claudeleaf CLAUDE.md

Project instructions for Claudeleaf, a tool that lets an AI agent edit Overleaf projects, which are online collaborative LaTeX documents, in real time.

In plain words
What is it for?
Use them when developing or maintaining Claudeleaf's TypeScript SDK, command-line interface, or MCP server for editing Overleaf projects.
Why use it?
They explain the project's structure, technology, and data flow so contributors can change it consistently.

Instructions file

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.

agentmods
npx agentmods add instructions/lonetis/claudeleaf/claude-md
Clone the repo
git clone --depth 1 https://github.com/lonetis/claudeleaf
Per session 4,463 This file is loaded in full into every session.
When invoked 4,463 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.04463 $0.04463
Opus 5 $0.02232 $0.02232
Sonnet 5 $0.00893 $0.00893
Haiku 4.5 $0.00446 $0.00446

Measured 2d ago against content hash e943f8d231d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claudeleaf CLAUDE.md 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 2d 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.

CLAUDE.md · 270 lines

How it starts

The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Internal documentation for Claudeleaf — the single source of truth for how the project works. (User-facing docs live in README.md.)

What this is

Claudeleaf bridges an Overleaf account to an API so Claude — or any agent/tool — can edit any of the account's projects programmatically through Overleaf's live web-editing channel (not git). Edits appear to collaborators in real time, attributed to the signed-in user. One instance is account-scoped: it lists every accessible project and edits any of them (by id or name); each project is backed by its own realtime connection.

TypeScript / Node, delivered as three layers over one core:

  • a TypeScript SDK (OverleafClient, account-scoped; ProjectSession, per-project),
  • a CLI (claudeleaf) — thin command wrapper,
  • an MCP server — thin tool wrapper, for Claude Code.

Tech stack

  • Node.js 20+, TypeScript (ESM, NodeNext), built with tsc to dist/. npm for tooling.
  • ws — the realtime WebSocket transport.
  • global fetch (Node) — the Socket.IO handshake and the REST tree/projects endpoints.
  • playwright-core — drives the user's installed Chrome/Edge for the one-time manual login (no browser download). Loaded lazily (dynamic import in auth.browserLogin) so the SDK/CLI/MCP stay lightweight — important for npx.
  • @modelcontextprotocol/sdk + zod — the MCP server.
  • vitest — unit + live integration tests. tsx — run TS directly (dev / MCP launch).

Project structure (src/, flat)

src/
  index.ts        public API: OverleafClient, ProjectSession, Config, Document, errors
  config.ts       account-level Config (no project/credentials); env parsing
  errors.ts       error hierarchy (ClaudeleafError + subclasses)
  util.ts         async helpers: Mutex, Deferred, sleep, withTimeout
  protocol.ts     Socket.IO 0.9 frame encode/decode (pure)
  ot.ts           ShareJS ops, offset<->rowcol, diff, wire encoding, git-blob hash (pure)
  logParser.ts    parse pdfTeX/LaTeX output.log into errors/warnings/bad-boxes (pure)
  document.ts     Document: local mirror of one open doc (text + version + generation)
  types.ts        shared types (Entity, ProjectSummary, ProjectInfo, CompileResult, ...)
  realtime.ts     RealtimeConnection(projectId): WS transport, acks, heartbeat, reconnect
  auth.ts         SessionManager: manual browser login + session cookie cache
  rest.ts         listProjects() + RestClient(projectId) for tree CRUD + compile/output
  session.ts      ProjectSession: one project's realtime connection, tree, edits, compile
  client.ts       OverleafClient: account-scoped; listProjects + per-project delegation
  cli.ts          CLI (login, doctor, projects, doc ops, compile, mcp); the bin
  mcpServer.ts    MCP server exposing the SDK as tools (each takes a project)
test/             vitest unit (no network) + integration/mcp e2e (live, auto-skip)

Read the full file on GitHub · 270 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. 2d ago First seen · 270 lines · 4,463 tokens per session scan A e943f8d231d9

Subscribe to this mod's changes

claudeleaf CLAUDE.md is an instructions file published in the GitHub repository lonetis/claudeleaf (14 stars, last pushed 2mo ago), licensed MIT. It adds 4,463 tokens to every session, about $0.0223 per session on Opus 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

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens