adhx CLAUDE.md

Project instructions for ADHX, a web application that saves and organizes bookmarks from Twitter/X and previews or saves media from several video and social platforms. It also describes local configuration files for personal credentials, test data, and development URLs.

In plain words
What is it for?
Use it when configuring, developing, or testing ADHX and when working with GitHub, Sentry, or local development settings.
Why use it?
It keeps personal settings out of shared project files while giving agents the repository’s product and workflow context.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/itsmemeworks/adhx/claude-md
Clone the repo
git clone --depth 1 https://github.com/itsmemeworks/adhx
Per session 28,572 This file is loaded in full into every session.
When invoked 28,572 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.28572 $0.28572
Opus 5 $0.14286 $0.14286
Sonnet 5 $0.05714 $0.05714
Haiku 4.5 $0.02857 $0.02857

Measured 2d ago against content hash d177f544866c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adhx CLAUDE.md scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

await fetch(url, { signal: AbortSignal.timeout(10_000) })
CLAUDE.md · 1,296 lines

How it starts

The opening of the file, as written. The whole thing — 1,296 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.

Local Configuration

Create ./CLAUDE.local.md for personal settings that won't be committed:

# Example CLAUDE.local.md

## GitHub CLI

Always use the `your-username` account for gh commands.

## Sentry CLI

Use org `your-org` and project `your-project`.

## Personal Notes

- My test user ID: user_abc123
- Local dev URL: http://localhost:3000

Use cases for CLAUDE.local.md:

  • CLI tool credentials (GitHub, Sentry, Fly.io accounts)
  • Personal test data and user IDs
  • Local environment URLs and ports
  • Workflow preferences specific to you
  • Notes that shouldn't affect other contributors

ADHX

Save it. Lose it. Find it.

A Twitter/X bookmark manager for people who bookmark everything and read nothing. Built with Next.js 16. Also previews and saves Instagram image posts/carousels and Reels, TikTok videos, and YouTube Shorts via the same URL-prefix trick (Instagram images and TikTok/Reels offer file send/download; YouTube plays via the official iframe embed).

Agent Context Protocol

This repo carries its own cumulative context so any fresh session — new branch, no conversation history — can self-orient:

  1. At session start, read the most recent entries of docs/WORKLOG.md (append-only, newest first). It records what was done recently, why, what's in flight, and open follow-ups — context that postdates the docs.
  2. After completing substantive work (feature, fix with a lesson, architectural decision, reverted experiment), append a dated entry to docs/WORKLOG.md: what/why/current state/follow-ups, ≤10 lines, newest first. Never rewrite or delete old entries.
  3. If your change makes this file, README.md, or ARCHITECTURE.md inaccurate, update them in the same PR.
  4. Always commit, push, and open/update a PR after substantive work. Do not wait to be asked. Use the GitHub account named in gitignored CLAUDE.local.md. Never merge — the user merges manually. This overrides any global “don't push unless asked” preference.

Read the full file on GitHub · 1,296 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. 2d ago First seen · 1,296 lines · 28,572 tokens per session scan A d177f544866c

Subscribe to this mod's changes

adhx CLAUDE.md is an instructions file published in the GitHub repository itsmemeworks/adhx (16 stars, last pushed 4d ago), licensed MIT. It adds 28,572 tokens to every session, about $0.1429 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

karakeep AGENTS.md

AGENTS.md instructions for karakeep-app/karakeep, covering karakeep project overview, project overview, project structure, applications (apps/) and packages (packages/).

karakeep-app/karakeep · 694 tokens

karakeep CLAUDE.md

Claude Code instructions for karakeep-app/karakeep, a project described as: A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search.

karakeep-app/karakeep · 3 tokens

karakeep GEMINI.md

Gemini CLI instructions for karakeep-app/karakeep, a project described as: A self-hostable bookmark-everything app (links, notes and images) with AI-based automatic tagging and full text search.

karakeep-app/karakeep · 3 tokens

Siftly CLAUDE.md

Instructions for viperrcrypto/Siftly, covering siftly, quick setup, ai authentication — no api key needed, key commands and project structure.

viperrcrypto/Siftly · 1,079 tokens

whatsapp-automation CLAUDE.md

Instructions for sumioshi/whatsapp-automation, covering vocabulário de acompanhamento (desambiguação), recipe do monitor de mensagem (sem zumbi), modo de envio por chat (confirmar vs autônomo), mídia na nuvem (midiapendente) — não é erro and grupo renomeado ≠ chat morto (slug é estável).

sumioshi/whatsapp-automation · 1,548 tokens

next-payload-ai-fluent-starter CLAUDE.md

Claude Code instructions for joshuamartyn/next-payload-ai-fluent-starter, covering read me first, 🔒 critical rule (must follow), 🧰 mcp servers & roles, 📦 task contract (keep work small & shippable) and 🧭 standard work session (do this every time).

joshuamartyn/next-payload-ai-fluent-starter · 1,622 tokens