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/kandotrun/x-mcp/agents-mdgit clone --depth 1 https://github.com/kandotrun/x-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/kandotrun/x-mcp/agents-md)<a href="https://agentmods.dev/instructions/kandotrun/x-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kandotrun/x-mcp/agents-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 | $0.00313 | $0.00313 |
| Opus 5 | $0.00156 | $0.00156 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
x-mcp AGENTS.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS https://x.mcp.2-38.com/health What it actually says
AGENTS.md
This repo contains x-mcp, a public read-only Streamable HTTP MCP server for X/Twitter search and retrieval via twitter.2-38.com. The implementation is a TypeScript + Hono Cloudflare Worker.
Operating rules
- Keep the MCP read-only. Do not add write actions such as post, like, repost, follow, DM, notifications, or authenticated timeline access without explicit Kan approval.
- The Worker endpoint is
https://x.mcp.2-38.com/mcp. - The upstream proxy base is
https://twitter.2-38.com/api/fx. - Do not commit
wrangler.jsonc,.dev.vars,.env*, Cloudflare account secrets, OAuth tokens, or API keys. - Keep
wrangler.example.jsoncsafe and placeholder-based except public route/vars. - Keep README and
docs/agent-install-prompts.mdbilingual when changing user-facing onboarding. - Keep
skills/x-mcp/SKILL.mdfocused on how agents should install/configure/use the MCP.
Verification before commit
Run:
npm run check
npm run deploy:dry
For remote smoke testing after deployment:
curl -sS https://x.mcp.2-38.com/health
curl -sS https://x.mcp.2-38.com/.well-known/mcp.json
Then verify MCP tools/list and search_posts using an MCP client or the SDK.
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 · 32 lines · 313 tokens per session scan A 163c8323a827
x-mcp AGENTS.md is an instructions file published in the GitHub repository kandotrun/x-mcp (0 stars, last pushed 16d ago), licensed MIT. It adds 313 tokens to every session, about $0.0016 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
projektor AGENTS.md
AGENTS.md instructions for TAJD/projektor, covering agents.md, what projektor is, coordination model (read this first), planning and design docs live in the wiki, not the repo and architecture: the service-layer contract (most important).
rewind AGENTS.md
AGENTS.md instructions for pdugan20/rewind, covering rewind, work modes, development commands, agent configuration and architecture overview.
ctxlayer CLAUDE.md
Claude Code instructions for stevenn/ctxlayer, covering ctxlayer — claude code briefing, what runs where, architecture pointers, how a claude session should work in this repo and conventions.
ctxlayer AGENTS.md
AGENTS.md instructions for stevenn/ctxlayer, covering working in this repo as an agent, golden path for any change, where things live, module rules and adding an endpoint.
cldcde CLAUDE.md
Instructions for aegntic/cldcde, covering claude.md, commands, development, database and architecture.
urantia-dev-api CLAUDE.md
Claude Code instructions for urantia-hub/urantia-dev-api, covering urantia-dev-api, scope of this service, tech stack, dependency and toolchain pins and testing against production.