Borrowing it
Nothing to install: this file belongs to Aiyo28/Xee-mcp. 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/Aiyo28/Xee-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/Aiyo28/Xee-mcpWrote 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/aiyo28/xee-mcp/claude-md)<a href="https://agentmods.dev/instructions/aiyo28/xee-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aiyo28/xee-mcp/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/aiyo28/xee-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/aiyo28/xee-mcp/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 | $0.00690 | $0.00690 |
| Opus 5.5 | $0.00276 | $0.00276 |
| Sonnet 5.5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
Xee-mcp 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 2mo 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xee-mcp — Agent Session Protocol
For Claude Code / Claude Desktop sessions working on this repo. Skinny by design.
Project shape
- What: MCP server for X (Twitter) — search + read only. Naming: X + See = Xee.
- Stack: Python 3.11+,
mcpSDK,twikitfor cookie-based scrape,uvfor deps. - Out of scope: posting, DMs, likes, retweets. If asked to add posting, push back — that's a separate repo (different threat model, different audit surface).
- Tag:
[OSS]per~/.claude/CLAUDE-current.mdPath B. Donation-only (paypal.me/aiyo28). No paid tiers ever.
Critical gotchas
- Read-only is law. Tools must never mutate X state. If a future contributor adds posting, reject the PR or move it to a separate repo.
- Cookie file path is via
XEE_MCP_COOKIESenv var. Never hardcode. Never log cookie contents. - twikit auth fragility. X may rotate session formats. If
searchoruser_tweetsstart returning empty, first check cookie validity, not code. - Single-account v0.1. Multi-account pool is v0.3 — only if reliable bot-detection forces it. Don't pre-build.
- Tool surface is two functions. Resist scope creep. New tools require a roadmap entry first.
- SEO/AEO discipline. README H1 and first paragraph are LLM-snippet targets. Don't change them without checking they still answer "What is Xee-mcp?" in <50 words.
- Bilingual EN-only v1. X audience is global, RU layer adds maintenance with no clear payoff. Invalidate only if RU/CIS audience signal becomes dominant.
- Name discipline. Repo + Python module + PyPI distro + CLI + server name + env vars all renamed from
mcp-xee→Xee-mcp(2026-05-17, vault [D]#4). Don't reintroduce the old name except in historical/changelog context.
Session opening checklist
- Read
README.md(~50 lines) andROADMAP.md(~30 lines) — the public surface contract. - If working on tools: read
src/xee_mcp/tools.pyandsrc/xee_mcp/client.pyfirst. - If working on auth: read
docs/cookies.md(when it exists). - Cross-project context lives in vault:
~/Documents/Developer/knowledge-os/Projects/Xee-mcp/_context.md.
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.
- 2mo ago First seen · 37 lines · 690 tokens per session scan A 9d33fd39fef0
Xee-mcp CLAUDE.md is an instructions file published in the GitHub repository Aiyo28/Xee-mcp (0 stars, last pushed 11d ago), licensed MIT. It adds 690 tokens to every session, about $0.0028 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.