Open Edit is an open-source, agent-driven video editing pipeline for creating subtitles, motion graphics, slides, and rendered videos. It is used by people who want coding agents and command-line tools to transcribe, edit, and produce video, with FFmpeg and other listed tools in its workflow. The catalogue entries extend or configure this workflow through instructions, a skill, a setting, and a hook.
Borrowing it
Nothing to install: this file belongs to veedstudio/open-edit. 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/veedstudio/open-edit/main/AGENTS.mdgit clone --depth 1 https://github.com/veedstudio/open-editWrote 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/veedstudio/open-edit/agents-md)<a href="https://agentmods.dev/instructions/veedstudio/open-edit/agents-md"><img src="https://agentmods.dev/badge/instructions/veedstudio/open-edit/agents-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/veedstudio/open-edit/agents-md"><img src="https://agentmods.dev/badge/instructions/veedstudio/open-edit/agents-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 | $0.00927 | $0.00927 |
| Opus 5.5 | $0.00371 | $0.00371 |
| Sonnet 5.5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
open-edit 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 27d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
A map for changing this repo. Making a video is the open-edit skill's job:
.claude/skills/open-edit/SKILL.md is the whole runtime contract, and nothing here is needed to run it.
Layout
.claude/skills/open-edit/: the product skill.SKILL.mdis the default load (setup, tools, the render contract, money, voice);TRANSCRIPTION.md,CUT.md,FABRIC.mdandVEED.mdload only when their situation arises.cli/: the@veedstudio/openedit-clipackage, every command.cli/src/cli.tsregisters them;cli/src/config.tsresolves the machine paths (ffmpeg, ffprobe, WhisperX) and the workspace the CLI writes (runs/, the recorded provider):OPEN_EDIT_ROOT, else the nearest project above the working directory.initinstalls the skill from the package's own tree.cli/src/veed/: the VEED client. Transcription, login, Fabric generation, background removal and the editor hand-off (editor-project.ts: a plan as editor items, and a project read back as a plan) share one login and one stored token. Background removal's default route is free. Its--fastmode andlipsyncuse the VEED login only to host the file, and--falputs the file on fal's own storage; in all three the generation call bills the user's own fal key, never a VEED workspace.cli/src/providers/: the fal client on the user's own key (fal.ts), the asset manifest (assets.ts: records underruns/<key>/assets/records/, so parallel writers never share a file: onerow-*.jsonper plain record, and each fal purchase as a series ofrequest-<id>.<n>.jsonversions of which only the highestnstands, all read together byreadManifest) and the queue ledger (queue-ledger.ts) that keeps an identical request from being bought twice.
Rules
- Authored pages render in Chrome through
openedit render.
Transcription providers
runs/<key>/transcript.json is the only seam: anything that writes that shape is a provider. There is
no default: on a cold start the user chooses (TRANSCRIPTION.md), and the choice is recorded in
$OPEN_EDIT_ROOT/.open-edit-prefs.json by openedit transcribe --record <provider> [--model <id>].
A bare openedit transcribe <video> runs the recorded provider; with none recorded and no --provider, it
refuses to start and says why.
VEED is listed first because it transcribes best, not because it wins ties.
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.
- 27d ago Changed · -154 lines · -3,033 tokens per session d1d1f3b3fbe5
- 1mo ago Changed · -10 lines · -833 tokens per session 9d053d02e829
- 1mo ago Changed · +3 lines · +46 tokens per session 2edbc9591893
- 1mo ago Changed · +4 lines · +99 tokens per session 3f01795a30a4
- 1mo ago Changed · +2 lines · +40 tokens per session b323373fa743
- 1mo ago First seen · 205 lines · 4,608 tokens per session scan A eb0d2a2ce335
open-edit AGENTS.md is an instructions file published in the GitHub repository veedstudio/open-edit (1,732 stars, last pushed 20d ago), licensed Apache-2.0. It adds 927 tokens to every session, about $0.0037 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.