Borrowing it
Nothing to install: this file belongs to MediaZione/AwrAiter. 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/MediaZione/AwrAiter/main/AGENTS.mdgit clone --depth 1 https://github.com/MediaZione/AwrAiterWrote 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/mediazione/awraiter/agents-md)<a href="https://agentmods.dev/instructions/mediazione/awraiter/agents-md"><img src="https://agentmods.dev/badge/instructions/mediazione/awraiter/agents-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/mediazione/awraiter/agents-md"><img src="https://agentmods.dev/badge/instructions/mediazione/awraiter/agents-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 | $0.00920 | $0.00920 |
| Opus 5.5 | $0.00368 | $0.00368 |
| Sonnet 5.5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
Grade A, and why
AwrAiter AGENTS.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 4d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md: connect AwrAIter for your user
This file is for AI agents. A person asked you to connect AwrAIter, their Telegram channel panel, to you or to their assistant. Do the steps in order. The server address is the only URL you need.
The same steps are at awraiter.ai/llms.txt. People connecting by hand should read docs/connect.md.
1. The server
https://awraiter.ai/mcp
Remote MCP over Streamable HTTP. Sign-in is OAuth 2.1 with dynamic client registration and PKCE, so no API key is needed when your client does OAuth.
2. Add it, if you can run commands
Add the server under the name awraiter, then start the sign-in.
| Client | Add | Sign in |
|---|---|---|
| Claude Code | claude mcp add --transport http awraiter https://awraiter.ai/mcp |
the person runs /mcp, picks awraiter, presses Authenticate |
| Codex CLI | codex mcp add awraiter --url https://awraiter.ai/mcp |
codex mcp login awraiter |
| Gemini CLI | gemini mcp add --transport http awraiter https://awraiter.ai/mcp |
/mcp auth awraiter |
| Cursor | add "awraiter": { "url": "https://awraiter.ai/mcp" } under mcpServers in ~/.cursor/mcp.json |
press Connect next to it in Cursor's MCP settings |
3. The sign-in
It opens a browser on the same computer as the client. The person signs in to AwrAIter with Telegram and presses Approve.
Ask them to sign in at awraiter.ai/login before you start the login. Codex stops waiting after 5 minutes, and signing in through the Telegram bot inside that window takes most of it.
4. No OAuth, or a client on a server: use a token
Use a token when your client has no OAuth, or when you run on a server and the person's browser is on another computer. In the second case, after Approve the browser shows "127.0.0.1 refused to connect" and the client gets nothing.
- The person opens awraiter.ai/mcp-connect and presses Create token. Full access lets you publish; read-only is for analytics. The token starts with
pat_and is shown once. - The person puts it into the
AWRAITER_TOKENenvironment variable themselves. - Send
Authorization: Bearer <token>on every request. In Codex:codex mcp add awraiter --url https://awraiter.ai/mcp --bearer-token-env-var AWRAITER_TOKEN.
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.
- 4d ago First seen · 63 lines · 920 tokens per session scan A 3ffc54e34064
AwrAiter AGENTS.md is an instructions file published in the GitHub repository MediaZione/AwrAiter (0 stars, last pushed 5d ago), licensed MIT. It adds 920 tokens to every session, about $0.0037 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 2026-11-02.
AwrAiter AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| AwrAiter AGENTS.mdMediaZione/AwrAiter | Instructions file | 0 | 5d ago | MIT | A | 920 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |