pre-submission

pre-submission is a skill for Claude Code, Codex from Rezenders/scientific_writing_agent. It costs 23 tokens per session (647 once invoked), scanned A, original, Apache-2.0.

A pre-submission checklist for a scientific paper. It builds the PDF, checks the LaTeX source for formatting problems, finds open annotations, and audits consistency across the manuscript.

In plain words
What is it for?
Use it as a final go-or-no-go check before submitting or resubmitting a manuscript.
Why use it?
It identifies build errors, unresolved notes, terminology conflicts, and other issues that can block or weaken a submission. An implementation check can be added when relevant.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it as a final go-or-no-go check before submitting or resubmitting a manuscript.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rezenders/scientific_writing_agent/pre-submission
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 Rezenders/scientific_writing_agent --skill pre-submission
Clone the repo
git clone --depth 1 https://github.com/Rezenders/scientific_writing_agent

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 pre-submission

README.md
[![agentmods](https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/pre-submission/github.svg)](https://agentmods.dev/skills/rezenders/scientific_writing_agent/pre-submission)
Your own site
<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/pre-submission"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/pre-submission/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.

agentmods 80×15 button for pre-submission

Your own site · 80×15
<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/pre-submission"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/pre-submission.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 647 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 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 $0.00023 $0.00647
Opus 5.5 $0.00009 $0.00259
Sonnet 5.5 $0.00005 $0.00129
Haiku 4.5 $0.00002 $0.00065

Measured 1mo ago against content hash f5d8022bca6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pre-submission 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.

.agents/skills/pre-submission/SKILL.md · 87 lines

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.

Pre-Submission Checklist

Run this checklist in order. This skill is diagnostic only.

Required Sequence

  1. Run paper-build.
  2. Run find-annotations.
  3. Use .agents/agents/consistency-auditor.md for a full pass across the active manuscript sections.
  4. Use .agents/agents/paper-implementation-checker.md for targeted spot-checks on the highest-risk technical claims, if the project has implementation-dependent claims.

Consistency Audit Scope

Audit the active section files listed in .agents/context/paper-model.md or included by <MAIN_TEX>.

Focus on:

  • macro drift
  • terminology drift
  • acronym consistency
  • notation mismatches
  • alignment between contribution statements and the body

Use an explicit prompt such as:

Perform a full consistency audit across the active section files listed in `.agents/context/paper-model.md`. Focus on macro drift, terminology drift, acronym consistency, notation mismatches, and contribution-statement alignment between the introduction and body.

Implementation Spot-Check Targets

Prioritize 3 to 5 high-risk claims, typically including:

  • runtime or algorithmic behavior;
  • interface, schema, or data-processing details;
  • experiment scripts, datasets, metrics, or generated tables;
  • any explicit artifact names, parameter values, or action names cited in the paper.

Ask the checker to report CONSISTENT, DIVERGES, or CANNOT_VERIFY.

Use .agents/agents/paper-implementation-checker.md rather than inventing an ad hoc check, and ask it to verify 3 to 5 claims with prompts such as:

Does this description match the current implementation? Report CONSISTENT / DIVERGES / CANNOT_VERIFY.

Pass And Fail Rules

  • Do not edit files while running this checklist.
  • Do not return GO if any step fails.
  • If the build environment is unavailable, report that limitation explicitly and mark the affected step accordingly.
  • Treat open \todo, \red, and author comment macros in active manuscript files as blocking.
  • Treat \hide entries in active manuscript files as requiring author review even if they are not rendered.
  • Report old/ annotation matches separately and do not let them block submission unless the user explicitly asks to include archival content.

Read the full file on GitHub · 87 lines

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. 1mo ago Changed · +2 lines · -14 tokens per session f5d8022bca6b
  2. 2mo ago First seen · 85 lines · 37 tokens per session scan A 1b5dccb8ce77

Subscribe to this mod's changes

pre-submission is a skill published in the GitHub repository Rezenders/scientific_writing_agent (14 stars, last pushed 17d ago), licensed Apache-2.0. It adds 23 tokens to every session and 647 once invoked, about $0.0001 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.

Related

pre-submission compared with skills from other repositories

pre-submission next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
pre-submissionRezenders/scientific_writing_agentSkill1417d agoApache-2.0A23Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35k2d agoApache-2.0A123Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA83Claude Code
matlabK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA44Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA71Claude Code, Codex
research-engineerdavila7/claude-code-templatesSkill33kyesterdayMITA43Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A205Claude Code