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 xinthink/reader-mcp-server --skill readergit clone --depth 1 https://github.com/xinthink/reader-mcp-serverWrote 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/xinthink/reader-mcp-server/reader)<a href="https://agentmods.dev/skills/xinthink/reader-mcp-server/reader"><img src="https://agentmods.dev/badge/skills/xinthink/reader-mcp-server/reader/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/xinthink/reader-mcp-server/reader"><img src="https://agentmods.dev/badge/skills/xinthink/reader-mcp-server/reader.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 | $0.00061 | $0.00748 |
| Opus 5.5 | $0.00024 | $0.00299 |
| Sonnet 5.5 | $0.00012 | $0.00150 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
reader 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 2mo 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reader
Interact with Readwise Reader library using executable scripts.
Quick Start
All Reader operations are available as scripts in the scripts/ subdirectory:
| Script | Purpose | Input |
|---|---|---|
list_documents.py |
Query documents | CLI flags |
create_document.py |
Save URL/content | JSON payload |
update_document.py |
Modify document | JSON payload |
bulk_update_documents.py |
Batch modify (max 50) | JSON payload |
delete_document.py |
Remove documents | JSON payload |
list_tags.py |
List all tags | CLI flags |
Authentication
Set the READWISE_ACCESS_TOKEN environment variable using one of these methods:
Method 1: Using a .env file
Create a .env file in the project directory:
READWISE_ACCESS_TOKEN=your-token-here
The scripts automatically load environment variables from .env using python-dotenv.
Method 2: Command line
Export in shell:
export READWISE_ACCESS_TOKEN=your-token-here
Or inline for a single command:
READWISE_ACCESS_TOKEN=your-token-here python scripts/list_documents.py
Getting your token
Get your token from: https://readwise.io/access_token
Setup
Install the required dependencies before using the scripts:
pip install -r scripts/requirements.txt
Common Workflows
List documents in a folder
python scripts/list_documents.py --location later --limit 10
Save a URL with tags
echo '{"url": "https://example.com/article", "tags": ["important"]}' | python scripts/create_document.py
Archive a document
echo '{"id": "doc-id", "location": "archive"}' | python scripts/update_document.py
Bulk archive multiple documents
echo '{"updates": [{"id": "doc1", "location": "archive"}, {"id": "doc2", "location": "archive"}]}' | python scripts/bulk_update_documents.py
Error Handling
| Exit Code | Meaning | Action |
|---|---|---|
| 0 | Success | Parse stdout |
| 1 | API error | Check stderr for details |
| 2 | Auth error | Verify READWISE_ACCESS_TOKEN |
| 3 | Rate limit | Wait and retry |
| 4 | Invalid input | Fix payload/flags |
What ships with it
9 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.
- references/usage-guide.md 14 KB
- scripts/bulk_update_documents.py 6.0 KB runs code
- scripts/create_document.py 5.1 KB runs code
- scripts/delete_document.py 4.3 KB runs code
- scripts/list_documents.py 10.0 KB runs code
- scripts/list_tags.py 6.2 KB runs code
- scripts/requirements.txt 34 B
- scripts/update_document.py 4.7 KB runs code
- scripts/utils.py 8.0 KB runs code
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.
- 2mo ago First seen · 113 lines · 61 tokens per session scan A 7a037defb1d7
reader is a skill published in the GitHub repository xinthink/reader-mcp-server (11 stars, last pushed 7mo ago), licensed MIT. It adds 61 tokens to every session and 748 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
grilling
A guided questioning process for testing a plan, decision, or idea. It maps dependent choices into a tree and asks only the questions that can be answered at each stage.
stay-within-limits
Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.
learn
Runs a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar domain or compiling materials into one reference. Not for quick lookups or single-file reads.
writing-shape
Skill "writing-shape" from vinvcn/mattpocock-skills-zh-CN, covering the loop, grounding, conversational feel, pulling from the pile and format arguments to actually have.
find-journalists
Build a researched, fit-checked journalist list for a specific PR campaign. Prefer Medialyst's asynchronous media-list research workflow when available, with explicit approval before credit spend; otherwise produce a best-effort local list with only publicly listed, source-cited contacts.