pr-first-review

pr-first-review is a skill for Claude Code, Codex from mergisi/awesome-hermes-agent. It costs 33 tokens per session (1,166 once invoked), scanned A, original, MIT.

A first review of a GitHub pull request, which is a proposed code change, before the main maintainer review. It reads the changes and checks security patterns, tests, coding conventions, scope, and breaking changes.

In plain words
What is it for?
Use it on new pull requests or new commits to review the diff and description, check for selected OWASP Top 10 security risks, compare changes with repository conventions, and report possible test or scope problems.
Why use it?
It catches common problems early so maintainers can focus on whether the change is correct and appropriate. It can flag issues such as unsafe database queries, cross-site scripting, missing access checks, and unrelated edits.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md.

Good fit Use it on new pull requests or new commits to review the diff and description, check for selected OWASP Top 10 security risks, compare changes with repository conventions, and report possible test or scope problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mergisi/awesome-hermes-agent/pr-first-review
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 mergisi/awesome-hermes-agent --skill pr-first-review
Clone the repo
git clone --depth 1 https://github.com/mergisi/awesome-hermes-agent

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 pr-first-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/mergisi/awesome-hermes-agent/pr-first-review/github.svg)](https://agentmods.dev/skills/mergisi/awesome-hermes-agent/pr-first-review)
Your own site
<a href="https://agentmods.dev/skills/mergisi/awesome-hermes-agent/pr-first-review"><img src="https://agentmods.dev/badge/skills/mergisi/awesome-hermes-agent/pr-first-review/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.

agentmods 80×15 button for pr-first-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/mergisi/awesome-hermes-agent/pr-first-review"><img src="https://agentmods.dev/badge/skills/mergisi/awesome-hermes-agent/pr-first-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,166 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.01166
Opus 5 $0.00016 $0.00583
Sonnet 5 $0.00007 $0.00233
Haiku 4.5 $0.00003 $0.00117

Measured 11d ago against content hash 156388d2bec6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pr-first-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 11d 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.

skills/pr-first-review/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR First Review

A first-pass code review for incoming pull requests. Catches the obvious things — failing tests, security anti-patterns, scope creep, breaking changes — and leaves comments before the maintainer opens the PR. The maintainer's review starts from "is this AI right?" instead of "what does this PR do?".

What this skill does

For every new PR (or new commit on an existing PR):

  1. Read the diff and the description — what files changed, what the author claims they did, whether tests were added.
  2. Run the OWASP Top 10 pattern check on the diff: SQL injection (string concatenation into queries, raw ORM calls), XSS (dangerouslySetInnerHTML, unescaped output), IDOR (resource access without auth checks), SSRF (server-side fetch from user-controlled URLs), broken auth (missing session validation), XXE, mass assignment.
  3. Style and convention check — does the change match the repo's established style (config file naming, error handling patterns, log format)? Is there a .eslintrc / .prettierrc / framework convention being violated?
  4. Scope check — does the PR do what its title/description claims, or did it sneak in unrelated changes? Flag any out-of-scope file in a separate comment.
  5. Breaking-change detection — function signatures changed? Public API field renamed? Migration script added? If yes and there's no CHANGELOG / version bump, flag it.
  6. Test coverage — did the PR change behavior without adding/updating a test? Comment with the specific behavior that should have a test.
  7. Block or flag — if a high-severity issue is found (RCE, exposed secrets, unauthenticated PII endpoint), request changes via the GitHub API. Otherwise, leave comments inline and let the human decide.

What this skill does NOT do

  • It does NOT replace a real static analyzer like Semgrep or CodeQL. Use those alongside for taint tracking and deep dataflow analysis.
  • It does NOT auto-merge or auto-approve PRs. Default behavior is comment-only; "request changes" requires explicit configuration.
  • It does NOT review architectural decisions or product fit — that's the human's call. It catches mechanical problems.
  • It does NOT review every line. The default config skips lockfiles, generated files (*.min.js, dist/), and snapshot tests.

Read the full file on GitHub · 84 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.

  1. 11d ago First seen · 84 lines · 33 tokens per session scan A 156388d2bec6

Subscribe to this mod's changes

pr-first-review is a skill published in the GitHub repository mergisi/awesome-hermes-agent (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 1,166 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 2026-08-31.

Related

Other skills, from other repositories

coding-standards

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

hashgraph-online/awesome-codex-plugins · 28 tokens

review-work

Quality gate: verify each acceptance criterion of a completed task/work unit, run quality checks, and create follow-up tasks for gaps. Use before merging or to audit delivered work. Invoked as /agiflow:review-work . Uses getworkunit, gettask, updatetask, createtask, createtaskcomment.

hashgraph-online/awesome-codex-plugins · 72 tokens

cross-model-review

A second-opinion code review that asks a different AI model to independently inspect a change, then compares both reviews. It focuses on logic, security, consistency, and omissions.

hashgraph-online/awesome-codex-plugins · 56 tokens

ontoly-software-graph

Use Ontoly Software Graph evidence, CLI reports, MCP, and official Ontoly Agent Skills before searching source files when reviewing architecture, dependencies, request flows, configuration, impact, or security-sensitive ownership.

hashgraph-online/awesome-codex-plugins · 47 tokens

codegraph

A local code-graph query tool for an existing project. It maps symbols and their relationships so you can search for definitions, callers, callees, affected files, and focused context.

hashgraph-online/awesome-codex-plugins · 55 tokens

gitnexus

A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.

hashgraph-online/awesome-codex-plugins · 58 tokens