agentmods.dev

twitter-bookmarks-downloader: Instructions file for Gemini CLI

GEMINI.md

twitter-bookmarks-downloader GEMINI.md is an instructions file for Gemini CLI from 0x1b2c/twitter-bookmarks-downloader. It costs 1,415 tokens per session, scanned A, original, MIT.

Project instructions for a browser script and local Go server that collect Twitter bookmarks and their media into local storage.

In plain words
What is it for?
Use them when developing or maintaining the Twitter bookmark downloader.
Why use it?
They give contributors the architecture, data flow, and commit rules needed to change the project without breaking its sync process.

Instructions file for Gemini CLI

Written for Gemini CLI: the file is GEMINI.md.

This is 0x1b2c/twitter-bookmarks-downloader's own configuration. It tells Gemini CLI how to work on twitter-bookmarks-downloader 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 twitter-bookmarks-downloader configures →

not rated 25repo +1 2mo ago A scan 1,415 tokens original MIT
View source ↗ 0x1b2c/twitter-bookmarks-downloader
Reuse

Borrowing it

Nothing to install: this file belongs to 0x1b2c/twitter-bookmarks-downloader. 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/0x1b2c/twitter-bookmarks-downloader/master/GEMINI.md
Clone the repo
git clone --depth 1 https://github.com/0x1b2c/twitter-bookmarks-downloader

Made for: Gemini CLI.

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 twitter-bookmarks-downloader GEMINI.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/0x1b2c/twitter-bookmarks-downloader/gemini-md/github.svg)](https://agentmods.dev/instructions/0x1b2c/twitter-bookmarks-downloader/gemini-md)
Your own site
<a href="https://agentmods.dev/instructions/0x1b2c/twitter-bookmarks-downloader/gemini-md"><img src="https://agentmods.dev/badge/instructions/0x1b2c/twitter-bookmarks-downloader/gemini-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 twitter-bookmarks-downloader GEMINI.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/0x1b2c/twitter-bookmarks-downloader/gemini-md"><img src="https://agentmods.dev/badge/instructions/0x1b2c/twitter-bookmarks-downloader/gemini-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,415 This file is loaded in full into every session.
When invoked 1,415 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 $0.01415 $0.01415
Opus 5.5 $0.00566 $0.00566
Sonnet 5.5 $0.00283 $0.00283
Haiku 4.5 $0.00142 $0.00142

Measured 2mo ago against content hash d41b7fdb77e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

twitter-bookmarks-downloader GEMINI.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 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.

GEMINI.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TBD (Twitter Bookmarks Depot) - Developer Guide

CRITICAL MANDATES

⚠️ COMMIT MESSAGE RULES (HIGHEST PRIORITY)

  1. NO CONVENTIONAL COMMITS: Absolutely DO NOT use prefixes like feat:, fix:, docs:, chore:, etc.
  2. SIMPLE & DESCRIPTIVE: Use clear, natural language sentences (e.g., "Add MIT license", "Fix parsing bug").
  3. CO-AUTHOR: Always include Co-authored-by: Gemini <[email protected]>.

1. Architecture Overview

This project (TBD) uses a hybrid architecture to safely and reliably sync Twitter bookmarks.

  • Frontend (Userscript): A Tampermonkey script running on https://x.com. It acts as a passive interceptor.
  • Backend (Go): A local HTTP server (:41008) backed by SQLite. It handles data parsing, storage, and media downloading.

Data Flow

  1. User scrolls the Twitter Bookmarks page.
  2. Userscript intercepts the native XMLHttpRequest.
  3. Userscript detects GraphQL responses containing "Bookmarks".
  4. Userscript forwards the raw response text (string) to http://localhost:41008/api/sync-raw using GM_xmlhttpRequest (to bypass CSP).
  5. Go Server parses the complex GraphQL JSON.
  6. Go Server saves metadata to SQLite (bookmarks.db) and checks for duplicates.
  7. Background Worker scans the DB for undownloaded media and downloads them to media/.

2. Key Technical Decisions & "Gotchas"

Frontend (Userscript)

  • Why GM_xmlhttpRequest? Twitter's Content Security Policy (CSP) blocks XHR/Fetch to localhost. GM_xmlhttpRequest operates in the extension context, bypassing this restriction.
  • Why Raw Text Forwarding?
    • Memory/Sandbox Limits: Twitter's GraphQL responses can be huge. Parsing them in the browser or passing large objects across the Tampermonkey sandbox boundary often causes RangeError: Invalid array length or memory crashes.
    • Stability: Sending the raw string shifts the heavy lifting to Go, which handles large memory allocations much better.
  • Hooking Strategy: We hook XMLHttpRequest.prototype.send and listen to the load event. This is more reliable than hooking fetch for capturing the complete response stream without stream locking issues.

Read the full file on GitHub · 89 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. 2mo ago First seen · 89 lines · 1,415 tokens per session scan A d41b7fdb77e4

Subscribe to this mod's changes

twitter-bookmarks-downloader GEMINI.md is an instructions file published in the GitHub repository 0x1b2c/twitter-bookmarks-downloader (25 stars, last pushed 2mo ago), licensed MIT. It adds 1,415 tokens to every session, about $0.0057 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 2026-09-02.

Backend and APIsBrowser automation
Related

twitter-bookmarks-downloader GEMINI.md compared with instructions from other repositories

twitter-bookmarks-downloader GEMINI.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
twitter-bookmarks-downloader GEMINI.md0x1b2c/twitter-bookmarks-downloaderInstructions file252mo agoMITA1,415Gemini CLI
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode