Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/leonardodalinky/SciDERnpx agentmods add skills/leonardodalinky/scider/section-writing-agentWrote 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/leonardodalinky/scider/section-writing-agent)<a href="https://agentmods.dev/skills/leonardodalinky/scider/section-writing-agent"><img src="https://agentmods.dev/badge/skills/leonardodalinky/scider/section-writing-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.
<a href="https://agentmods.dev/skills/leonardodalinky/scider/section-writing-agent"><img src="https://agentmods.dev/badge/skills/leonardodalinky/scider/section-writing-agent.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 | $0.00125 | $0.02746 |
| Opus 5 | $0.00063 | $0.01373 |
| Sonnet 5 | $0.00025 | $0.00549 |
| Haiku 4.5 | $0.00013 | $0.00275 |
Grade A, and why
section-writing-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 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.
This is a copy
97% identical to section-writing-agent — 7 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.
How it starts
The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Section Writing Agent (Step 4)
Faithful implementation of the Section Writing Agent from PaperOrchestra (Song et al., 2026, arXiv:2604.05018, §4 Step 4, App. F.1 pp. 47–49).
Cost: ONE LLM call (App. B: "Section Writing Agent (1 call): A single, comprehensive multimodal call to draft and compile the complete LaTeX manuscript"). Do NOT split this into per-section calls — the paper explicitly designs it as one comprehensive call so the model can maintain global coherence across sections.
Inputs
workspace/outline.json— the master planworkspace/inputs/idea.md— technical detailsworkspace/inputs/experimental_log.md— raw data for tables and qualitative analysisworkspace/drafts/intro_relwork.tex— the template with Intro + Related Work already filled in by Step 3. This is your starting point. The preamble, package list, style, and the two pre-filled sections must be preserved verbatim.workspace/citation_pool.json— the citation map ({key, title, abstract}for each verified paper)workspace/refs.bib— the BibTeX fileworkspace/inputs/conference_guidelines.md— formatting rulesworkspace/figures/— the actual PNG files from Step 2 (used as multimodal vision input!)workspace/figures/captions.json— caption text per figure_idworkspace/tex_profile.json— TeX package availability flags (written bycheck_tex_packages.pyat Step 0). Read this before generating any LaTeX. It tells you which packages are installed so you select the right cross-reference pattern, font packages, etc. before you write — not after you try to compile.
Output
workspace/drafts/paper.tex— the complete LaTeX paper, with all sections filled. The Step 5 Refinement Agent will iterate on this file.
How to do it
0.5. Read tex_profile.json and select LaTeX patterns
Before composing the prompt, read workspace/tex_profile.json and apply
these rules to every LaTeX choice in the generated paper:
| Profile flag | True → use | False → use instead |
|---|---|---|
use_cleveref |
\cref{fig:X}, \cref{tab:Y} |
Figure~\ref{fig:X}, Table~\ref{tab:Y} |
use_nicefrac |
\nicefrac{a}{b} |
$a/b$ |
use_microtype |
\usepackage{microtype} |
omit the line |
use_t1_fontenc |
\usepackage[T1]{fontenc} |
omit the line |
What ships with it
6 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.
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 · 235 lines · 125 tokens per session scan A 6fcb6aa66dbe
section-writing-agent is a skill published in the GitHub repository leonardodalinky/SciDER (88 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 125 tokens to every session and 2,746 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to section-writing-agent, differing in 7 lines, and is treated as a copy.
Other skills, from other repositories
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…
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…
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…
intro-drafter
Drafts the Introduction prose for a technical paper, guided internally by a six-paragraph flowchart: background and running example, existing limitations, problem essence and goal, key challenges, solution overview, contributions. Positions the paper as Technique or New Problem/Setting, aligns contributions with…
figure-designer
Advises on the design of the three core figures in a technical paper: the Motivated Example (Figure 1), the Solution Overview (Methodology), and the Experimental Results figures. Recommends the right design paradigm, layout, labelling, and tool for each figure type, then runs a quality-control audit. Use when the user…
tech-paper-template
Structures a technical paper's full logical skeleton using a thinking-template table (research background, limitations, key idea or goal, challenges, methodology modules, contributions), positions the paper as Technique or New Problem/Setting, and runs a four-point self-consistency check. Use when the user is…