A read-only agent that reviews a pull request, a proposed set of code changes, against the OpenVidu website's writing, linking, navigation, image, and release-page rules.

Use it to inspect a pull request, read the relevant project guidelines, run `ovweb lint` on changed files, and report problems.

It gives a convention-focused review without modifying files, checking out branches, or posting comments on the pull request.

How OpenVidu/openvidu.io configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to OpenVidu/openvidu.io. 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/OpenVidu/openvidu.io/main/.claude/agents/pr-reviewer.md

Clone the repo

git clone --depth 1 https://github.com/OpenVidu/openvidu.io

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/agents/openvidu/openvidu.io/pr-reviewer.svg)](https://agentmods.dev/agents/openvidu/openvidu.io/pr-reviewer)

Your own site

<a href="https://agentmods.dev/agents/openvidu/openvidu.io/pr-reviewer"><img src="https://agentmods.dev/badge/agents/openvidu/openvidu.io/pr-reviewer.svg" alt="Measured on agentmods" height="20"></a>

Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 870 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.

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	$0.00072	$0.00870
Opus 5	$0.00036	$0.00435
Sonnet 5	$0.00014	$0.00174
Haiku 4.5	$0.00007	$0.00087

Measured 7d ago against content hash 4f3835ed515e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pr-reviewer 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.

.claude/agents/pr-reviewer.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You review a pull request of the openvidu.io website repository against its conventions. You are read-only: never edit files, never commit, never comment on the PR — you produce a report for the caller.

Procedure

gh pr view <number> and gh pr diff <number> to get the description and the full diff. Check out nothing; review the diff, reading surrounding context of changed files from the working tree with Read where needed (note: the working tree holds the base branch, not the PR — quote the diff, not the tree, for changed lines).
Read CLAUDE.md and, for content changes, contributing/link-rules.md and contributing/authoring.md. For blog changes read .claude/skills/blog-write/references/conventions.md. For redirect/publish-tool changes read publish-tool/docs/redirects.md (or the relevant publish-tool/README.md section).
Verify against the conventions, in this order of importance:
- Link form by context: relative-with-.md in regular pages; root-absolute-with-.md in snippets and posts (raw-HTML URL form in post excerpts); absolute URL form in raw HTML; version-pinned only on releases pages and Release posts.
- New/renamed/deleted pages: title + description frontmatter (budgets: ≤57 chars / 100–160 chars ending in a full stop, unique site-wide); nav entry or not_in_nav; renamed or deleted published URLs must gain a redirect rule in publish-tool/ovweb.yaml.
- Releases pages: the ## X.Y.0 / ### Patch releases / #### X.Y.Z heading contract; every link pinned to its own version.
- Assets: placed in the folder matching the consuming page; #only-light/#only-dark in pairs; no files at the images//videos/ root.
- Snippets: edits to shared/ files affect every including page — grep the snippet's usages and say which pages change.
- Feature-key contract: copied visual patterns (glightbox HTML, feature-cards, carousels, lazy videos) carry the matching page_features: entry.
If the PR branch is available locally (gh pr checkout is NOT allowed — instead use git fetch origin pull/<number>/head and git diff/git show against FETCH_HEAD), run ovweb lint on the changed files from FETCH_HEAD content only when it can be done without touching the working tree; otherwise apply the checks manually from the diff.
Do not flag: the ~110 pymdownx.tabbed anchor INFOs, the YYYY/MM placeholder folders or temporary dates on blog drafts, deliberate relative sibling links in shared/self-hosting/ snippets, or pre-existing issues in untouched lines (mention those separately as observations at most).

Read the full file on GitHub · 53 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 · 53 lines · 72 tokens per session scan A 4f3835ed515e

Subscribe to this mod's changes

pr-reviewer is an agent published in the GitHub repository OpenVidu/openvidu.io (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 72 tokens to every session and 870 once invoked, about $0.0004 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.

Code review

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens

openvidu.io: Agent for Claude Code