overleaf

overleaf is a skill for Claude Code, Codex from DJRHails/dotfiles. It costs 109 tokens per session (3,111 once invoked), scanned B, original, MIT.

A command-line tool for managing Overleaf projects through an existing logged-in browser session. It can list, read, write, delete, mirror, compile, and download project files.

In plain words
What is it for?
Use it to sync a local directory with an Overleaf project, edit its files, compile documents, and retrieve the resulting PDF.
Why use it?
It provides scriptable Overleaf access without the paid Git or GitHub integrations. This helps automate project file changes and PDF builds from a terminal.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./overleaf.py files write <project> main.tex --from ./built/main.tex [--yes].

Good fit Use it to sync a local directory with an Overleaf project, edit its files, compile documents, and retrieve the resulting PDF.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/DJRHails/dotfiles
agentmods
npx agentmods add skills/djrhails/dotfiles/overleaf

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 overleaf

README.md
[![agentmods](https://agentmods.dev/badge/skills/djrhails/dotfiles/overleaf/github.svg)](https://agentmods.dev/skills/djrhails/dotfiles/overleaf)
Your own site
<a href="https://agentmods.dev/skills/djrhails/dotfiles/overleaf"><img src="https://agentmods.dev/badge/skills/djrhails/dotfiles/overleaf/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 overleaf

Your own site · 80×15
<a href="https://agentmods.dev/skills/djrhails/dotfiles/overleaf"><img src="https://agentmods.dev/badge/skills/djrhails/dotfiles/overleaf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,111 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00109 $0.03111
Opus 5.5 $0.00044 $0.01244
Sonnet 5.5 $0.00022 $0.00622
Haiku 4.5 $0.00011 $0.00311

Measured 1mo ago against content hash f520921213fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

overleaf scanned grade B with 1 finding 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.

The scan reads SKILL.md. This mod also ships 2 executable files (overleaf.py, test_overleaf.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

printf '%s' "$s" > ~/.config/overleaf/session && chmod 600 ~/.config/overleaf/session && \
modules/agents/skills/overleaf/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overleaf CLI

Overleaf publishes no API, and both its git bridge and its GitHub sync are premium features. overleaf.py drives the same endpoints the web editor drives, authenticated by the overleaf_session2 cookie of a logged-in browser — so a free account gets scriptable read and write access, including the directory mirroring the git bridge would otherwise be for.

Sibling of the slack skill and built the same way: a PEP 723 uv run script, one typed pydantic model per payload, typer sub-apps, an env-file preload, and the same "runs headless off-box" session path.

Prerequisites

  • Signed into https://www.overleaf.com/ in a browser. Nothing else — no premium plan, no token, no OAuth app. The session is read from the browser's own cookie store, or supplied directly where that is not possible (see Auth).
  • uv installed. Dependencies are inline: browser-cookie3, pydantic, requests, rich, typer, websocket-client.

Commands

All commands take PROJECT as a project id, a project URL, or a name (matched exactly, then case-insensitively, then by substring; an ambiguous name lists the candidates instead of guessing). -v prints session details to stderr and -b picks the browser; both are top-level options, so they come before the subcommand (overleaf.py -b firefox files ls <project>).

./overleaf.py session                         # who the session belongs to (the quickest check)
./overleaf.py export-env                      # print this browser's session for another host

./overleaf.py projects list [--json] [--archived]
./overleaf.py projects new "Paper title"      # prints the new project's id and URL

./overleaf.py files ls   <project> [--json]   # paths with their entity ids and kinds
./overleaf.py files read <project> sections/intro.tex [-o out.tex]
./overleaf.py files write <project> main.tex --from ./built/main.tex [--yes]
./overleaf.py files rm   <project> figures/old.png [--yes]

./overleaf.py push <project> ./staged [--prune] [--dry-run] [--yes]
./overleaf.py compile  <project> [--pdf paper.pdf] [--logs]
./overleaf.py download <project> [-o project.zip]

Read the full file on GitHub · 230 lines

Files

What ships with it

2 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.

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 First seen · 230 lines · 109 tokens per session scan B f520921213fd

Subscribe to this mod's changes

overleaf is a skill published in the GitHub repository DJRHails/dotfiles (2 stars, last pushed 2d ago), licensed MIT. It adds 109 tokens to every session and 3,111 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-09.

Related

overleaf compared with skills from other repositories

overleaf next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
overleafDJRHails/dotfilesSkill22d agoMITB109Claude Code, Codex
md2pdfjoshukraine/dotfilesSkill42910d agoMITA22Claude Code
treatment-plansmagic3007/dotfilesSkill112d agoMITB86Claude Code
latex-postersmagic3007/dotfilesSkill112d agoMITA60Claude Code
open-notebookmagic3007/dotfilesSkill112d agoMITA123Claude Code, Codex
liteparsemagic3007/dotfilesSkill112d agoMITA98Claude Code
clinical-decision-supportmagic3007/dotfilesSkill112d agoMITA97Claude Code