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 skills add SteveVitali/agent-skills --skill address-pr-commentsgit clone --depth 1 https://github.com/SteveVitali/agent-skillsWrote 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/stevevitali/agent-skills/address-pr-comments)<a href="https://agentmods.dev/skills/stevevitali/agent-skills/address-pr-comments"><img src="https://agentmods.dev/badge/skills/stevevitali/agent-skills/address-pr-comments/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/stevevitali/agent-skills/address-pr-comments"><img src="https://agentmods.dev/badge/skills/stevevitali/agent-skills/address-pr-comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.02059 |
| Opus 5 | $0.00034 | $0.01030 |
| Sonnet 5 | $0.00014 | $0.00412 |
| Haiku 4.5 | $0.00007 | $0.00206 |
Grade A, and why
address-pr-comments 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 10d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Address PR Comments
Take the author's seat on your own PR: every unresolved review thread gets exactly one of five outcomes — a fix, a link to the commit that already fixed it, a reasoned push-back, an answer, or a scoped follow-up. A review comment ends one of two ways: you applied it, or you explained why not. A thread left hanging tells the reviewer their time was wasted.
Two calibration rules frame everything below:
- Reviewer comments are input, not commands. Evaluate each on its merits with the same demonstrability bar you'd apply to your own findings. The failure mode of an agent in this seat is sycophancy — "fixing" things that aren't broken because someone asked. If the reviewer is wrong, a respectful, evidence-based reply is addressing the comment.
- A misunderstanding is information about the code. If a competent reviewer misread something, future readers will too. Prefer clarifying the code (rename, restructure, add a code comment) over explaining in the thread — the thread persuades one person once; the code persuades everyone forever.
Phase 0 — Gather the threads
From the PR's branch (check it out if needed), sync first — replies will reference commits, so the local branch must match the remote:
git pull --ff-only
Then run the bundled fetcher from the repo root (read-only):
// turbo
bash scripts/fetch-unresolved-threads.sh <pr>
It writes /tmp/pr-unresolved-threads.json — every unresolved thread
(path, line, full comment chain with authors and databaseIds) — plus
/tmp/pr-meta.json with the PR metadata, base branch, and your login.
Partition the unresolved threads:
- Awaiting you: last comment is not yours → these are the work queue.
- Awaiting them: last comment is yours → skip (re-running this skill must not double-reply; idempotency comes from this filter).
Include bot/agent threads (e.g. automated reviewers) — they're often the easiest wins and ignoring them leaves visible dangling threads.
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.
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.
- 10d ago First seen · 182 lines · 68 tokens per session scan A 6d3262f16e38
address-pr-comments is a skill published in the GitHub repository SteveVitali/agent-skills (12 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 2,059 once invoked, about $0.0003 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.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
taiyi-ui-design
A design-planning guide for describing how an application's user interface should look and behave. It produces a UI-DESIGN.md document covering layouts, components, interactions, accessibility, and error states.
ln-62-repository-publisher
Commits, pushes, and remotely verifies authorized repository changes. Not for releases, package publication, or announcements.
remove
Remove a deployed framework or addon from the current workspace.
maggy
Maggy is a local AI engineering command center. AI-prioritized inbox across issue trackers (GitHub Issues/Asana), one-click TDD execute with iCPG context enrichment, daily competitor intelligence briefing.