content-refinement-agent

content-refinement-agent is a skill for Claude Code, Codex from leonardodalinky/SciDER. It costs 104 tokens per session (2,518 once invoked), scanned A, original, Apache-2.0.

A later PaperOrchestra pipeline step that reviews and revises a research-paper draft through several controlled iterations. It saves each draft, review, score, and the best accepted final version.

In plain words
What is it for?
Use it to simulate peer review, revise paper.tex, check claims against experimental data and citations, preserve snapshots, and select the strongest accepted draft.
Why use it?
It provides a recorded way to improve a paper instead of making undocumented edits. Checks against the experiment log and allowed references help catch unsupported claims or invented results.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/leonardodalinky/scider/content-refinement-agent
Any agent
npx skills add leonardodalinky/SciDER --skill content-refinement-agent
Clone the repo
git clone --depth 1 https://github.com/leonardodalinky/SciDER

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.

agentmods badge for content-refinement-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/leonardodalinky/scider/content-refinement-agent.svg)](https://agentmods.dev/skills/leonardodalinky/scider/content-refinement-agent)
Your own site
<a href="https://agentmods.dev/skills/leonardodalinky/scider/content-refinement-agent"><img src="https://agentmods.dev/badge/skills/leonardodalinky/scider/content-refinement-agent.svg" alt="Measured on agentmods" 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 2,518 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 $0.00104 $0.02518
Opus 5 $0.00052 $0.01259
Sonnet 5 $0.00021 $0.00504
Haiku 4.5 $0.00010 $0.00252

Measured 6d ago against content hash 7bd827987dcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/apply_worklog.py, scripts/score_delta.py, scripts/snapshot.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

Copies of this mod

1 near-identical copy found in the catalogue:

.scider/skills/content-refinement-agent/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 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

The refinement loop

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 · 257 lines

Files

What ships with it

7 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.

  1. 6d ago First seen · 257 lines · 104 tokens per session scan A 7bd827987dcb

Subscribe to this mod's changes

content-refinement-agent is a skill published in the GitHub repository leonardodalinky/SciDER (88 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 104 tokens to every session and 2,518 once invoked, about $0.0005 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

drawio-reconstruction

Reconstructs reference images into high-fidelity, editable Draw.io files with rendered previews: native Draw.io elements carry text and structure, SVG covers simple icons that match the reference, and cropped or transparent PNGs preserve complex visuals. Use when the user wants a diagram image, research figure…

HKUSTDial/Supervisor-Skills · 102 tokens

idea-evaluator

Evaluates a preliminary research idea against a five-dimension framework (Higher, Faster, Stronger, Cheaper, Broader) plus idea-lifecycle and student-capability matching, paradigm-shift probing, and a fatal-flaws audit. Returns a reviewer-style verdict; non-STEM ideas route to substitute frameworks. Use when the user…

HKUSTDial/Supervisor-Skills · 123 tokens

paper-polish

Polishes existing academic prose while preserving the author's meaning: grammar and flow repair, tone calibration against evidence strength, AI-tone removal, and Chinese-to-English rewriting at submission quality. Never fabricates data, citations, or claims, and flags any edit that could change scientific meaning. Use…

HKUSTDial/Supervisor-Skills · 93 tokens

paper-writer

Drafts publishable paper prose from the author's own materials, from a single paragraph to a full manuscript, across STEM and non-STEM fields. Every factual claim traces to user input, verified retrieval, or field common knowledge; citations pass an independent verification ladder; delivery is clean prose with zero…

HKUSTDial/Supervisor-Skills · 90 tokens

pre-submission-reviewer

Runs a pre-submission review of a technical paper across five dimensions: macro logic, writing details, English grammar, LaTeX formatting, and figure quality. Uses a reviewer-style severity taxonomy (CRITICAL / MAJOR / MINOR) and flags banned AI-tone vocabulary and em-dash misuse. Use when the user asks to 'review…

HKUSTDial/Supervisor-Skills · 104 tokens

benchmark-paper-template

Structures Benchmark and Evaluation papers using the five-pillar framework (Research Gap, Construction Pipeline, Evaluation Framework, Empirical Findings, optional Companion Method). Returns a completeness audit, a six-part Introduction logic chain, a Section 2-7 skeleton, and a pre-submission checklist. Use when…

HKUSTDial/Supervisor-Skills · 96 tokens