Borrowing it
Nothing to install: this file belongs to rome-os/rome. 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/rome-os/rome/main/.claude/skills/respond-to-review/SKILL.mdgit clone --depth 1 https://github.com/rome-os/romeWrote 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/rome-os/rome/respond-to-review)<a href="https://agentmods.dev/skills/rome-os/rome/respond-to-review"><img src="https://agentmods.dev/badge/skills/rome-os/rome/respond-to-review/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/rome-os/rome/respond-to-review"><img src="https://agentmods.dev/badge/skills/rome-os/rome/respond-to-review.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 | $0.00048 | $0.00348 |
| Opus 5.5 | $0.00019 | $0.00139 |
| Sonnet 5.5 | $0.00010 | $0.00070 |
| Haiku 4.5 | $0.00005 | $0.00035 |
Grade A, and why
respond-to-review 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.
What it actually says
Respond to review feedback
The goal is to get the PR merged as the change it set out to be, with every reviewer concern settled. Two things defeat that: the PR grows with each review round and drifts from its scope, or findings stay open and the next round raises them again.
- Stay on scope. Fix real defects this PR introduced, each proven by a test that fails without the fix. A defect in prose, including a PR description that misstates the change, has no test: correct it directly and say so in the reply. An existing defect that makes this PR wrong or unsafe to merge — the change depends on it, or makes it reachable — gets its own PR on a branch off the base branch, and this PR's description names it in a Blocked by line. Open that PR from a new session when the environment allows, and take its number from that session's report; otherwise open it from this session. Everything else stays out of this PR; file a bug issue for a real defect unless one already exists.
- Leave nothing open. Every finding ends fixed here, fixed in a blocking PR, filed as an issue, or declined with a reason.
- Close the loop in one short reply. Say what changed, what did not, and why, so the reviewer can approve without asking again.
When the issue the PR closes looks wrong, ask the user. Never edit the issue.
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 Changed · -51 lines 6dbaf2957566
- 1mo ago Changed · -12 lines · -57 tokens per session f3b09ab46e6e
- 1mo ago First seen · 78 lines · 105 tokens per session scan A 8aedfd3494c6
respond-to-review is a skill published in the GitHub repository rome-os/rome (871 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 348 once invoked, about $0.0002 per session on Opus 5.5. 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
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
github
GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries. Use when: (1) checking PR status or CI, (2) creating/commenting on issues, (3) listing/filtering PRs or issues, (4) viewing run logs. NOT for: complex web UI interactions requiring manual browser flows (use browser tooling when available)…
hypotheses
Turns a research direction into testable hypotheses with predictions, competing explanations and the experiments that discriminate between them, including the design (controls, randomization, blocking), sample size or seed count, the pre-specified analysis, and the result that would falsify each hypothesis. Use when a…
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.
control-center-review
Review one captured Control Center build before runtime activation.
review-pr
Review GitHub pull requests. Use when user says "review PR", "review pull request", or "/review-pr".