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.
npx agentmods add instructions/sho0pi/doomscroll-mcp/claude-mdgit clone --depth 1 https://github.com/Sho0pi/doomscroll-mcpWrote 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/sho0pi/doomscroll-mcp/claude-md)<a href="https://agentmods.dev/instructions/sho0pi/doomscroll-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sho0pi/doomscroll-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.01423 | $0.01423 |
| Opus 5 | $0.00711 | $0.00711 |
| Sonnet 5 | $0.00285 | $0.00285 |
| Haiku 4.5 | $0.00142 | $0.00142 |
Grade A, and why
doomscroll-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 5d 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 — 115 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.
Status
Pre-implementation. Repo currently holds only README.md (design spec) and LICENSE. No source code, tests, or build config exist yet. The README is the authoritative design — implement against it.
What This Is
An MCP server exposing Instagram Reels browsing to AI agents. The MCP collects and returns structured reel data only; it performs no analysis, ranking, or recommendation. Those are the agent's job.
Pipeline: AI Agent → DoomScroll MCP → Playwright → Instagram Web
Stack
- Python, managed with
uv(dependency install + execution) - MCP (server framework)
- Playwright (browser automation against Instagram web)
Intended Tool Surface (from README)
login(),login_status(),logout()— auth lifecyclescroll_reels(limit=50, search=None, hashtag=None)— drives default feed, keyword search, or hashtag page; returns list of reel dicts (url, creator, caption, likes, comments, date_posted, audio, etc.)
Humanization
To reduce bot-detection risk, browsing behavior must be randomized via a HumanizeConfig.
Passive (core, always on, no account side effects):
- randomized delay between scrolls (range, not fixed)
- variable scroll distance/speed, occasional scroll-up
- random "watch" pause per reel before advancing
- jittered mouse movement, viewport randomization
- per-session reel cap + cooldown before next session
Active (opt-in, OFF by default — mutates the user's account):
- liking reels. This is real engagement: visible to creators, pollutes the user's algorithm, and is a primary IG spam-detection trigger. Gate behind an explicit flag, keep probability low, rate-limit hard, and never perform silently.
class HumanizeConfig:
scroll_delay_range: tuple = (2.0, 6.0) # seconds
watch_duration_range: tuple = (1.0, 5.0)
scroll_jitter: bool = True
session_max_reels: int = 200
cooldown_after_session: float = 0
# active — opt-in, risky
enable_likes: bool = False
like_probability: float = 0.0 # 0..1
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.
- 5d ago First seen · 115 lines · 1,423 tokens per session scan A e5199e2a72d6
doomscroll-mcp CLAUDE.md is an instructions file published in the GitHub repository Sho0pi/doomscroll-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,423 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 2026-08-31.
Other instructions, from other repositories
Browser4 CLAUDE.md
Claude Code instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
cc-websearch CLAUDE.md
Claude Code instructions for Djarvur/cc-websearch, covering project, constraints, technology stack, what not to add and conventions.
fix-quera AGENTS.md
Instructions for AlirezaKeshavarz83/fix-quera, covering agent guidance, project shape, visual style, quera page data findings and compatibility findings.
sniff AGENTS.md
AGENTS.md instructions for Aboudjem/sniff, covering agents.md: sniff, what this repo is, how an agent should use sniff, handling the playwright setup gate and finding output schema.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.
sendblue-browser-use AGENTS.md
Instructions for sendblue-api/sendblue-browser-use, covering agents.md — sendblue-browser-use, what this repo is, setup, common commands and health (no auth).