What is content-refinement-agent?

A paper-editing step from PaperOrchestra that simulates peer review, revises the draft, and keeps snapshots of each attempt. LaTeX is a document format commonly used for research papers.

Use it to review and revise a research paper, check claims against an experiment log and approved bibliography, and produce a final LaTeX file and PDF.

It helps find weaknesses, unsupported claims, formatting problems, and inconsistencies before submission. Saved snapshots make it possible to identify and retain the best accepted version.

content-refinement-agent — Skill by woodfishhhh/EZ_math

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 woodfishhhh/EZ_math_model --skill content-refinement-agent

Clone the repo

git clone --depth 1 https://github.com/woodfishhhh/EZ_math_model

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/woodfishhhh/ez_math_model/content-refinement-agent/github.svg)](https://agentmods.dev/skills/woodfishhhh/ez_math_model/content-refinement-agent)

Your own site

<a href="https://agentmods.dev/skills/woodfishhhh/ez_math_model/content-refinement-agent"><img src="https://agentmods.dev/badge/skills/woodfishhhh/ez_math_model/content-refinement-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/woodfishhhh/ez_math_model/content-refinement-agent"><img src="https://agentmods.dev/badge/skills/woodfishhhh/ez_math_model/content-refinement-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,060 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 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00104	$0.03060
Opus 5.5	$0.00042	$0.01224
Sonnet 5.5	$0.00021	$0.00612
Haiku 4.5	$0.00010	$0.00306

Measured 1mo ago against content hash 805b4779987a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

content-refinement-agent 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 1mo ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/apply_worklog.py, scripts/score_delta.py, scripts/score_trajectory.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to content-refinement-agent — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/ez-math-model/external/paper-orchestra/skills/content-refinement-agent/SKILL.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Content Refinement Agent (Step 5)

Faithful implementation of the Content Refinement Agent from PaperOrchestra (Song et al., 2026, arXiv:2604.05018, §4 Step 5, App. F.1 pp. 49–51).

Cost: ~5–7 LLM calls (App. B), typically ~3 refinement iterations, each consisting of one reviewer call and one revision call.

The paper highlights this step as one of the largest contributors to overall quality: refinement alone accounts for +19% (CVPR) and +22% (ICLR) absolute acceptance-rate improvement (Fig. 4). Get this step right.

Inputs

workspace/drafts/paper.tex — output of Step 4
workspace/inputs/conference_guidelines.md
workspace/inputs/experimental_log.md — used as ground truth for the hallucination check
workspace/citation_pool.json / workspace/refs.bib — the allowed bibliography

Outputs

workspace/refinement/iter1/, iter2/, iter3/ — per-iteration snapshots containing paper.tex, paper.pdf, review.json, score.json
workspace/refinement/worklog.json — append-only history of decisions
workspace/final/paper.tex and workspace/final/paper.pdf — copy of the best accepted snapshot

prev_score = score(paper.tex)                  # baseline from initial draft
snapshot iter0/

for iter in 1..ITER_CAP (default 3):
    1. simulate_review(paper.tex) → review.json
       (uses `references/reviewer-rubric.md` rubric)

    2. apply_revision(paper.tex, review.json) → new_paper.tex
       (uses verbatim Refinement Agent prompt at `references/prompt.md`)

    3. snapshot iter<N>/ with new_paper.tex, review.json
       latexmk -pdf new_paper.tex → iter<N>/paper.pdf

    4. score(new_paper.tex) → curr_score

    5. decide via score_delta.py:
       - if curr.overall > prev.overall:                       ACCEPT
       - elif curr.overall == prev.overall and net_subaxis ≥0: ACCEPT
       - else:                                                 REVERT

    6. apply_worklog.py to append the decision

    7. if REVERT or no actionable weaknesses or iter == ITER_CAP: HALT

    paper.tex ← new_paper.tex   (only on ACCEPT)
    prev_score ← curr_score

cp <best iter>/paper.tex → workspace/final/paper.tex

Read the full file on GitHub · 296 lines

Files

What ships with it

11 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 296 lines · 104 tokens per session scan A 805b4779987a

Subscribe to this mod's changes

content-refinement-agent is a skill published in the GitHub repository woodfishhhh/EZ_math_model (43 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 3,060 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to content-refinement-agent, differing in 0 lines, and is treated as a copy.

Claude Code Scientific Writing and docs agent-skills codex cumcm icm mathematical-modeling

mathmodel-skill

An end-to-end workflow for mathematical-modeling competitions, including CUMCM, MCM/ICM, and the Electrical Cup. It guides teams from choosing a problem through modeling, solving, checking, writing, rule compliance, and final review.

handsomeZR-netizen/mathmodel-skill · 127 tokens

math-modeling-solver

A Chinese-language guide for solving mathematical modeling competition problems. It covers China’s CUMCM and America’s MCM/ICM, where teams use mathematics and code to answer real-world problem statements.

Lupynow/math-modeling-skills · 186 tokens

math-modeling-paper

A Chinese-language guide for writing papers for mathematical modelling competitions, where teams use mathematics and data to study a real-world problem.

Lupynow/math-modeling-skills · 202 tokens

interpret-modeling-problems

A method for turning a mathematical modelling contest problem and its attachments into a checked plan for solving and documenting it.

zhoufz021/interpret-modeling-problems · 114 tokens

mcm-model-typeset

A set of writing and formatting rules for the model-building and solution section of a Chinese mathematical modelling paper. It defines section structure, equation explanations, constraints, and model summaries without changing the supplied numbers or formulas.

LiXiang106991/MathModelAgent · 65 tokens

math-modeling-finalizer

A finalization guide for mathematical-modeling projects after the main results are largely fixed.

mantou6666/Math-Modeling-Agent-Flow · 160 tokens

content-refinement-agent