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.
npx agentmods add instructions/adjective-rob/snap/claude-mdgit clone --depth 1 https://github.com/adjective-rob/snapWrote 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/adjective-rob/snap/claude-md)<a href="https://agentmods.dev/instructions/adjective-rob/snap/claude-md"><img src="https://agentmods.dev/badge/instructions/adjective-rob/snap/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 | $0.00476 | $0.00476 |
| Opus 5 | $0.00238 | $0.00238 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00048 | $0.00048 |
Grade A, and why
snap 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 5d 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.
What it actually says
Snap -- Project Context for Claude Code
What this is
A two-component system: a Tauri 2.x desktop app (Rust + vanilla JS) for screen annotation, and a Python MCP server that exposes the annotation inbox to coding agents.
Architecture
app/-- Tauri 2.x project. Vanilla HTML/CSS/JS frontend, no framework. Rust backend handles screen capture, window context, and file I/O.mcp-server/-- Python package usingfastmcp. Stdio transport. Reads from~/.snap/inbox/.
Key decisions
- Vanilla JS for the overlay frontend. No React, no build tooling beyond what Tauri provides.
- Screen capture uses
gnome-screenshot(GNOME Wayland),grim(wlroots Wayland), orscrot(X11) via subprocess. Tries each in order, uses the first that works. - Window context uses
xdotoolon X11. Returns None on Wayland. - Annotations stored as PNG + sidecar JSON pairs in
~/.snap/inbox/. - MCP server is read-only. It never writes annotations, only reads and deletes.
- On Wayland: app runs in single-shot overlay mode, triggered by GNOME custom keybinding via
snap-trigger.sh. - On X11: app runs as a persistent tray app with built-in global hotkey via Tauri's global-shortcut plugin.
Conventions
- Tauri commands use snake_case
- JS annotation objects match the sidecar JSON schema
- All file paths use
~/.snap/as the root - Error handling: never crash silently, always log to
~/.snap/snap.log - Log rotation at 1MB for both Rust and Python
- Git commits: short, direct messages
Build
make build # Build everything
make dev # Run in dev mode
npx tauri build # Rebuild Tauri app only (must use this, not cargo build alone)
Important: Always use npx tauri build or make build, never bare cargo build. The Tauri build embeds the frontend files into the binary. cargo build alone produces a binary with no frontend.
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.
- 5d ago First seen · 40 lines · 476 tokens per session scan A d282ee468cd8
snap CLAUDE.md is an instructions file published in the GitHub repository adjective-rob/snap (5 stars, last pushed 2mo ago), licensed MIT. It adds 476 tokens to every session, about $0.0024 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 2026-08-31.
Other instructions, from other repositories
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).
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.
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.
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.
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).