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/sandraschi/calibremcp/agents-mdgit clone --depth 1 https://github.com/sandraschi/calibremcpWrote 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/sandraschi/calibremcp/agents-md)<a href="https://agentmods.dev/instructions/sandraschi/calibremcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sandraschi/calibremcp/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 | $0.00431 | $0.00431 |
| Opus 5 | $0.00216 | $0.00216 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
calibremcp 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- calibremcp AGENTS.md — 94% identical, 4 lines differ
What it actually says
calibremcp — Agent Guide
Overview
SOTA April 2026 industrialized FastMCP 3.2.0 server for conversational Calibre e-book library management with sampling, agentic workflows, skills, prompts, and LanceDB metadata RAG
Entry Points
uv run schip-mcp-calibre→calibre_mcp.__main__:run
Standards
- FastMCP 3.2+ portmanteau tool pattern — tools use
operationenum param - Responses: structured dicts with
success,message, domain-specific fields - Dual transport: stdio (Claude Desktop) + HTTP (
MCP_TRANSPORT=http) - See mcp-central-docs for fleet-wide coding standards
Key Files
README.md— full documentationpyproject.toml— build config and entry pointsCLAUDE.md— Claude Code context (if present)
HTTP Daemon + Stdio Proxy
This server owns persistent state (Calibre metadata.db, LanceDB RAG index, book FTS cache). To prevent database contention when multiple stdio clients connect concurrently, use the HTTP Daemon + Stdio Proxy pattern:
- Start the HTTP daemon (owns DB):
python -m calibre_mcp(HTTP mode) - Stdio clients (Claude Desktop, opencode, Cursor) probe
http://127.0.0.1:10720/mcpon startup - If the daemon is alive, the stdio instance becomes a lightweight proxy via
create_proxy()— zero DB initialization - If unreachable, starts normally as a standalone server
Env var to override the probe URL: CALIBREOPS_API_URL (default: http://127.0.0.1:10720/mcp)
Reference implementation: src/calibre_mcp/server.py
Install docs: follow mcp-central-docs/standards/AGENT_INSTALL_REFERENCE.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.
- 4d ago First seen · 34 lines · 431 tokens per session scan A 0e1c2ccc7676
calibremcp AGENTS.md is an instructions file published in the GitHub repository sandraschi/calibremcp (41 stars, last pushed 3d ago), licensed MIT. It adds 431 tokens to every session, about $0.0022 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 2026-08-30.
Other instructions, from other repositories
calibre-mcp CLAUDE.md
Instructions for caelum29/calibre-mcp, covering claude.md — calibre mcp server, macro goal, target environment (ground-truth, do not re-derive), hard constraints / gotchas (these killed earlier attempts) and engineering invariants (constrain every edit).
comfyops-mcp AGENTS.md
AGENTS.md instructions for sandraschi/comfyops-mcp, covering agents.md — comfyops-mcp, identity, key files, tools and quick ref.
framework AGENTS.md
AGENTS.md instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
autogen copilot-instructions.md
Copilot instructions for microsoft/autogen, covering autogen multi-agent ai framework, working effectively, prerequisites and environment setup, python development workflow and quick validation (under 1 second each).
jentic-one GEMINI.md
Instructions for jentic/jentic-one: Otherwise, read AGENTS.md — this repo's canonical agent guidance.
AgentGo AGENTS.md
Instructions for yeasy/AgentGo, covering agents.md, purpose, startup instructions, trust & safety and failure modes.