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/yfge/ai-video-studio/agents-mdgit clone --depth 1 https://github.com/yfge/ai-video-studioWrote 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/yfge/ai-video-studio/agents-md)<a href="https://agentmods.dev/instructions/yfge/ai-video-studio/agents-md"><img src="https://agentmods.dev/badge/instructions/yfge/ai-video-studio/agents-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 | $0.01428 | $0.01428 |
| Opus 5 | $0.00714 | $0.00714 |
| Sonnet 5 | $0.00286 | $0.00286 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
ai-video-studio AGENTS.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 6d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents Guidance for ai-video-studio
This file is the lightweight entrypoint for every coding agent working in this repository. Treat it as the table of contents, not the encyclopedia. Detailed policy lives in the linked docs under docs/.
Instruction Order
- Follow: system / developer -> user ->
AGENTS.md-> linked repository docs. - Keep
CLAUDE.mdandGEMINI.mdas exact mirrors or symlinks to this file. - Keep real rules in the repository. Do not treat chat history, ad-hoc notes, or personal memory as source of truth.
Repository Mission
ai-video-studio is an AI production platform with:
ai-pic-backend/: FastAPI, SQLAlchemy, Alembic, Celery, provider integrations.ai-pic-frontend/: Next.js 16 App Router operator workflows.scripts/: repository automation, harness CLIs, and enforcement checks.tasks.md: the canonical product task board. Do not create or revivetask.md.
Agent System Of Record
Start here, then read only the docs needed for the task:
- ARCHITECTURE.md: system layout, dependency direction, choke points.
- FRONTEND.md: frontend structure rules and harness notes.
- RELIABILITY.md: harness runtime modes, browser evidence, trace policy.
- SECURITY.md: security and secret-handling constraints.
- docs/README.md: full docs index.
- docs/architecture/contracts.md: repo contracts, audit outputs, choke-point policy.
- docs/architecture/file-size-limits.md: file-size and layering limits.
- docs/architecture/testing-policy.md: validation matrix and minimum gates.
- docs/architecture/agent-workflow.md: ledger, commit discipline, browser validation recording.
- docs/generated/db-schema.md: current schema snapshot.
docs/exec-plans/active/anddocs/exec-plans/completed/: tracked execution plans.
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.
- 6d ago First seen · 107 lines · 1,428 tokens per session scan A c0715e1d58f3
ai-video-studio AGENTS.md is an instructions file published in the GitHub repository yfge/ai-video-studio (60 stars, last pushed 1mo ago), licensed MIT. It adds 1,428 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 2026-08-30.
Other instructions, from other repositories
Buildable CLAUDE.md
Claude Code instructions for BihanBanerjee/Buildable, covering claude.md, project overview, commands, backend and frontend.
full-stack-ai-agent-template CLAUDE.md
Claude Code instructions for vstorm-co/full-stack-ai-agent-template, covering claude.md, project overview, commands, install dependencies and run tests.
full-stack-ai-agent-template AGENTS.md
AGENTS.md instructions for vstorm-co/full-stack-ai-agent-template, covering agents.md, project overview, commands, cli and architecture.
tracecat AGENTS.md
AGENTS.md instructions for TracecatHQ/tracecat, covering tracecat agent notes, path-specific notes, repo map, fargate deployment notes and setup and verification.
fullstack-starter AGENTS.md
AGENTS.md instructions for first-fluke/fullstack-starter, covering oh-my-agent, architecture, per-agent dispatch, code search and workflows.
fullstack-starter CLAUDE.md
Claude Code instructions for first-fluke/fullstack-starter, covering oh-my-agent, architecture, per-agent dispatch, code search and workflows.