paper-implementation-checker

paper-implementation-checker is an agent for Claude Code from Rezenders/scientific_writing_agent. It costs 75 tokens per session (599 once invoked), scanned A, original, Apache-2.0.

A review agent that checks whether a technical statement in a LaTeX research paper matches the software implementation behind it. LaTeX is a system commonly used to write scientific papers.

In plain words
What is it for?
Use it when a paper describes software and you need to check claims against schemas, source code, examples, interface methods or design documents.
Why use it?
It helps find differences between what a paper says and what the code, data structures or interfaces actually do. It reports whether a claim is consistent, differs from the implementation or cannot be verified.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

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 agents/rezenders/scientific_writing_agent/paper-implementation-checker
Clone the repo
git clone --depth 1 https://github.com/Rezenders/scientific_writing_agent

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 paper-implementation-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/rezenders/scientific_writing_agent/paper-implementation-checker.svg)](https://agentmods.dev/agents/rezenders/scientific_writing_agent/paper-implementation-checker)
Your own site
<a href="https://agentmods.dev/agents/rezenders/scientific_writing_agent/paper-implementation-checker"><img src="https://agentmods.dev/badge/agents/rezenders/scientific_writing_agent/paper-implementation-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 599 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 5.1 $0.00075 $0.00599
Opus 5 $0.00037 $0.00300
Sonnet 5 $0.00015 $0.00120
Haiku 4.5 $0.00007 $0.00060

Measured 6d ago against content hash 7445b81f7c26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

paper-implementation-checker 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 6d 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/agents/paper-implementation-checker.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a consistency checker between manuscript claims and software implementation.

Task

Given a technical claim from the manuscript (or a section to verify), check it against the implementation and report CONSISTENT / DIVERGES / CANNOT_VERIFY.

Procedure

  1. Identify the types, behaviors, interfaces, or methods mentioned in the claim.
  2. Search the implementation for matching definitions:
    • <PATH_TO_SCHEMAS_OR_TYPES>/ — type names, data structures, schemas
    • <PATH_TO_EXAMPLES>/ — running examples referenced in the paper
  3. Check runtime behavior and method names in:
    • <PATH_TO_MAIN_INTERFACE> — interface methods, runtime behavior
  4. Check design intent in:
    • <PATH_TO_DESIGN_DOCS> — architecture / schema design intent

Implementation Reference Table

What to verify Where to look
Type names, data structures, schemas <path>
Running examples referenced in the paper <path>
Runtime behavior, interface method names <path>
Design intent / architecture documentation <path>

Output Format

For each claim checked:

CLAIM: <quoted or paraphrased claim>
STATUS: CONSISTENT | DIVERGES | CANNOT_VERIFY
EVIDENCE: <file:line or construct name>
NOTES: <any nuance — e.g. paper uses older terminology, implementation renamed X to Y>

Read the full file on GitHub · 69 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. 6d ago First seen · 69 lines · 75 tokens per session scan A 7445b81f7c26

Subscribe to this mod's changes

paper-implementation-checker is an agent published in the GitHub repository Rezenders/scientific_writing_agent (11 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 599 once invoked, about $0.0004 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 agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

Geoprocessing Specialist

ArcPy and Python toolbox expert who automates spatial workflows — builds .pyt toolboxes, Model Builder processes, batch geoprocessing automation, and custom analysis scripts for ArcGIS Pro.

SHAdd0WTAka/Zen-Ai-Pentest · 45 tokens

research-scout

Scans the NeqSim codebase to discover scientific paper opportunities that will drive code improvement. Every paper must improve NeqSim — adding tests, validating models against data, hardening algorithms, or implementing new capabilities. Produces ranked, actionable topics that feed into the planner agent.

equinor/neqsim · 61 tokens

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens

mathodology-problem-analyst

Use for contest problem decomposition, scoring criteria, constraints, variables, assumptions, and deliverable mapping.

sweetcornna/mathodology · 29 tokens

astronomical-instrumentation-scientist

Reasons from system-level error budgets, the diffraction limit and Strehl ratio, detector figures of merit, and resolving power through Zemax/Code V tolerancing, ETC radiometry, AO modeling, and on-sky standard-star commissioning while treating flexure drift, IR persistence, ghosts, and quasi-static speckles as…

K-Dense-AI/scientific-agents · 78 tokens