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.
npx skills add NeelPrime/arbiterx --skill arbiterx-reviewgit clone --depth 1 https://github.com/NeelPrime/arbiterxWrote 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.
[](https://agentmods.dev/skills/neelprime/arbiterx/arbiterx-review)<a href="https://agentmods.dev/skills/neelprime/arbiterx/arbiterx-review"><img src="https://agentmods.dev/badge/skills/neelprime/arbiterx/arbiterx-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.
<a href="https://agentmods.dev/skills/neelprime/arbiterx/arbiterx-review"><img src="https://agentmods.dev/badge/skills/neelprime/arbiterx/arbiterx-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00017 | $0.00246 |
| Opus 5 | $0.00009 | $0.00123 |
| Sonnet 5 | $0.00003 | $0.00049 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
arbiterx-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 9d 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.
What it actually says
ArbiterX Review
Review the current diff (or specified files) against the 10 engineering rules.
Instructions
-
Look at the git diff or specified files
-
Check each one against:
- YAGNI: Is there anything built that wasn't asked for?
- Error handling: Are all I/O operations protected?
- Type safety: Are all functions typed?
- Resource cleanup: Are all resources properly closed?
- Magic numbers: Are there inline numeric literals?
- Dead code: Unused imports, commented code?
- Single responsibility: Functions over 30 lines?
- Fail fast: Late validation?
- Performance: O(n²) patterns, string concat in loops?
- Security: Hardcoded secrets, SQL injection, eval?
-
Output a table:
| File | Issue | ArbiterX | Severity | Fix |
|---|
- Give an overall score (0-100) and pass/fail (threshold: 70)
Be specific. Point to exact lines. Suggest the minimal fix.
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.
- 9d ago First seen · 32 lines · 17 tokens per session scan A 1243064fad79
arbiterx-review is a skill published in the GitHub repository NeelPrime/arbiterx (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 17 tokens to every session and 246 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 2026-08-31.
Other skills, from other repositories
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
verify-language
Language-specific verification for Python, TypeScript/JavaScript, and Go. Checks type safety, language idioms, and best practices. Use when asked to "verify language", "check types", or for language-specific checks.
verify-quality
Verify code quality including naming conventions, organization, documentation, and general best practices. Use when asked to "verify quality", "check code quality", or "review code organization".
quality
This skill should be used when the user asks about "code quality", "formatting", "linting", "lint rules", "code style", "error handling", "unsafe code", "documentation comments", "doc comments", "rustfmt", "prettier", "eslint", "clippy", or needs guidance on code quality enforcement and configuration.
pr-review
Use when conducting manual PR reviews - provides structured checklist covering security, performance, maintainability, and code quality dimensions with anti-sycophancy principles.
receiving-code-review
Use when receiving PR review feedback or code review comments. Enforces verification-first response to review feedback with anti-sycophancy classification and constructive disagreement protocol.