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 NitorCreations/nitor-agent-skills --skill pr-review-responsegit clone --depth 1 https://github.com/NitorCreations/nitor-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/nitorcreations/nitor-agent-skills/pr-review-response)<a href="https://agentmods.dev/skills/nitorcreations/nitor-agent-skills/pr-review-response"><img src="https://agentmods.dev/badge/skills/nitorcreations/nitor-agent-skills/pr-review-response/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/nitorcreations/nitor-agent-skills/pr-review-response"><img src="https://agentmods.dev/badge/skills/nitorcreations/nitor-agent-skills/pr-review-response.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 | $0.00119 | $0.05216 |
| Opus 5 | $0.00060 | $0.02608 |
| Sonnet 5 | $0.00024 | $0.01043 |
| Haiku 4.5 | $0.00012 | $0.00522 |
Grade A, and why
pr-review-response 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 11d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Responding to PR review comments
Work a review round to completion: every actionable comment ends as either a pushed fix or an explained decision, with a reply on every thread — and resolution left to whoever's actually waiting on it: the human reviewer, or the bot-only cleanup rule in Reply to each thread, then conditionally resolve. Reply text is for the reviewer, not the user — so it states what changed and why, and cites the commit.
This skill has two kinds of check-in, and neither is a rubber stamp. Divergent or reject decisions are pressure-tested with the user as they're reasoned through (Reason about each comment) — batched into as few AskUserQuestion prompts as possible rather than one interruption per thread — because a "won't fix" or a divergent fix lands on the reviewer's thread under the user's name and is awkward to retract once posted. Catching those objections early, before the diff exists, means the code you implement next never has to be unwound over a disagreement the user would have rejected. Everything else — the fixes, the actual diff, the reply/resolve/re-request plan — is implemented first, locally and uncommitted (no cost to doing it before anyone signs off; it's fully reversible), then handed to the user for a single go/no-go on the real artifact in Confirm before executing. That confirmation scales to what the diff actually looks like: small and expected gets a compact go/no-go, anything bigger or surprising gets walked through in more detail. Either way, nothing pushes, replies, resolves, or re-requests before it.
Shell state does not persist between commands. Each Bash call runs in a fresh shell — exported variables, VAR=… assignments, and captured values like a commit SHA are gone by the next call. So the OWNER/REPO/PR/SHA placeholders below are for readability only: once you've resolved a value, substitute the literal into every later command (e.g. write repos/acme/widgets/pulls/42/..., not repos/$OWNER/$REPO/pulls/$PR/...), or keep the work that needs a variable inside a single Bash call. Do not rely on one command's environment reaching the next.
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.
- 11d ago First seen · 227 lines · 119 tokens per session scan A f4c9464e9dd1
pr-review-response is a skill published in the GitHub repository NitorCreations/nitor-agent-skills (2 stars, last pushed 29d ago), licensed MIT. It adds 119 tokens to every session and 5,216 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…