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/kristianedlund/hardcover-mcp/pythongit clone --depth 1 https://github.com/kristianedlund/hardcover-mcpWhat 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 | $0.01410 | $0.01410 |
| Opus 5 | $0.00705 | $0.00705 |
| Sonnet 5 | $0.00282 | $0.00282 |
| Haiku 4.5 | $0.00141 | $0.00141 |
Grade A, and why
hardcover-mcp python.instructions.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 2d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Python Coding Conventions
General Instructions
- Readability first. Write code that is easy to read and reason about. Clever one-liners are acceptable only when they do not obscure intent.
- State intent in comments. For non-trivial logic — especially GraphQL query construction, mutation side-effects, and caching — add a comment explaining why, not just what.
- Fail loud, fail early. Validate inputs at function boundaries. Never silently swallow bad data or fall back to a default that hides a bug.
- Keep functions focused. A function should do one thing. If a function needs a
multi-step comment header (
# --- 1. ...,# --- 2. ...), consider whether any step deserves its own function. - Async by default. All I/O-bound functions (API calls, network) must be
async. Keep sync helpers for pure data formatting.
Type Hints
- Use union syntax:
X | YandX | None(Python 3.10+, PEP 604), notOptional[X]orUnion[X, Y]. - Annotate all function signatures with parameter and return types.
- Use
list[int]/dict[str, float](lowercase built-ins, Python 3.9+, PEP 585), notList/Dictfromtyping. - Do not use
from __future__ import annotations. The project targets Python 3.14; the import is a no-op and adds noise.
Docstrings
- Follow NumPy docstring style for all public functions and classes.
- Private helpers (prefixed
_) require at minimum a one-line summary docstring. - Always document: what the input data shape/convention is, and what the output represents.
async def handle_search_books(arguments: dict[str, Any]) -> list[TextContent]:
"""
Search Hardcover for books matching a query string.
Parameters
----------
arguments : dict[str, Any]
Tool arguments. Required key: ``query`` (str).
Optional: ``per_page`` (int, default 10, max 25), ``page`` (int, default 1).
Returns
-------
list[TextContent]
Single-element list with JSON-formatted search results.
"""
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.
- 2d ago First seen · 144 lines · 1,410 tokens per session scan A ae4d73865c37
hardcover-mcp python.instructions.md is an instructions file published in the GitHub repository kristianedlund/hardcover-mcp (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,410 tokens to every session, about $0.0070 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.