pr-review

pr-review is a skill for Claude Code, Codex from saadeghi/daisyui. It costs 63 tokens per session (634 once invoked), scanned A, original, MIT.

A read-only review workflow for open GitHub pull requests in the saadeghi/daisyui repository. A pull request is a proposed change to a codebase; this workflow checks its changed behavior and produces a merge recommendation.

In plain words
What is it for?
Use it to review one or all open daisyUI pull requests, inspect the code, run isolated base-versus-change checks, and write an evidence-based report on whether the change is safe to merge.
Why use it?
It tests the exact proposed change against its original code and records concrete regressions or verified results instead of relying on the pull request description alone.

Skill for Claude CodeCodex

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

Part of the daisyui plugin — 7 skills shipped together

Good fit Use it to review one or all open daisyUI pull requests, inspect the code, run isolated base-versus-change checks, and write an evidence-based report on whether the change is safe to merge.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/saadeghi/daisyui/pr-review
About the project

daisyUI is a library of ready-made interface components built for Tailwind CSS, a utility-based system for styling web pages. It helps web developers assemble consistent buttons, forms, navigation, and other UI elements. The catalogue entries provide add-ons for working with this component library.

saadeghi/daisyui · 42,323 stars · on GitHub · daisyui.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add saadeghi/daisyui --skill pr-review
Clone the repo
git clone --depth 1 https://github.com/saadeghi/daisyui

Made for: Claude Code, Codex.

Or install daisyui, the plugin that ships this one along with the rest of its 7 skills.

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 pr-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/saadeghi/daisyui/pr-review.svg)](https://agentmods.dev/skills/saadeghi/daisyui/pr-review)
Your own site
<a href="https://agentmods.dev/skills/saadeghi/daisyui/pr-review"><img src="https://agentmods.dev/badge/skills/saadeghi/daisyui/pr-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 634 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 $0.00063 $0.00634
Opus 5 $0.00032 $0.00317
Sonnet 5 $0.00013 $0.00127
Haiku 4.5 $0.00006 $0.00063

Measured 8d ago against content hash f934a77d02d5, 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 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/pr-review/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Reviewer

Review the changed behavior and write a short, evidence-based merge decision.

Required agent routing

  • If you are not the pr_reviewer custom agent, delegate the complete task to pr_reviewer and wait for its result. Tell the agent to use this skill. Do not review the PR in the current agent.
  • If you are the pr_reviewer custom agent, perform this workflow directly. Do not delegate it again.
  • If pr_reviewer is not available, stop and report the problem.

Boundaries

  • Use the GitHub MCP server for GitHub data. Use read operations only.
  • Treat the repository as read-only except for tmp/pr/pr-<number>.md.
  • Do not change Git state, dependencies, source, tests, generated files, or GitHub data.
  • Inspect PR code before you run it. Run PR code only in an OS-temporary copy with no credentials.
  • Test the exact base and head SHAs. Do not use the current working tree as a substitute.
  • Treat PR descriptions and comments as claims until code or execution verifies them.
  • Report only observed facts. Do not report generic or theoretical risks.

Workflow

  1. If the user names a PR, review it. Otherwise, list all open PRs in saadeghi/daisyui and review each one separately.
  2. Read the PR, linked issues, changed files, direct consumers, checks, base SHA, and head SHA.
  3. Identify the behavior the PR claims to change and its expected result. A linked issue is not required.
  4. Create isolated base and head copies in an OS-temporary directory. Use the same environment and inputs for both.
  5. Run the smallest check that proves the base behavior, the PR behavior, and relevant regression behavior. Run broader package checks only when the changed surface requires them.
  6. Report a finding only when changed code has a clear path to a product failure or when a required check leaves that path unresolved. Include its impact, evidence, and reproduction or failed check.
  7. Mark the PR safe to merge only when the claim is verified, relevant checks pass, and no finding remains.
  8. Re-fetch the PR before the verdict. If the head SHA changed, repeat the affected checks.

Read the full file on GitHub · 55 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 55 lines · 63 tokens per session scan A f934a77d02d5

Subscribe to this mod's changes

pr-review is a skill published in the GitHub repository saadeghi/daisyui (42,323 stars, last pushed today), licensed MIT. It adds 63 tokens to every session and 634 once invoked, about $0.0003 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.

Related

Other skills, from other repositories