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.
npx skills add gpsaggese/helpers --skill research_idea.write_draft_papergit clone --depth 1 https://github.com/gpsaggese/helpersWrote 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/gpsaggese/helpers/research_idea.write_draft_paper)<a href="https://agentmods.dev/skills/gpsaggese/helpers/research_idea.write_draft_paper"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/research_idea.write_draft_paper/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/gpsaggese/helpers/research_idea.write_draft_paper"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/research_idea.write_draft_paper.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 | $0.00009 | $0.01023 |
| Opus 5.5 | $0.00004 | $0.00409 |
| Sonnet 5.5 | $0.00002 | $0.00205 |
| Haiku 4.5 | $0.00001 | $0.00102 |
Grade A, and why
research_idea.write_draft_paper 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Given a research idea, write a full conference paper draft using the
template in
papers/template/
Workflow
Read the Inputs
- Read the research idea passed by the user (a file under
research/ideas/*.md, or idea text pasted directly) - Read the paper template
papers/template/paper.md, including the comment block at the top, for usage and section structure - Read an existing paper for style and depth, e.g.
papers/Optimal_strategy_for_racket_sports/paper.md
Set Up the Paper Directory
- Derive a short
Title_Casename for the paper from the idea (e.g.RL_for_Automated_EDA); ask the user if the idea does not suggest an obvious name - Create
papers/<Paper_Name>/if it does not exist - Link
Makefiletopapers/template/Makefilewith a symlink, so all the paper dirs stay in sync, e.g.,ln -s ../template/Makefile papers/<Paper_Name>/Makefile- Do not copy or edit it for a single paper
- Copy
references.bib,ieee-template.typ, andfigures/frompapers/template/into the new directory - Do not copy
run_latex.sh,lint_latex.sh, ortemplate.pdf: they are obsolete or build outputs- Build with
make, which runsrun_latex.pyfor LaTeX andrender_images.pyfor diagrams - Lint with
lint_text.py -i <file> --use_dockerized_prettier
- Build with
- If the paper is written in LaTeX instead of Markdown, also copy
paper.texand keep the\input{papers/template/style.tex}line in it, shared by all papers - Do not overwrite an existing
paper.mdwithout confirming with the user - Say in the file
paper.mdhow it was generated, with this comment at the top of the file:<!-- Generated by `.claude/skills/research_idea.write_draft_paper/SKILL.md` -->
Write paper.md
- Fill in every
<...>placeholder with content derived from the idea: title, author(s) (the assignee(s) listed inresearch/ideas/README.mdfor this idea, plus GP Saggese), abstract, keywords, and all body sections - Keep the template's section structure (
Introduction,Related Work,Problem Formulation, core methodology,Discussion/Limitations,Conclusion); add, remove, or rename sections only where the template allows - Turn the idea's
Core Idea,Formalization,Key Examples, andResearch Topicsinto theIntroductionandProblem Formulationsections - Turn the idea's
QuestionsandNext stepsintoDiscussion/LimitationsandConclusion/Future Workmaterial - State plainly, per the template, what has not been validated (e.g. no computational implementation or empirical evaluation) instead of fabricating results the idea does not support
- Delete the template's guidance bullets and HTML comment once replaced with real content
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.
- yesterday First seen · 87 lines · 9 tokens per session scan A 6e8ae4b3c50f
research_idea.write_draft_paper is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 9 tokens to every session and 1,023 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-11-06.
research_idea.write_draft_paper compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| research_idea.write_draft_papergpsaggese/helpers | Skill | 158 | today | Apache-2.0 | A | 9 | Claude Code |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | today | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 5d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 5d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 5d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | today | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | today | Apache-2.0 | A | 205 | Claude Code |