clawrium: Skill for Claude Code

.claude/skills/itx-review-pr/SKILL.md

itx-review-pr is a skill for Claude Code from ric03uec/clawrium. It costs 12 tokens per session (1,799 once invoked), scanned A, original, Apache-2.0.

A workflow for requesting an automated review of a GitHub pull request. It gathers the pull request details and changes, then reports blocking issues or readiness to merge.

In plain words
What is it for?
Use it to review a specified pull request or the pull request for the current branch, using the project's configured review service when available.
Why use it?
It gives a pull request a repeatable review step and makes serious findings explicit before merging.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions AGENTS.md.

This is ric03uec/clawrium's own configuration. It tells Claude Code how to work on clawrium 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 clawrium configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ric03uec/clawrium. 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/ric03uec/clawrium/main/.claude/skills/itx-review-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ric03uec/clawrium

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.

agentmods badge for itx-review-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/ric03uec/clawrium/itx-review-pr/github.svg)](https://agentmods.dev/skills/ric03uec/clawrium/itx-review-pr)
Your own site
<a href="https://agentmods.dev/skills/ric03uec/clawrium/itx-review-pr"><img src="https://agentmods.dev/badge/skills/ric03uec/clawrium/itx-review-pr/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 itx-review-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/ric03uec/clawrium/itx-review-pr"><img src="https://agentmods.dev/badge/skills/ric03uec/clawrium/itx-review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,799 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 $0.00012 $0.01799
Opus 5 $0.00006 $0.00899
Sonnet 5 $0.00002 $0.00360
Haiku 4.5 $0.00001 $0.00180

Measured 2d ago against content hash 210f12719e4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

itx-review-pr 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 2d 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/skills/itx-review-pr/SKILL.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Review

Request a code review for a pull request.

Instructions

  1. Identify PR:

    • If PR number provided, use it
    • If not, find PR for current branch:
      gh pr view --json number,title,url
      
  2. Get PR Details:

    gh pr view <number> --json number,title,body,files,additions,deletions
    gh pr diff <number>
    
  3. Check Review Configuration:

    ITX_CONFIG="$(git rev-parse --show-toplevel)/.claude/itx-config.json"
    if [ -f "$ITX_CONFIG" ]; then
      REVIEW_ENABLED=$(jq -r '.mcp.review_enabled // false' "$ITX_CONFIG")
    else
      REVIEW_ENABLED="false"
    fi
    
  4. Execute Review:

If Automated Review Enabled

Attempt each transport in order. Tool identifiers differ by harness, so do not invoke a configured or example name unless it is available in the current harness. An unavailable, failed, or timed-out attempt falls through to the next step.

  1. ATX via MCP: Inspect the current tool list for an ATX request-review tool. If one is available, invoke it with Review PR #<number>. If MCP is unavailable, fails, or times out, continue to the CLI step.
  2. ATX via CLI: Check command -v atx and require atx server status to report Running: true. If both checks pass, run the stateless review command so the result does not depend on harness-specific hooks:
    atx review request \
      --prompt "Review PR #<number>, including its full diff and tests." \
      --format json --timeout 15m
    
    If the CLI is unavailable, stopped, fails, or times out, continue to manual review.
  3. Manual review: After both automated transports are exhausted, use the manual checklist below and state clearly which attempts were unavailable or failed.

Process Automated Review Results:

  • If rating <= 3/5 or blocking issues exist:
    • List issues to fix
    • Recommend specific changes
  • If rating > 3/5 and no blockers:
    • PR is ready for merge

Report:

## Automated Review Summary

**PR**: #<number> - <title>
**Rating**: <X>/5

### Blocking Issues
<table or "None">

### Warnings
<list or "None">

### Suggestions
<list or "None">

### Verdict
<READY FOR MERGE / NEEDS CHANGES>

Read the full file on GitHub · 259 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. 2d ago Changed · +19 lines 210f12719e4d
  2. 8d ago Changed · -1 lines · -1 tokens per session 4d6615660d3c
  3. 12d ago First seen · 241 lines · 13 tokens per session scan A 05b08da6ea72

Subscribe to this mod's changes

itx-review-pr is a skill published in the GitHub repository ric03uec/clawrium (51 stars, last pushed 3d ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,799 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 2026-08-30.

Related

Other skills, from other repositories

python

Use when the task is Python itself, in any framework or none: PEP 695 generics, mypy --strict typing, dataclass/Protocol/TypedDict/Enum choices, asyncio.TaskGroup, stdlib idioms, src/ layout + pyproject.toml with uv, ruff+mypy+pytest gate. NOT a FastAPI/ASGI service (that is fastapi), NOT a deep pytest suite (that is…

ericrisco/rsc-harness · 94 tokens

pir-action-tracker

Parses Post-Incident Review (PIR) pages in a Confluence space, fetches live status from referenced Jira tickets, updates action item tables with current status and due dates, marks completed PIRs with a visual closure panel, and surfaces any overdue actions for follow-up. Designed for Customer Success, Support, and…

Perseus-Computing-LLC/perseus · 78 tokens

code-review-python

Deep Python-specific code review covering type annotations, async pitfalls, mutable defaults, threading safety, and domain modeling. Applied in addition to the generic code-review skill when Python code is detected. Invoked when reviewing Python PRs, Py changes, or performing Python-specific quality checks.

soulcodex/agentic · 59 tokens

agentic-preflight

Use when shipping a branch — reviewing, documenting, linting, testing, and pushing work behind a quality gate. Also use when a push is blocked by the agentic-preflight pre-push hook or when the user says agentic-preflight:uninstall to remove this tool from the current project.

elanthus/agentic-preflight · 66 tokens

aget-release-critique

Adversarial review with the Critic perspective of the Release Delivery Triad (L818). Dual-mandate: spec coverage audit + deep bug finding.

aget-framework/template-advisor-aget · 0 tokens

karpathy-guidelines

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Zandereins/schliff · 46 tokens