Borrowing it
Nothing to install: this file belongs to RP-Digital-Innovations/context-snipe. 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/RP-Digital-Innovations/context-snipe/main/CLAUDE.mdgit clone --depth 1 https://github.com/RP-Digital-Innovations/context-snipeWrote 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/rp-digital-innovations/context-snipe/claude-md)<a href="https://agentmods.dev/instructions/rp-digital-innovations/context-snipe/claude-md"><img src="https://agentmods.dev/badge/instructions/rp-digital-innovations/context-snipe/claude-md/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.
<a href="https://agentmods.dev/instructions/rp-digital-innovations/context-snipe/claude-md"><img src="https://agentmods.dev/badge/instructions/rp-digital-innovations/context-snipe/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02052 | $0.02052 |
| Opus 5 | $0.01026 | $0.01026 |
| Sonnet 5 | $0.00410 | $0.00410 |
| Haiku 4.5 | $0.00205 | $0.00205 |
Grade A, and why
context-snipe 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 9d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Snipe — Master Reference
Read this before touching anything. AI tools have built pieces of this across multiple repos without leaving a map. This is the map.
What Context Snipe actually is
A Windows desktop app (and supporting tools) that gives AI coding tools real information about the developer's screen and project dependencies — so the AI stops giving useless generic advice.
Two main features:
- Screen capture — press Ctrl+Shift+X and the app grabs a screenshot of whatever window you're in, runs OCR on it, and makes that available to your AI coding tool (Cursor, Windsurf, VS Code, Zed) via MCP.
- Dependency/CVE scanning — reads your lockfiles and tells your AI which known security vulnerabilities actually affect your project.
Business model: Free (screen capture only) / Pro $9/mo / Security $29/mo.
The 4 repos and what each one does
1. context-snipe-v2 (PRIVATE) — the actual product
This is the main thing. Everything else supports it.
A Tauri 2 desktop app that runs as a background tray icon.
- On first boot: automatically writes itself into the MCP config files of Cursor, Windsurf, VS Code, and Zed so the AI tools can talk to it.
- When the user presses Ctrl+Shift+X: captures the active window via DXGI (Windows GPU direct), runs OCR via Tesseract to extract text from the image, saves the result to a temp file.
- When an AI tool asks for context: the MCP server reads that temp file and returns the screenshot + OCR text to the AI.
- Also includes dependency scanning (reads lockfiles) and CVE checking.
Key files in src-tauri/src/:
lib.rs— app startup, tray icon, global shortcut, daemon modecapture.rs— screen capture + OCR logicide_registrar.rs— writes the MCP config into IDE folders on first bootmcp_server.rs— the MCP JSON-RPC server (runs when invoked with--mcp)mcp_firewall.rs— routes the capture result to the MCP layer
State as of June 2026: The code compiles (old error.txt files in the repo are
from earlier debugging, the current code has those fixes). Releases v0.1.0
through v0.1.2 exist in context-snipe-releases.
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.
- 9d ago First seen · 189 lines · 2,052 tokens per session scan A 2f78ab17b424
context-snipe CLAUDE.md is an instructions file published in the GitHub repository RP-Digital-Innovations/context-snipe (1 stars, last pushed 2mo ago), licensed MIT. It adds 2,052 tokens to every session, about $0.0103 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
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.