OpenChatCutSAFE
Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.
Overview
Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.
f9f0498ec41dOBSERVED · 2026-10-20Install
Commands as the repository documents them. They are shown, not run.
npx skills add 0xsline/OpenChatCut --skill openchatcut
claude mcp add --transport http \
npx skills add 0xsline/OpenChatCut --skill openchatcut
Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned | |
| codex | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: openchatcut description: Connect an MCP-capable coding agent to OpenChatCut and edit local video projects. Use when the user asks to install, connect, or set up OpenChatCut; inspect or edit an OpenChatCut project; work with its timeline, transcript, captions, media, generation, motion graphics, audio, color, or export tools; or recover from an OpenChatCut MCP error. --- # OpenChatCut OpenChatCut is a local-first, agent-native video editor. This skill is the single external entry point; specialized editing guidance remains inside the running editor and is loaded on demand with `load_skill`. ## Route the task - Install, connect, or diagnose the MCP server: read `references/getting-started.md`. - Inspect or modify a project: read `references/editing-workflow.md`. - Recover from a failed tool call, stale session, or missing editor: read `references/known-errors.md`. ## Essentials 1. Start OpenChatCut before connecting. The default MCP endpoint is `http://localhost:5199/api/external-mcp/mcp`. 2. Call `openchatcut_status`, then `list_projects`. Select a project only when the user names it or the current context identifies it. 3. Call `load_skill` before specialized work. It is read-only and requires neither `begin_edit_session` nor `editSessionId`; available names and support files come from the live MCP tool description. With progressive exposure enabled, this call reveals the skill's referenced tools and emits `tools/list_changed`; refresh the list before continuing. 4. Before project reads or edits, call `begin_edit_session`. Keep its `editSessionId` and pass it to every draft-safe editor tool. 5. Set `reuseExisting: true` on `begin_edit_session` to reuse your active draft or adopt an unchanged orphan. Existing operations and approval mode are kept. If reuse is rejected, call `list_edit_sessions`. Use `recover_edit_session` only with a listed `recoveryActions` value; another online owner must finish or discard its own session. 6. Use `approvalMode: "manual"` unless the user explicitly asks for unattended application. In manual mode, the user approves the complete proposal in OpenChatCut. In auto mode, `review_edit_session` applies the complete draft. 7. Finish with `review_edit_session`. Report success only after `get_edit_session` returns `applied`. ## Skill version `2026-09-04.1` The OpenChatCut MCP server announces its required skill baseline. If the server baseline is newer, run: ```bash npx skills update openchatcut ``` Fallback command: ```bash npx skills add 0xsline/OpenChatCut --skill openchatcut ```
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
f9f0498ec41dfull audit observations/trust-audit/skill/0xsline__openchatcut.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-20 | f9f0498ec41d | SAFE | B | 89 | first audit |
Questions
What does the OpenChatCut skill do?
Open-source, local-first conversational AI video editor with a professional multi-track timeline, Agent Skills, MCP integration, and Remotion rendering.
Is OpenChatCut safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can OpenChatCut access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does OpenChatCut work with?
Its documentation mentions claude-code and codex. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (f9f0498ec41d), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.
Add this badge to your README
Shows this page's audit result and links back to it. It updates when the audit does.
[](https://modelsatlas.com/skills/0xsline/openchatcut/)
Not your listing, or something out of date? Claim or update your listing.