Borrowing it
Nothing to install: this file belongs to jeeftor/abs-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/jeeftor/abs-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/jeeftor/abs-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/jeeftor/abs-mcp/agents-md)<a href="https://agentmods.dev/instructions/jeeftor/abs-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jeeftor/abs-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/jeeftor/abs-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jeeftor/abs-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 | $0.01164 | $0.01164 |
| Opus 5.5 | $0.00466 | $0.00466 |
| Sonnet 5.5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00116 | $0.00116 |
Grade A, and why
abs-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 1mo 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Project Goal
Build a high-quality Model Context Protocol server for Audiobookshelf. The server should expose safe, typed MCP tools and resources for inspecting and managing an Audiobookshelf instance, with repeatable tests against a local Docker Audiobookshelf fixture.
Working Assumptions
- Prefer Go for the first implementation unless a later decision record changes that. This matches the nearby Audiobook Organizer ABS client and the official Go MCP SDK.
- Treat the public Audiobookshelf API docs as useful but not authoritative. They currently state that they are out of date and no longer maintained.
- Treat Audiobookshelf source code and verified Docker round-trip tests as the source of truth for behavior.
- The user cannot configure this corporate Codex instance with MCP servers, so local verification must not depend on registering this server in Codex.
Tooling Preferences
- Use
rgfor content searches. - Use
fdorfindfor file discovery. - Use
rtkas the command prefix for shell commands in this workspace. - Use
uvfor Python helper scripts and virtual environments if Python is added. - Use
go test ./...for Go verification once Go code exists. - Use
docker composeonly through repo scripts or documented make targets so the ABS fixture remains resettable.
Coding Discipline
- For non-trivial changes, state the working assumption and the smallest verifiable goal before editing.
- Keep edits surgical and traceable to the current task.
- Prefer simple, typed request/response structures over generic maps at MCP boundaries.
- Do not add speculative MCP tools. Add tools only when backed by an ABS endpoint, a fixture scenario, or a documented user workflow.
- Do not log bearer tokens, API keys, cookies, or raw Authorization headers.
- Do not persist user credentials in committed files.
- Do not mutate files in
/Users/Shared/Docker/audiobook-organizerunless explicitly asked. That fixture can be read and invoked as an external dependency while planning.
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.
- 1mo ago First seen · 80 lines · 1,164 tokens per session scan A 3f905484c232
abs-mcp AGENTS.md is an instructions file published in the GitHub repository jeeftor/abs-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,164 tokens to every session, about $0.0047 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.