Borrowing it
Nothing to install: this file belongs to terminalcraft/moltbook-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/terminalcraft/moltbook-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/terminalcraft/moltbook-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/terminalcraft/moltbook-mcp/agents-md)<a href="https://agentmods.dev/instructions/terminalcraft/moltbook-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/terminalcraft/moltbook-mcp/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/terminalcraft/moltbook-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/terminalcraft/moltbook-mcp/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 | $0.00525 | $0.00525 |
| Opus 5.5 | $0.00210 | $0.00210 |
| Sonnet 5.5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
moltbook-mcp 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 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.
What it actually says
AGENTS.md
Project Overview
MCP (Model Context Protocol) server for Moltbook — a social platform for AI agents. Provides engagement state tracking, content security (blocklist, injection detection), thread diffing, trust scoring, and Bluesky cross-platform discovery.
Architecture
- Single-file server:
index.js(~1400 lines). ES module, Node 18+. - Protocol: MCP over stdio using
@modelcontextprotocol/sdk. - State: JSON file at
~/.config/moltbook/engagement-state.json. Tracks seen posts, comments, votes, pending queue. - API: All Moltbook calls go through
https://www.moltbook.com/api/v1. Auth viaMOLTBOOK_API_KEYenv var. - Blocklist:
~/moltbook-mcp/blocklist.json. Authors on the list have content filtered from digests.
Key Patterns
- Every tool is registered via
server.tool()with Zod schemas for validation. - Content from Moltbook posts/comments is untrusted — wrapped in
[USER_CONTENT_START]...[USER_CONTENT_END]markers. - Dedup guard prevents duplicate comments/posts on retries (120s window).
- Failed comments auto-queue to
pendingCommentswith exponential backoff. moltbook_digestscores posts by heuristics (length, question marks, links, code blocks) to filter signal from noise.
Tools Provided
20 MCP tools: moltbook_post, moltbook_post_create, moltbook_comment, moltbook_vote, moltbook_search, moltbook_submolts, moltbook_profile, moltbook_profile_update, moltbook_state, moltbook_thread_diff, moltbook_digest, moltbook_trust, moltbook_karma, moltbook_pending, moltbook_follow, moltbook_export, moltbook_import, moltbook_bsky_discover.
Running
MOLTBOOK_API_KEY=<key> node index.js
Testing
No test suite. Validate by running the server and calling tools via MCP client.
Dependencies
@modelcontextprotocol/sdk— MCP protocol@atproto/api— Bluesky integrationmonero-ts— XMR balance checkingzod(transitive via MCP SDK) — schema validation
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 · 36 lines · 525 tokens per session scan A dc9295be3b7e
moltbook-mcp AGENTS.md is an instructions file published in the GitHub repository terminalcraft/moltbook-mcp (12 stars, last pushed 4mo ago), licensed MIT. It adds 525 tokens to every session, about $0.0021 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 2026-08-30.
moltbook-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| moltbook-mcp AGENTS.mdterminalcraft/moltbook-mcp | Instructions file | 12 | 4mo ago | MIT | A | 525 | 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 |