What is pr-review-gate?

A procedure for checking that all review conversations on a Rosetta pull request are closed before calling it mergeable. A pull request is a proposed code change, and review threads are conversations attached to that change.

Use it when a pull request becomes ready, after pushing fixes, or when bot comments need triaging and resolution.

Green automated checks and an approving review status can still leave an open bot comment that blocks merging. This gate catches that separate requirement.

How tikoci/rosetta configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tikoci/rosetta. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tikoci/rosetta/main/.github/skills/pr-review-gate/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/tikoci/rosetta

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tikoci/rosetta/pr-review-gate.svg)](https://agentmods.dev/skills/tikoci/rosetta/pr-review-gate)

Your own site

<a href="https://agentmods.dev/skills/tikoci/rosetta/pr-review-gate"><img src="https://agentmods.dev/badge/skills/tikoci/rosetta/pr-review-gate.svg" alt="Measured on agentmods" height="20"></a>

Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,321 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00099	$0.01321
Opus 5	$0.00049	$0.00660
Sonnet 5	$0.00020	$0.00264
Haiku 4.5	$0.00010	$0.00132

Measured 7d ago against content hash 3b87764f613e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pr-review-gate 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 7d 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.

.github/skills/pr-review-gate/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review Gate

Rosetta's branch protection on main requires all conversation threads resolved, enforced independently of status checks. CodeRabbit and Copilot both submit COMMENTED reviews (never CHANGES_REQUESTED), so reviewDecision stays clean and checks show green while the PR is still mergeStateStatus: BLOCKED by an open bot thread. Full rationale: .github/instructions/pr-review-bots.instructions.md — this skill is the runnable procedure; read that file for the "why."

When to use

A PR just went Ready for Review, or you pushed a fix commit, and you're about to tell the user the PR is done/mergeable.
gh pr merge refuses despite green checks.
The user asks to address, triage, or close out review comments.

When NOT to use

Draft PRs — bots don't review drafts.
As a substitute for requesting a fresh bot pass. Re-review costs money (Copilot) or burns a rate-limited slot (CodeRabbit: 1-3/hour) — only request one (@coderabbitai review PR comment, or re-request the Copilot reviewer) for fixes big/ambiguous enough to warrant a second look. A one-line string fix doesn't need it; resolve the thread and move on.

Procedure

Resolve the PR and repo.

gh pr view --json number,url,headRefName  # or: gh pr view <N> if given
gh repo view --json owner,name --jq '.owner.login + "/" + .name'

Read the real gate, not reviewDecision.
```
gh pr view <N> --json mergeStateStatus,reviewDecision,statusCheckRollup
```
mergeStateStatus: BLOCKED with green statusCheckRollup and clean reviewDecision means unresolved threads — proceed to step 3. CLEAN means you're done; skip to step 6.

List unresolved threads (GraphQL — the flat comment list hides resolution state).

gh api graphql -f query='query{repository(owner:"OWNER",name:"REPO"){pullRequest(number:N){reviewThreads(first:100){nodes{id isResolved isOutdated path line}}}}}' \
  --jq '.data.repository.pullRequest.reviewThreads.nodes[]|select(.isResolved==false)|"\(.id)\t\(.path):\(.line)"'

Read the full file on GitHub · 114 lines

Changes

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.

7d ago First seen · 114 lines · 99 tokens per session scan A 3b87764f613e

Subscribe to this mod's changes

pr-review-gate is a skill published in the GitHub repository tikoci/rosetta (44 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 1,321 once invoked, about $0.0005 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.

Claude Code Code review Git and workflow ai bun copilot mcp mcp-server

gentle-ai-collab-perfect

Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…

Gentleman-Programming/gentle-ai · 106 tokens

branch-pr

Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.

Gentleman-Programming/gentle-ai · 26 tokens

work-unit-commits

Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.

Gentleman-Programming/gentle-ai · 33 tokens

chained-pr

Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.

Gentleman-Programming/gentle-ai · 32 tokens

github-review-pr

Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Do NOT use for…

feiskyer/claude-code-settings · 90 tokens

memorix-git-memory

Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.

AVIDS2/memorix · 31 tokens

rosetta: Skill for Claude Code