agentmods.dev

paper-build

paper-build is a skill for Claude Code, Codex from Rezenders/scientific_writing_agent. It costs 19 tokens per session (457 once invoked), scanned A, original, Apache-2.0.

A build-and-check workflow for a LaTeX manuscript, where LaTeX is a system commonly used to produce scientific PDFs. It builds the PDF and runs chktex, a tool that reports likely LaTeX and writing mistakes.

In plain words
What is it for?
Use it after changing the manuscript to validate the PDF build and review lint warnings by file and line.
Why use it?
It shows whether the paper can be compiled and highlights errors, warnings, missing references, and missing citations after substantive edits.

Skill for Claude CodeCodex

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

not rated 14repo changed 1mo ago A scan 19 tokens original Apache-2.0

Good fit Use it after changing the manuscript to validate the PDF build and review lint warnings by file and line.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rezenders/scientific_writing_agent/paper-build
View source ↗ Rezenders/scientific_writing_agent
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 paper-build
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 paper-build

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/rezenders/scientific_writing_agent/paper-build"><img src="https://agentmods.dev/badge/skills/rezenders/scientific_writing_agent/paper-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 457 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 $0.00019 $0.00457
Opus 5.5 $0.00008 $0.00183
Sonnet 5.5 $0.00004 $0.00091
Haiku 4.5 $0.00002 $0.00046

Measured 1mo ago against content hash e327dc0d57e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

paper-build 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/paper-build/SKILL.md · 54 lines

What it actually says

Paper Build

Build and validate the manuscript using the current repository Makefile.

Workflow

  1. Change to <PROJECT_ROOT>.
  2. Run make pdf.
  3. Scan build output for fatal LaTeX errors, especially lines beginning with !.
  4. Report whether the build succeeded.
  5. If the build fails, stop and report the error details instead of continuing.
  6. If the build succeeds, run make lint.
  7. Run make lint-diff (or python3 scripts/lint_diff.py) to determine whether any chktex warnings are new relative to .agents/context/lint-baseline.json.
  8. Report non-suppressed chktex warnings grouped by file, and distinguish pre-existing baseline warnings from newly introduced warnings.
  9. Report undefined references and missing citations found in build output.

Commands

cd <PROJECT_ROOT>
make pdf
make lint
make lint-diff

Repository-Specific Expectations

Customize these in .agents/context/paper-model.md for a concrete paper project:

  • <BUILD_COMMAND> builds <PDF_OR_ARTIFACT_PATH>.
  • <LINT_COMMAND> runs the project's LaTeX or manuscript lint checks.
  • <OPTIONAL_DIFF_LINT_COMMAND> distinguishes newly introduced warnings from any accepted baseline.
  • Update lint baselines only after intentional cleanup or when the user explicitly asks.

Reporting Requirements

  • Build status: PASS or FAIL
  • PDF target status: <PDF_OR_ARTIFACT_PATH>
  • Fatal LaTeX error details when present
  • Undefined references: lines matching LaTeX Warning: Reference ... undefined
  • Missing citations: lines matching LaTeX Warning: Citation ... undefined
  • Lint status with warnings grouped by file
  • Lint-diff status: NO NEW WARNINGS or list of newly introduced warnings

Constraints

  • If the TeX toolchain or chktex is unavailable, report that explicitly.
  • Do not claim a clean result if the build failed, if undefined references remain, or if missing citations remain.
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 · -19 lines · -9 tokens per session e327dc0d57e2
  2. 2mo ago First seen · 73 lines · 28 tokens per session scan A fd7ecdd09562

Subscribe to this mod's changes

paper-build is a skill published in the GitHub repository Rezenders/scientific_writing_agent (14 stars, last pushed 17d ago), licensed Apache-2.0. It adds 19 tokens to every session and 457 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.

DocumentsPDFScientific
Related

paper-build compared with skills from other repositories

paper-build next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
paper-buildRezenders/scientific_writing_agentSkill1417d agoApache-2.0A19Claude Code, Codex
pydicomK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA52Claude Code, Codex
nature-paper2wordYuan1z0825/nature-skillsSkill52k2d agoApache-2.0A233Codex
pptx-postersK-Dense-AI/scientific-agent-skillsSkill56k4d agoMITA59Claude Code
nature-paper-transYuan1z0825/nature-skillsSkill52k2d agoApache-2.0A68Codex
extracting-lab-tablesmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A210Claude Code
paper-compilewanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITB53Claude Code