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 phuc-nt/openclaw-skills --skill goodreadsgit clone --depth 1 https://github.com/phuc-nt/openclaw-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/phuc-nt/openclaw-skills/goodreads)<a href="https://agentmods.dev/skills/phuc-nt/openclaw-skills/goodreads"><img src="https://agentmods.dev/badge/skills/phuc-nt/openclaw-skills/goodreads/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/phuc-nt/openclaw-skills/goodreads"><img src="https://agentmods.dev/badge/skills/phuc-nt/openclaw-skills/goodreads.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 | $0.00060 | $0.01881 |
| Opus 5 | $0.00030 | $0.00941 |
| Sonnet 5 | $0.00012 | $0.00376 |
| Haiku 4.5 | $0.00006 | $0.00188 |
Grade A, and why
goodreads 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 10d 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 — 286 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goodreads Skill
Full read + write access to Goodreads via RSS feeds and Playwright browser automation.
Scripts
# Read-only (RSS + scraping, no login required)
R=scripts/goodreads-rss.py
# Write (Playwright browser automation, requires one-time login)
W=scripts/goodreads-write.sh
Setup
See references/SETUP.md for installation and first-time login instructions.
Quick start:
# Install dependencies
pip install playwright playwright-stealth
playwright install chromium
# Login to Goodreads (one-time, opens browser)
./scripts/goodreads-write.sh login
User Configuration
Replace <USER_ID> with your Goodreads user ID in all commands below.
How to find your user ID: Go to your Goodreads profile page. The URL will be like:
goodreads.com/user/show/12345678-yourname— the number is your user ID.
For write commands with RSS verification, set:
export GOODREADS_USER_ID="<YOUR_USER_ID>"
Read Commands
1. View shelf
python3 $R shelf <USER_ID> --shelf <shelf> [--limit N] [--sort <sort>]
--shelf |
Meaning |
|---|---|
currently-reading |
Currently reading |
read |
Already read |
to-read |
Want to read |
<custom> |
Custom shelf |
--sort |
Meaning |
|---|---|
date_read |
Date finished (default for read) |
date_added |
Date added to shelf |
rating |
Personal rating |
title |
Book title |
author |
Author name |
avg_rating |
Average Goodreads rating |
Examples:
python3 $R shelf <USER_ID> --shelf currently-reading
python3 $R shelf <USER_ID> --shelf read --limit 20 --sort date_read
python3 $R shelf <USER_ID> --shelf to-read --limit 50
python3 $R shelf <USER_ID> --shelf read --limit 200 --sort rating
Fields returned: title, author, book_id, isbn, user_rating (0–5), average_rating, date_read, date_added, review, shelves, description (300 chars), published, book_url
2. Recent activity
python3 $R activity <USER_ID> [--limit N]
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 286 lines · 60 tokens per session scan A 81b5d5541c79
goodreads is a skill published in the GitHub repository phuc-nt/openclaw-skills (25 stars, last pushed 5mo ago), licensed MIT. It adds 60 tokens to every session and 1,881 once invoked, about $0.0003 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.