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 ShaishavMaisuria/research-paper-lifecycle-skills --skill refactor-structuregit clone --depth 1 https://github.com/ShaishavMaisuria/research-paper-lifecycle-skillsWrote 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/shaishavmaisuria/research-paper-lifecycle-skills/refactor-structure)<a href="https://agentmods.dev/skills/shaishavmaisuria/research-paper-lifecycle-skills/refactor-structure"><img src="https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/refactor-structure/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/shaishavmaisuria/research-paper-lifecycle-skills/refactor-structure"><img src="https://agentmods.dev/badge/skills/shaishavmaisuria/research-paper-lifecycle-skills/refactor-structure.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 | $0.00214 | $0.02526 |
| Opus 5.5 | $0.00086 | $0.01010 |
| Sonnet 5.5 | $0.00043 | $0.00505 |
| Haiku 4.5 | $0.00021 | $0.00253 |
Grade A, and why
refactor-structure 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.
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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactor Structure
Fix the architecture of the argument, not its words. A paper can be grammatical, on-template, and within the page limit and still fail because the story is assembled in the wrong order, a section doesn't do its job, the introduction promises things the body never delivers, or the conclusion outruns the evidence. This skill diagnoses those problems and produces a restructuring plan — move / merge / split / cut, with the reasoning for each — that the author approves before a single section is rewritten.
It plans and (on approval) executes the moves. It does not reword sentences
(that is polish-prose) and it does not fit the paper to a venue's rules
(that is tailor-to-venue).
When to use
- "The structure feels off" / "it doesn't flow" / "reorganize my paper".
- Reviewers said: hard to follow, disorganized, the story is unclear, the contribution is buried, related work is in the wrong place, a section doesn't belong.
- The intro over-promises (claims a proof / user study / ablation the body doesn't contain), or the conclusion claims something never evidenced.
- Redundant sections (two Background sections), or one section doing two jobs (Results carrying Threats-to-Validity).
Not for: sentence wording / de-AI-ifying (polish-prose), page limits /
templates / track fit (tailor-to-venue), the Related Work section's content
(draft-related-work), or whether the citations are real (verify-citations).
Inputs
- The draft: main
.texfile (the script follows\input/\include). - Optional: the paper's intended contribution list and target paper type, from
.paper-memory/profile.ymlif present (a theory paper and an empirical paper have different expected arcs). If absent, ask the author for the one-sentence claim and the contribution bullets.
Process
1. Read the structure, don't re-read the paper
Run the bundled extractor to get the skeleton on one screen:
python3 skills/refactor-structure/scripts/outline_extract.py <main.tex>
What ships with it
3 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.
- 1mo ago First seen · 193 lines · 214 tokens per session scan A adffacddcf4c
refactor-structure is a skill published in the GitHub repository ShaishavMaisuria/research-paper-lifecycle-skills (55 stars, last pushed 3d ago), licensed Apache-2.0. It adds 214 tokens to every session and 2,526 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
research-manager
Use this when starting a new research project or managing a complex, multi-step research workflow.
academic-writing
You must use this when producing any research prose — literature reviews, syntheses, analyses, methodology descriptions, discussion sections, abstracts, or any written output intended for an academic audience.
systematic-review
You must use this when conducting PRISMA-standard systematic reviews, protocol development, or Risk of Bias assessment.
hypothesis-testing
You must use this when formulating testable hypotheses, designing experimental controls, or defining falsification criteria.
multi-source-investigation
You must use this when investigating complex claims across diverse sources or fact-checking contradictory information.
peer-review
You must use this when critiquing academic manuscripts, evaluating methodological rigor, or providing structured reviewer feedback.