Borrowing it
Nothing to install: this file belongs to vaxastudio/frameio-agent. 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/vaxastudio/frameio-agent/main/AGENTS.mdgit clone --depth 1 https://github.com/vaxastudio/frameio-agentWrote 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/vaxastudio/frameio-agent/agents-md)<a href="https://agentmods.dev/instructions/vaxastudio/frameio-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/vaxastudio/frameio-agent/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 | $0.02376 | $0.02376 |
| Opus 5 | $0.01188 | $0.01188 |
| Sonnet 5 | $0.00475 | $0.00475 |
| Haiku 4.5 | $0.00238 | $0.00238 |
Grade A, and why
frameio-agent 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frame.io Agent — Agent Instructions
You are helping the user run Frame.io from this local repo.
Allowed operations
Read (no confirmation needed):
auth login,auth status,verifyprojects— list accounts / workspaces / projectslatest— newest assets in a project (recency-first)search "<query>"— account-wide search (lexical or--nlpfor natural language)comments <file_id>— normalized review notes (text + timecode + author + thread)brief --project <id>— one-paragraph project status
Vision (read-only; local file writes only):
frames pull --project|--folder <id> --out <dir>— download one preview frame per clip +manifest.jsonmapping images to file_ids. Then YOU (the agent) Read the images, judge them, and drive the next command. The CLI never judges images.contact-sheet --project|--folder <id> --out X.png— PIL composite of thumbnails.--from-manifest <dir>builds offline from a frames-pull output;--only/--excludefilter by file_id;--indexnumbers tiles + writes<out>.index.json.
Write (every one is confirmation-gated):
share create [file_ids...] --name "..."— bundle assets into a review share. Optional--reviewers [email protected],[email protected]adds email recipients.refs add <source> --folder <id>— upload a local file, trigger a remote_upload from a direct URL, or yt-dlp from a streaming platform.
For every mutation:
- Always show the confirmation summary the CLI prints, then wait for the user's y/N before sending.
- Only pass
--yeswhen the user has explicitly authorized the specific action in the current conversation. Authorization to "send the director a link" once is not standing authorization for future shares or uploads. - Pre-fill flags from what the user said; never invent recipients, expirations, passwords, target folders, or source URLs.
- Echo the visibility / mode plainly in your readout: "public link, anyone with the URL will be able to view" / "yt-dlp will download to a temp file before uploading" / "no downloads allowed."
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 · 123 lines · 2,376 tokens per session scan A 765d86420fe0
frameio-agent AGENTS.md is an instructions file published in the GitHub repository vaxastudio/frameio-agent (2 stars, last pushed 2mo ago), licensed MIT. It adds 2,376 tokens to every session, about $0.0119 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
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).
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.
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.