Borrowing it
Nothing to install: this file belongs to rajpootathar/Crane. 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/rajpootathar/Crane/main/CLAUDE.mdgit clone --depth 1 https://github.com/rajpootathar/CraneWrote 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/rajpootathar/crane/claude-md)<a href="https://agentmods.dev/instructions/rajpootathar/crane/claude-md"><img src="https://agentmods.dev/badge/instructions/rajpootathar/crane/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 | $0.03674 | $0.03674 |
| Opus 5 | $0.01837 | $0.01837 |
| Sonnet 5 | $0.00735 | $0.00735 |
| Haiku 4.5 | $0.00367 | $0.00367 |
Grade A, and why
Crane 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 7d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crane — Project Ruleset
Native GPU-rendered desktop development environment built in pure Rust with egui/wgpu.
Tech stack
- Language: Rust edition 2024
- GUI: eframe 0.34 + egui 0.34 + wgpu backend
- Terminal: in-house
crane_termcrate (crates/crane_term) wrappingvte0.15 (parser only) + portable-pty 0.9 (cross-platform PTY). Owns the grid, scrollback, ?2026 sync replay, and resize reflow. Replacedalacritty_terminalend-to-end on thefeat/crane-termbranch. - Concurrency: parking_lot mutexes,
std::threadfor PTY reader; no async runtime - Git: shell out to the
gitbinary viastd::process::Command— nevergit2, neverlibgit2 - Text / markdown / diff: syntect (syntax highlighting), pulldown-cmark (markdown), similar (diff)
- File dialogs: rfd (native folder/file pickers)
- Icon: loaded from
crane.pngviaimagecrate, set as app icon viaViewportBuilder::with_icon
Naming glossary (canonical — do not drift)
Regions (top-level screen areas):
- Left Panel — projects tree
- Main Panel — active Tab's Layout of Panes
- Right Panel — Changes / Files
Hierarchy:
- Project — a git repo on disk. Contains 1+ Workspaces.
- Workspace — a branch checkout of a Project, backed by
git worktree addunder~/.crane-worktrees/<project-name>/<branch>by default (user can override location). Contains 1+ Tabs. - Tab — a named surface in the Main Panel. Owns one Layout.
- Layout — the split tree inside a Tab (what ⌘D / ⌘⇧D splits).
- Pane — a leaf in a Layout; one of: Terminal, Files, Markdown, Diff, Browser.
- File Tab — an open file inside the Files Pane. Internal-only term — never at the top level.
Code still uses the old names Workspace (for the Layout struct) and Worktree (for the Workspace struct); rename is agreed but not yet executed.
Architecture
Single binary, single process. No FFI, no Go, no subprocesses other than git.
crate::app vs warpui — two names, two things
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.
- 7d ago First seen · 227 lines · 3,674 tokens per session scan A 9110c819382d
Crane CLAUDE.md is an instructions file published in the GitHub repository rajpootathar/Crane (20 stars, last pushed 1mo ago), licensed MIT. It adds 3,674 tokens to every session, about $0.0184 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.