xray

xray is a command for coding agents from fcakyon/phd-skills. It costs 32 tokens per session (674 once invoked), scanned A, original, MIT.

A five-part audit of a research paper against its code, experiment outputs, and citations. It checks numbers, terminology, paper-to-code consistency, references, and evaluation claims.

In plain words
What is it for?
Use it to inspect LaTeX papers, BibTeX files, result files, and source code, then report findings with high, medium, or low severity.
Why use it?
It helps find claims that cannot be traced to evidence, incorrect results, inconsistent terms, citation errors, and weaknesses in the reported evaluation.

Command

Part of the phd-skills plugin — 12 skills, 6 commands, 2 agents, 4 hooks shipped together

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.

agentmods
npx agentmods add commands/fcakyon/phd-skills/xray
Clone the repo
git clone --depth 1 https://github.com/fcakyon/phd-skills

Or install phd-skills, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 2 agents, 4 hooks.

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 xray

README.md
[![agentmods](https://agentmods.dev/badge/commands/fcakyon/phd-skills/xray.svg)](https://agentmods.dev/commands/fcakyon/phd-skills/xray)
Your own site
<a href="https://agentmods.dev/commands/fcakyon/phd-skills/xray"><img src="https://agentmods.dev/badge/commands/fcakyon/phd-skills/xray.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 674 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.00674
Opus 5 $0.00016 $0.00337
Sonnet 5 $0.00006 $0.00135
Haiku 4.5 $0.00003 $0.00067

Measured 4d ago against content hash 34e89961f991, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xray 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 4d 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.

plugin/commands/xray.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Paper X-Ray Audit

You are performing a multi-dimensional audit of a research paper against its codebase and experimental results.

Step 1: Discover Paper Files

Find all .tex files in the project:

  • Use Glob to find **/*.tex files
  • Identify the main .tex file (usually imports other sections)
  • Find .bib files for citation checking
  • Find result files (JSON, CSV, logs) for numerical verification

Step 2: Launch Parallel Audits

Spawn 5 sub-agents in parallel, each handling one audit dimension. Each agent should return a structured list of findings rated HIGH/MEDIUM/LOW.

Agent 1: Numerical Accuracy

Task: Extract every number from the .tex files (dataset sizes, metric values, percentages, counts). For each number, trace it to its source in the codebase — a result file, code output, config, or tracking system. Report any number that doesn't match its source or cannot be traced.

Agent 2: Terminology Consistency

Task: Extract all technical terms defined in the methods section. Search for each term across ALL sections of the paper. Flag inconsistent usage: same concept with different names, same name with different meanings, defined but unused terms, or used but undefined terms.

Agent 3: Code-Paper Alignment

Task: For each method or algorithm described in the paper, find the corresponding code implementation. Compare the paper's description with the actual code. Check that hyperparameters, architecture details, loss functions, and training procedures match between paper and code.

Agent 4: Citation Accuracy

Task: Read the .bib file. For each entry, verify author names, venue, and year against web search or DBLP. For cited claims in the .tex files that include specific numbers, check whether those numbers appear in the cited paper. Flag unverified metadata and unsupported cited claims.

Agent 5: Evaluation Integrity

Task: Review the evaluation code and result files. Check for: data leakage between train/val/test splits, off-by-one errors in metric computation, wrong aggregation methods (micro vs macro), mismatched ground-truth and prediction alignment, zero-division edge cases, and results that don't reproduce from the evaluation scripts.

Read the full file on GitHub · 64 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. 4d ago First seen · 64 lines · 32 tokens per session scan A 34e89961f991

Subscribe to this mod's changes

xray is a command published in the GitHub repository fcakyon/phd-skills (382 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 674 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.