Borrowing it
Nothing to install: this file belongs to Xero-Team/zpdf. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Xero-Team/zpdf/main/CLAUDE.mdgit clone --depth 1 https://github.com/Xero-Team/zpdfWrote 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/instructions/xero-team/zpdf/claude-md)<a href="https://agentmods.dev/instructions/xero-team/zpdf/claude-md"><img src="https://agentmods.dev/badge/instructions/xero-team/zpdf/claude-md.svg" alt="Measured on agentmods" 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 | $0.01770 | $0.01770 |
| Opus 5 | $0.00885 | $0.00885 |
| Sonnet 5 | $0.00354 | $0.00354 |
| Haiku 4.5 | $0.00177 | $0.00177 |
Grade A, and why
zpdf 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 6d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build & Test Commands
cargo build # build all crates (default: cpu-render)
cargo build --features gpu-render # include wgpu GPU backend
cargo test # run all tests
cargo test -p zpdf-parser # test a single crate
cargo clippy --workspace # lint all crates
cargo run -p zpdf-cli -- render <file.pdf> -p 1 -o out.png --dpi 150
cargo run -p zpdf-cli -- info <file.pdf>
cargo run -p zpdf-cli -- dump <file.pdf> <obj-num> <gen-num>
cargo run -p zpdf-cli -- debug-stream <file.pdf> <obj-num> <gen-num>
Features: cpu-render (default, tiny-skia), gpu-render (wgpu). Set on the root zpdf crate.
Architecture
18-crate workspace. Strict one-direction dependency flow — render backends never depend on the parser.
PDF bytes
→ zpdf-parser (lexer, xref incl. /XRefStm + lazy repair, object/stream decoding, filters, RC4/AES decryption)
→ zpdf-document (catalog, page tree + attribute inheritance, effective_box/CropBox, font loading)
→ zpdf-content (content stream tokenizer → operator interpreter; shading.rs evaluates axial/radial gradients, mesh.rs decodes type 4–7 mesh shadings)
→ zpdf-display-list (flat RenderCommand sequence)
→ zpdf-render-cpu | zpdf-render-wgpu (implements RenderBackend trait from zpdf-render)
Supporting crates feed into zpdf-content: zpdf-font (Type1/TrueType/CID, CMap, encoding), zpdf-image (JPEG/Flate/CCITT/masks/palettes → RGBA), zpdf-color (device/Indexed/Lab conversion + the PDF function evaluator in function.rs — types 0/2/3/4, used by tint transforms and shadings).
zpdf-core provides shared types used everywhere: ObjectId, PdfObject, Matrix, Rect, Error, ParseLimits.
zpdf-writer is the authoring/editing crate (depends on parser + document + content, never on renderers): DocumentBuilder (creation from scratch, TrueType embedding + sparse-glyf subsetting), IncrementalWriter (ISO §7.5.6 updates — annotations with baked /AP, forms, stamps, redaction, page ops, signing; encrypted docs via new_with_password), rewrite_pdf (GC/decrypt/compress/downsample/encrypt-on-save), linearize_pdf (Annex F), append_document (merge incl. outlines/AcroForm/OCGs).
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.
- 6d ago First seen · 80 lines · 1,770 tokens per session scan A 1cb260a49933
zpdf CLAUDE.md is an instructions file published in the GitHub repository Xero-Team/zpdf (11 stars, last pushed 5d ago), licensed MIT. It adds 1,770 tokens to every session, about $0.0089 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
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.