Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wangke19/gemini-ai-helpersnpx agentmods add commands/wangke19/gemini-ai-helpers/coderabbit-adoption-reportWrote 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/commands/wangke19/gemini-ai-helpers/coderabbit-adoption-report)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/coderabbit-adoption-report"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/coderabbit-adoption-report/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/commands/wangke19/gemini-ai-helpers/coderabbit-adoption-report"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/coderabbit-adoption-report.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 | $0.00010 | $0.01870 |
| Opus 5 | $0.00005 | $0.00935 |
| Sonnet 5 | $0.00002 | $0.00374 |
| Haiku 4.5 | $0.00001 | $0.00187 |
Grade A, and why
coderabbit-adoption-report 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 9d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
teams:coderabbit-adoption-report
Synopsis
/teams:coderabbit-adoption-report
/teams:coderabbit-adoption-report --start-date 2026-02-01 --end-date 2026-02-28
Description
The teams:coderabbit-adoption-report command measures CodeRabbit Pro adoption across a curated list of ~160 OCP payload repositories by calculating what percentage of merged PRs received a Pro-tier CodeRabbit review (identified by "Plan: Pro" in the comment body).
The list of repos to scan is defined in extensions/teams/skills/coderabbit-adoption/allowed-repos.txt.
It uses a Python script that calls the GitHub search API via gh CLI. The script does one org-wide query for PRs with Pro reviews, then batched queries (20 repos per batch) for all merged PRs. Per-repo breakdowns are calculated in Python. Takes about a minute to complete with progress shown.
How CodeRabbit Pro Reviews Work
CodeRabbit was enabled across most OCP payload repos on 2026-03-09. Since many of these repos are open source, CodeRabbit may leave comments on any PR — but only Pro reviews (indicated by Plan: Pro in the CodeRabbit comment) provide the full-quality analysis we want.
CodeRabbit does not review bot PRs. PRs authored by bot accounts (e.g., dependabot[bot], github-actions[bot], openshift-monitoring-bot[bot]) are intentionally skipped by CodeRabbit. Bot PRs appearing in the "missed" list are expected and should not be counted against adoption.
The script uses "Plan: Pro" as a search term combined with commenter:coderabbitai[bot] to directly identify Pro-reviewed PRs, then compares against all merged PRs to find the gap.
The script filters to PRs created on or after the enablement date (2026-03-09) to avoid counting old long-lived PRs that merged after enablement but were never seen by CodeRabbit.
Arguments
--start-date YYYY-MM-DD(optional): Start of the date range for merged PRs. Defaults to 7 days ago.--end-date YYYY-MM-DD(optional): End of the date range for merged PRs. Defaults to today.
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.
- 9d ago First seen · 150 lines · 10 tokens per session scan A 21954b473cb9
coderabbit-adoption-report is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 10 tokens to every session and 1,870 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
audit-quick
Run a quick codebase orientation scan — Phases 0 and 1 only (architecture map + health assessment). Skips deep analysis (security, performance, code quality) and the roadmap. Good for onboarding onto a new project or a fast pre-review checkup. Run /audit --resume later to continue with the deep phases.
review
Perform a comprehensive code review with actionable feedback.
adversarial-review
Get a devil's advocate review that challenges your design decisions.
adr-review
Run the workflow in docs/playbooks/adr-review.md. You review only — never write or rewrite the ADR for me. Check problem framing, option fairness, trade-offs and consequences, reversibility, the revisit trigger, and weak reasoning. Give pointed questions and concrete suggestions; I write the words. If it supersedes an…
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.