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 skills add vladmdgolam/agent-skills --skill apple-books-mcpgit clone --depth 1 https://github.com/vladmdgolam/agent-skillsWrote 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/skills/vladmdgolam/agent-skills/apple-books-mcp)<a href="https://agentmods.dev/skills/vladmdgolam/agent-skills/apple-books-mcp"><img src="https://agentmods.dev/badge/skills/vladmdgolam/agent-skills/apple-books-mcp/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/skills/vladmdgolam/agent-skills/apple-books-mcp"><img src="https://agentmods.dev/badge/skills/vladmdgolam/agent-skills/apple-books-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 14 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 14 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium Memory Poisoning · line 50 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
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 | $0.00081 | $0.01603 |
| Opus 5 | $0.00041 | $0.00801 |
| Sonnet 5 | $0.00016 | $0.00321 |
| Haiku 4.5 | $0.00008 | $0.00160 |
Grade A, and why
apple-books-mcp 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 13d 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Books MCP
MCP server: vgnshiyer/apple-books-mcp
Install: npx -y @anthropic-ai/claude-code mcp add apple-books -- uvx apple-books-mcp
Tools Reference
| Tool | Purpose |
|---|---|
list_all_books |
List all books (ID, title, author) |
get_book_annotations |
All annotations for a book by ID. No color data. |
describe_annotation |
Full details for one annotation including color |
get_highlights_by_color |
All highlights of one color across entire library |
search_highlighted_text |
Search annotations by highlighted text |
search_notes |
Search by user-written notes |
list_all_annotations |
All annotations across all books |
list_all_collections |
List collections |
get_collection_books |
Books in a collection |
describe_book / describe_collection |
Details by ID |
recent_annotations |
Recently created annotations |
full_text_search |
Full text search across books |
Critical: Color Extraction Strategy
get_book_annotations does NOT return colors. describe_annotation returns colors but one at a time — 150+ calls for a single book.
Solution: Call get_highlights_by_color once per color (5 total calls), then cross-reference annotation IDs programmatically.
Available colors: PINK, BLUE, YELLOW, GREEN, PURPLE
Underlines: color = null, is_underline = 1
Build the Color Map
import json, glob
# After calling get_highlights_by_color for PINK, BLUE, YELLOW, GREEN, PURPLE
# Results save to files when they exceed token limits
ann_color = {}
colors = ["PINK", "BLUE", "YELLOW", "GREEN", "PURPLE"]
for color_file, color in zip(sorted(glob.glob("path/to/results/*.txt")), colors):
with open(color_file, 'r') as f:
data = json.load(f)
current_id = None
for line in data.get("text", "").split("\n"):
line = line.strip()
if line.startswith("ID: "):
current_id = line.split("ID: ")[1].strip()
elif line.startswith("Selected text: ") and current_id:
selected = line[len("Selected text: "):]
if selected and selected != "None":
ann_color[current_id] = color
# Look up: ann_color.get(str(annotation_id), None) # None = underline
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.
- 13d ago First seen · 182 lines · 81 tokens per session scan A 1dd70ce7c90d
apple-books-mcp is a skill published in the GitHub repository vladmdgolam/agent-skills (8 stars, last pushed 5d ago), licensed MIT. It adds 81 tokens to every session and 1,603 once invoked, about $0.0004 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 skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.