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.
curl -O https://raw.githubusercontent.com/0x1b2c/twitter-bookmarks-downloader/master/GEMINI.mdgit clone --depth 1 https://github.com/0x1b2c/twitter-bookmarks-downloaderWrote 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/instructions/0x1b2c/twitter-bookmarks-downloader/gemini-md)<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.
<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>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 | $0.01415 | $0.01415 |
| Opus 5 | $0.00707 | $0.00707 |
| Sonnet 5 | $0.00283 | $0.00283 |
| Haiku 4.5 | $0.00142 | $0.00142 |
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 8d 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 — 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)
- NO CONVENTIONAL COMMITS: Absolutely DO NOT use prefixes like
feat:,fix:,docs:,chore:, etc.- SIMPLE & DESCRIPTIVE: Use clear, natural language sentences (e.g., "Add MIT license", "Fix parsing bug").
- 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
- User scrolls the Twitter Bookmarks page.
- Userscript intercepts the native
XMLHttpRequest. - Userscript detects GraphQL responses containing "Bookmarks".
- Userscript forwards the raw response text (string) to
http://localhost:41008/api/sync-rawusingGM_xmlhttpRequest(to bypass CSP). - Go Server parses the complex GraphQL JSON.
- Go Server saves metadata to SQLite (
bookmarks.db) and checks for duplicates. - 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 tolocalhost.GM_xmlhttpRequestoperates 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 lengthor memory crashes. - Stability: Sending the raw string shifts the heavy lifting to Go, which handles large memory allocations much better.
- 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
- Hooking Strategy: We hook
XMLHttpRequest.prototype.sendand listen to theloadevent. This is more reliable than hookingfetchfor capturing the complete response stream without stream locking issues.
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.
- 8d ago First seen · 89 lines · 1,415 tokens per session scan A d41b7fdb77e4
twitter-bookmarks-downloader GEMINI.md is an instructions file published in the GitHub repository 0x1b2c/twitter-bookmarks-downloader (19 stars, last pushed 20d ago), licensed MIT. It adds 1,415 tokens to every session, about $0.0071 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 2026-09-02.
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.
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.
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).
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.
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).
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.