address-pr-feedback.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01249 |
| Opus 5 | $0.00061 | $0.00624 |
| Sonnet 5 | $0.00024 | $0.00250 |
| Haiku 4.5 | $0.00012 | $0.00125 |
Grade A, and why
address-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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Address PR Feedback
Produce a clean, prioritized triage plan of a PR's review feedback, staged in a dedicated worktree so later fixes stay isolated. Stop before editing code — the deliverable is an accurate map of what reviewers actually asked for.
The hard part is signal vs. noise: reviewer asks are spread across three
GitHub comment surfaces and buried in automated chatter (bot approvals, CI
tables, pasted config). A good plan surfaces every genuine ask exactly once with
its file:line anchor, and drops noise without discarding anything a human
wrote.
Workflow
1. Resolve + collect with the bundled collector. It resolves the PR, then returns PR meta, verdict, and all three comment surfaces (reviews, inline line comments, conversation) as one JSON object — pre-filtered to drop pure noise (regression tables, bare bot approvals) while keeping structured bot findings and every human comment full.
scripts/collect.sh [<N>] # no arg -> the user's most recent authored PR
Confirm the resolved PR number + title with the user before continuing. If
gh auth status fails, stop and have them run gh auth login.
2. Create an isolated worktree off the PR branch (.pr.headRefName from the
JSON) so the work doesn't disturb the user's checkout. Report the path; don't
cd their shell.
git fetch origin <headRefName>
git worktree add ../<repo>-pr<N>-feedback <headRefName>
If the branch is already checked out elsewhere, git refuses — report that rather than forcing it.
3. Triage the collected JSON. Route every item by author first, then content — this ordering is what keeps a casual human aside from being mistaken for noise. The collector already dropped pure noise; the judgment below is what it can't do.
Human-authored comment → it may ONLY land in 🔧 Actionable, 🧹 Nitpick, or ❓ Needs decision. A human comment is never noise or "informational", no matter how casual, hedged, optional, or rambling ("you could delete this if you want", "might be nice to…", a pasted config/persona). The ✅ bucket and any "noise" label are off-limits for human content. Sort it:
- Clear, concrete request → 🔧 Actionable (or 🧹 Nitpick if trivial).
- Ambiguous, optional, hedged, or half-formed → ❓ Needs decision. Capture the underlying ask and let the user call it. (e.g. "you could delete deploy.sh if you want" is a decision, not noise.)
- The only human content with no action is an explicit approval carrying no ask ("LGTM") — record it as the verdict, not an item.
What ships with it
2 files 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.
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 · 107 lines · 122 tokens per session scan A b891256635b6
address-pr-feedback is a skill published in the GitHub repository theimaginaryfoundation/what-iff (15 stars, last pushed yesterday), licensed Apache-2.0. It adds 122 tokens to every session and 1,249 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 2026-09-09.
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.
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.
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…
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…
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…
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.