x-bookmarks-pipeline: Instructions file for Claude Code

CLAUDE.md

x-bookmarks-pipeline CLAUDE.md is an instructions file for Claude Code from joemccann/x-bookmarks-pipeline. It costs 1,792 tokens per session, scanned A, original, MIT.

Repository instructions for a Rust program that collects and analyzes X bookmarks, where X is the social network formerly known as Twitter.

In plain words
What is it for?
Use them when building, testing, or modifying the bookmark pipeline, its Rust components, browser login flow, database cache, email notices, or language-model integrations.
Why use it?
They explain the project’s architecture, setup, caching, authentication, notifications, and usage-cost tracking so changes fit the existing design.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; positional $N argument.

This is joemccann/x-bookmarks-pipeline's own configuration. It tells Claude Code how to work on x-bookmarks-pipeline 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 x-bookmarks-pipeline configures →

Reuse

Borrowing it

Nothing to install: this file belongs to joemccann/x-bookmarks-pipeline. 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/joemccann/x-bookmarks-pipeline/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/joemccann/x-bookmarks-pipeline

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 x-bookmarks-pipeline CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/joemccann/x-bookmarks-pipeline/claude-md/github.svg)](https://agentmods.dev/instructions/joemccann/x-bookmarks-pipeline/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/joemccann/x-bookmarks-pipeline/claude-md"><img src="https://agentmods.dev/badge/instructions/joemccann/x-bookmarks-pipeline/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 x-bookmarks-pipeline CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/joemccann/x-bookmarks-pipeline/claude-md"><img src="https://agentmods.dev/badge/instructions/joemccann/x-bookmarks-pipeline/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,792 This file is loaded in full into every session.
When invoked 1,792 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 $0.01792 $0.01792
Opus 5 $0.00896 $0.00896
Sonnet 5 $0.00358 $0.00358
Haiku 4.5 $0.00179 $0.00179

Measured 10d ago against content hash 948678db5c18, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

x-bookmarks-pipeline 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 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.

CLAUDE.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Rust-only architecture

This repository is a Rust implementation of the X bookmark pipeline with shared provider abstractions and a single executable workflow in src/main.rs.

  • llm.rs exposes the shared LLMProvider trait (classify, analyze_image, generate_code) and provider wrappers.
  • cache.rs owns SQLite persistence with shared mutable access using Arc<Mutex<Connection>>.
  • orchestrator.rs coordinates bounded worker parallelism and on_meta_saved side effects.
  • notify.rs implements SmtpNotifier via lettre; one email per cycle listing new bookmarks only.
  • error.rs centralizes PipelineError and conversion of external failures.
  • browser.rs implements CDP auto-consent (connects to existing Chrome via HTTP discovery on port 9222), and closes only the OAuth callback tab after auth by exact redirect URI match.
  • cost.rs tracks per-bookmark LLM token usage and USD costs with per-provider pricing.
  • x_api_cache.rs caches username→user_id mappings, token validation state, and tracks X API request budgets.
  • main.rs handles startup, env loading, provider bootstrap, and CLI dispatch.

Setup

cp .env.example .env
cargo build
cargo test
cargo run -- --help

The binary loads .env from current directory at startup.

Cache Management

# View cache statistics
cargo run -- --cache-stats

# Clear bookmark cache only (keeps output files)
cargo run -- --clear-cache

# Full reset: clear all caches AND delete output files
cargo run -- --reset

The --reset command performs a complete reset:

  1. Clears bookmark cache (SQLite)
  2. Deletes X API cache file (username mappings, request stats)
  3. Recursively deletes all output files (.meta.json, .pine)

Environment

Required API keys:

  • CEREBRAS_API_KEY
  • XAI_API_KEY
  • ANTHROPIC_API_KEY
  • OPENAI_API_KEY

Optional SMTP notifications:

  • SMTP_HOST
  • SMTP_USER
  • SMTP_PASSWORD
  • SMTP_FROM
  • SMTP_TO

Optional runtime tuning:

  • CEREBRAS_MODEL
  • XAI_MODEL
  • ANTHROPIC_MODEL
  • OPENAI_MODEL
  • CACHE_PATH
  • X_API_CACHE_PATH — SQLite cache for X API cost optimization (default: cache/x_api.db)
  • MAX_WORKERS
  • API_TIMEOUT
  • VISION_TIMEOUT
  • FETCH_TIMEOUT
  • XPB_DAEMON / DAEMON_MODE
  • DAEMON_INTERVAL_SECONDS / XPB_DAEMON_INTERVAL_SECONDS — (default: 900s/15min)
  • DAEMON_FETCH_LIMIT — bookmarks per daemon cycle (default: 25)
  • DAEMON_FETCH_PAGES — max pages per daemon cycle (default: 1)
  • DAEMON_MAX_CYCLES / XPB_DAEMON_MAX_CYCLES
  • TOKEN_VALIDATION_CACHE_SECONDS — skip /users/me calls within this window (default: 300s)
  • XPB_CHROME_USER_DATA_DIR — Chrome profile for CDP discovery (defaults to platform default)
  • XPB_CHROME_APP — macOS app name for open -a (e.g. Chrome Debug)

Read the full file on GitHub · 165 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. 10d ago First seen · 165 lines · 1,792 tokens per session scan A 948678db5c18

Subscribe to this mod's changes

x-bookmarks-pipeline CLAUDE.md is an instructions file published in the GitHub repository joemccann/x-bookmarks-pipeline (92 stars, last pushed 13d ago), licensed MIT. It adds 1,792 tokens to every session, about $0.0090 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.

Related

Other instructions, from other repositories

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 · 7,296 tokens

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.

openai/codex · 5,153 tokens

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 · 6,785 tokens

spec-kit AGENTS.md

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.

github/spec-kit · 7,104 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens