oz-for-oss: Skill for Claude Code

.agents/skills/review-pr-local/SKILL.md

review-pr-local is a skill for Claude Code, Codex from warpdotdev/oz-for-oss. It costs 31 tokens per session (292 once invoked), scanned A, original, MIT.

Repository-specific rules for reviewing pull requests, which are proposed code changes. They add project guidance for wording, links, missing data, errors, and debugging information.

In plain words
What is it for?
Use it when reviewing changes in the oz-for-oss repository, especially code that displays user-facing text, optional data, links, or error messages.
Why use it?
It helps reviewers catch problems that generic review rules may miss, such as broken messages, empty links, inconsistent terms, or errors that reveal too much.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is warpdotdev/oz-for-oss's own configuration. It tells Claude Code and Codex how to work on oz-for-oss itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything oz-for-oss configures →

Reuse

Borrowing it

Nothing to install: this file belongs to warpdotdev/oz-for-oss. 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/warpdotdev/oz-for-oss/main/.agents/skills/review-pr-local/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/warpdotdev/oz-for-oss

Made for: Claude Code, Codex.

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.

agentmods badge for review-pr-local

README.md
[![agentmods](https://agentmods.dev/badge/skills/warpdotdev/oz-for-oss/review-pr-local.svg)](https://agentmods.dev/skills/warpdotdev/oz-for-oss/review-pr-local)
Your own site
<a href="https://agentmods.dev/skills/warpdotdev/oz-for-oss/review-pr-local"><img src="https://agentmods.dev/badge/skills/warpdotdev/oz-for-oss/review-pr-local.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 292 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.00292
Opus 5 $0.00015 $0.00146
Sonnet 5 $0.00006 $0.00058
Haiku 4.5 $0.00003 $0.00029

Measured 8d ago against content hash 6d173c7350f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

review-pr-local 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 8d 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.

.agents/skills/review-pr-local/SKILL.md · 28 lines

What it actually says

Repo-specific review guidance for oz-for-oss

This file is a companion to the core review-pr skill. It does not redefine the review output schema, severity labels, safety rules, or evidence rules. It only specializes the override categories the core skill marks as overridable.

User-facing strings

  • Flag interpolated text that would read unnaturally at runtime (e.g. wrong casing after a sentence fragment like "The triage concluded that {summary}").
  • Link text should be descriptive (e.g. "triage session on Warp"), not bare URLs or generic "click here" labels.
  • Verify that terminology is consistent across related messages in the same PR.

Graceful degradation

  • When code renders optional dynamic data (URLs, session links, metadata), flag cases where a missing value would produce empty or broken output. The fix is usually to omit the element entirely and show a short fallback message.
  • Prefer starting with generic, user-safe error messages over exposing internal details.

Debugging and observability

  • Do not suggest removing session links, workflow URLs, or other debugging context from error paths. These are valuable for post-incident investigation even when the operation failed.
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.

  1. 8d ago First seen · 28 lines · 31 tokens per session scan A 6d173c7350f9

Subscribe to this mod's changes

review-pr-local is a skill published in the GitHub repository warpdotdev/oz-for-oss (307 stars, last pushed 6d ago), licensed MIT. It adds 31 tokens to every session and 292 once invoked, about $0.0002 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.