agentmods.dev

autoclip-ai: Instructions file for Claude Code

CLAUDE.md

autoclip-ai CLAUDE.md is an instructions file for Claude Code from AnirudhGupta007/autoclip-ai. It costs 3,037 tokens per session, scanned A, original, MIT.

Project notes and instructions for an AI video-clipping application. They describe the application's architecture, operating limits, current status, owner decisions, and next steps.

In plain words
What is it for?
Use it as a handoff when working on the AutoClip AI codebase. It covers conversational video clipping, uploads, generated clips, deployment, and planned authentication work.
Why use it?
They give a coding agent the background and constraints needed to continue work without reopening settled decisions. The material is specific to one project rather than a general add-on.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions subagents; positional $N argument.

This is AnirudhGupta007/autoclip-ai's own configuration. It tells Claude Code how to work on autoclip-ai 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 autoclip-ai configures →

not rated 4repo yesterday A scan 3,037 tokens original MIT
View source ↗ AnirudhGupta007/autoclip-ai
Reuse

Borrowing it

Nothing to install: this file belongs to AnirudhGupta007/autoclip-ai. 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/AnirudhGupta007/autoclip-ai/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AnirudhGupta007/autoclip-ai

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 autoclip-ai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/anirudhgupta007/autoclip-ai/claude-md/github.svg)](https://agentmods.dev/instructions/anirudhgupta007/autoclip-ai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/anirudhgupta007/autoclip-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/anirudhgupta007/autoclip-ai/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 autoclip-ai CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/anirudhgupta007/autoclip-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/anirudhgupta007/autoclip-ai/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,037 This file is loaded in full into every session.
When invoked 3,037 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.03037 $0.03037
Opus 5.5 $0.01215 $0.01215
Sonnet 5.5 $0.00607 $0.00607
Haiku 4.5 $0.00304 $0.00304

Measured today against content hash 1f933317b705, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

autoclip-ai 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 today.

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.

`rtk proxy curl …` when you need raw JSON from curl.
CLAUDE.md · 176 lines

How it starts

The opening of the file, as written. The whole thing — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoClip AI — notes for Claude

Read this first. It's the handoff between sessions: what the project is, the rules the owner set, where the work stands, and what to do next.

What this is

Conversational video clipping: upload a long video, chat ("4 funny 30s clips, 9:16"), a LangGraph deep agent finds moments and renders captioned, reframed clips. FastAPI + LangGraph/deepagents + LlamaIndex/pgvector + Redis + React/Vite/Tailwind/react-three-fiber, Docker Compose, deployed on one EC2 box. See README.md (architecture, API, env vars), DEPLOY.md, EVALUATION.md, BENCHMARKS.md.

Owner's rules (don't re-litigate)

  • Portfolio project, nothing more. Keep scope small; build the bare minimum first.
  • Limits: 300 MB / 60 min per upload, for everyone (admins too, via VIDEO_MINUTES_CAP_ADMINS=1). Audio uploads (mp3/m4a/wav/aac/ogg/flac) are supported and become audiograms. No 3-hour support, no email verification, no extra admin features.
  • Google sign-in is WANTED (replaces the old "no OAuth" rule). Plan: free hostname 15-206-112-113.sslip.io (Let's Encrypt cert via the existing acme.sh), authlib code flow + PKCE, google_sub column, issue the existing session cookie. Not built yet — do it together with the owner, who creates the OAuth client in Google Cloud (redirect https://15-206-112-113.sslip.io/api/auth/google/callback, scopes openid email profile). Fallback hostname: a free autoclip.is-a.dev. Email/password and the demo stay.
  • OpenRouter for every model call. No Groq/Whisper/other providers.
  • Spend nothing without asking: no domain, no disk resize, no new paid services. Paid OpenRouter runs only above a $10 balance, with --budget-usd. Unit tests mock every LLM call.
  • Landing page: keep the existing motion (3D FilmScene scroll) and fonts (Plus Jakarta Sans + Inter). Palette is now 2+1: obsidian black, platinum, gold as the accent only.
  • Never push or merge to master without explicit approval — a push to master auto-deploys to production (.github/workflows/deploy.yml). Work on branch portfolio-overhaul. Don't touch the prod server, AWS resources or GitHub settings without the owner.
  • No Co-Authored-By: Claude trailers in commits, no Claude footer in PRs.
  • Wild Target (copyrighted film) is eval-only. Never commit its footage, transcript or dialogue quotes; never show it publicly. reports/ is gitignored for that reason. The public demo/landing uses the CC BY Doctorow talk.
  • The owner likes work split across parallel Opus sub-agents with strict file ownership, then integrated and reviewed by the main session.

Read the full file on GitHub · 176 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. today First seen · 176 lines · 3,037 tokens per session scan A 1f933317b705

Subscribe to this mod's changes

autoclip-ai CLAUDE.md is an instructions file published in the GitHub repository AnirudhGupta007/autoclip-ai (4 stars, last pushed yesterday), licensed MIT. It adds 3,037 tokens to every session, about $0.0121 per session on Opus 5.5. 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 2026-11-13.

ai-agentsfastapigeminilanggraphmultimodal-ai
Related

autoclip-ai CLAUDE.md compared with instructions from other repositories

autoclip-ai CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
autoclip-ai CLAUDE.mdAnirudhGupta007/autoclip-aiInstructions file4yesterdayMITA3,037Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file280k2d agoMITA4,325Codex, OpenCode