wallabag-mcp: Instructions file for Claude Code

CLAUDE.md

wallabag-mcp CLAUDE.md is an instructions file for Claude Code from rusty4444/wallabag-mcp. It costs 666 tokens per session, scanned A, original, MIT.

A project instruction file for a Python MCP server that connects to Wallabag, a read-it-later service, through its REST API. It documents setup, code structure, linting, tests, and the checks used in continuous integration.

In plain words
What is it for?
Use it when changing the Wallabag MCP server to install its development dependencies, run Ruff and pytest, inspect its client and tool layers, or understand its CI checks. Ruff is a Python code-quality checker, and pytest is a Python testing tool.
Why use it?
It tells a coding agent how this repository is organised and how to verify changes instead of relying on generic assumptions. It also separates required checks from optional tests that contact live documentation.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is rusty4444/wallabag-mcp's own configuration. It tells Claude Code how to work on wallabag-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything wallabag-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rusty4444/wallabag-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.

Copy the file
curl -O https://raw.githubusercontent.com/rusty4444/wallabag-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/rusty4444/wallabag-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for wallabag-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rusty4444/wallabag-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/rusty4444/wallabag-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rusty4444/wallabag-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rusty4444/wallabag-mcp/claude-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.

agentmods 80×15 button for wallabag-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rusty4444/wallabag-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rusty4444/wallabag-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 666 This file is loaded in full into every session.
When invoked 666 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00666 $0.00666
Opus 5.5 $0.00266 $0.00266
Sonnet 5.5 $0.00133 $0.00133
Haiku 4.5 $0.00067 $0.00067

Measured 7d ago against content hash 1335a3e149fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wallabag-mcp CLAUDE.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 7d 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.

CLAUDE.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

pip install -e '.[dev]'          # setup
ruff check .                     # lint (line-length 120, rules E,F,I,UP,B,SIM)
pytest                           # tests
pytest tests/test_client.py::test_oauth_token_requested_and_used   # single test
python scripts/live_docs_test.py # optional; hits live wallabag docs

CI (.github/workflows/ci.yml) runs lint, syntax/import smoke checks, and the test suite on Python 3.11–3.14.

scripts/live_docs_test.py and scripts/model_validate.py are optional network checks — neither is part of CI.

Architecture

Three layers, stdio MCP server:

  • client.py — thin httpx wrapper over the wallabag REST API. All config and the OAuth token live in module-level globals, set via configure() (falling back to env vars per-read). There is no client object to pass around; tests must call client.configure(...) in a fixture. _token() does the password grant against /oauth/v2/token and caches the token with a 30s expiry margin. Every failure raises WallabagError.
  • tools.py — register_tools(mcp) defines all ~17 tools inside one function closing over the MCPServer instance. Tools return strings, never structured data, and each wraps its call in except Exception returning f"Error ...: {exc}" so the MCP client sees a message rather than a protocol error.
  • __init__.py — builds the MCPServer singleton at import time, main() reads env vars → configure() → mcp.run(transport="stdio").

Details that bite:

  • _api_path() appends .json to every path (/api/entries.json) — mock URLs in tests must include it.
  • wallabag responses are HAL-ish; _items() unwraps _embedded.items, plain items, or a bare list. Mutating endpoints sometimes return 204/empty, so client functions fall back to re-fetching the entry.
  • Booleans cross the API as 0/1 via _bool_int(); tags are comma-separated strings, not lists.
  • tests/test_protocol.py spawns the server as a subprocess and asserts every tool and every parameter has a non-empty description. New Field(description=...) is mandatory, and the tool count assertion (>= 17) is a floor.

Read the full file on GitHub · 37 lines

Changes

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.

  1. 7d ago First seen · 37 lines · 666 tokens per session scan A 1335a3e149fa

Subscribe to this mod's changes

wallabag-mcp CLAUDE.md is an instructions file published in the GitHub repository rusty4444/wallabag-mcp (3 stars, last pushed 8d ago), licensed MIT. It adds 666 tokens to every session, about $0.0027 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 2026-10-10.

Related

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).

microsoft/vscode · 9,649 tokens

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.

vercel/next.js · 7,257 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,159 tokens