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 skills add Mandrilsquad1441/codex-davinci-resolve-mcp --skill resolve-studiogit clone --depth 1 https://github.com/Mandrilsquad1441/codex-davinci-resolve-mcpWrote 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/skills/mandrilsquad1441/codex-davinci-resolve-mcp/resolve-studio)<a href="https://agentmods.dev/skills/mandrilsquad1441/codex-davinci-resolve-mcp/resolve-studio"><img src="https://agentmods.dev/badge/skills/mandrilsquad1441/codex-davinci-resolve-mcp/resolve-studio/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/skills/mandrilsquad1441/codex-davinci-resolve-mcp/resolve-studio"><img src="https://agentmods.dev/badge/skills/mandrilsquad1441/codex-davinci-resolve-mcp/resolve-studio.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 | $0.00050 | $0.00560 |
| Opus 5 | $0.00025 | $0.00280 |
| Sonnet 5 | $0.00010 | $0.00112 |
| Haiku 4.5 | $0.00005 | $0.00056 |
Grade A, and why
resolve-studio 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 8d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve Studio Control
Operate DaVinci Resolve as a cautious post-production assistant. Use the
resolve-studio-control MCP server for Resolve state and operations; do not
invent results or use arbitrary shell, Python, Lua, or Resolve-method calls.
Operating loop
- Call
resolve_healthfirst. If the bridge is unavailable, report the exact prerequisite instead of guessing. The bridge must stay on127.0.0.1. - Inspect the current project and timeline before changing anything.
- For delivery work, call
resolve_production_preflightwith the requested output specification and output directory. Stop on blockers or unexplained warnings. - Before edits, call
resolve_export_project_backupto create a new.drpbackup. Never overwrite an existing backup. - Call
resolve_duplicate_timelineand make all edits on the versioned revision. Preserve the source timeline. - Save, rerun preflight, configure the requested render, queue it, and poll
resolve_render_statusuntil the job completes or fails. - Call
resolve_verify_mediaon the finished file. Do not call a delivery successful unless codec, dimensions, frame rate, audio, duration, size and the requested checksum checks pass.
Safety rules
- Treat project deletion and other destructive actions as exceptional. Prepare and execute them in separate calls with the same scoped arguments and a fresh confirmation token; never reuse or expose a token.
- Keep media and output paths inside the configured allowlists. Refuse path traversal, symlink escapes, overwrite requests, or output locations that are not explicitly allowed.
- Do not enable Resolve network scripting, bind the bridge to a non-loopback address, or expose the bridge token.
- Do not claim that a render, backup, or timeline export exists until the tool response and the filesystem/media QC both prove it.
- Prefer idempotent, additive operations and explain what will change before executing a consequential edit.
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.
- 8d ago First seen · 51 lines · 50 tokens per session scan A 69b8b47299eb
resolve-studio is a skill published in the GitHub repository Mandrilsquad1441/codex-davinci-resolve-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 560 once invoked, about $0.0003 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 skills, from other repositories
davinci-resolve-cli
Use this skill when the user wants to script DaVinci Resolve from the command line — list/open/save projects, batch-import media, queue or wait on render jobs, list timelines/clips, or add/delete timeline markers. Trigger on mentions of DaVinci Resolve, "render this timeline", "import this footage", "tag clips", or…
wedding-cinematic-reel
Color-match event footage to a hero/reference clip, sync highlight cuts to music beats, and build a four-minute wedding reel.
skill
Skill "skill" from Mun1to/vidorq, covering vidorq skill — edición por ia (v1), flujo, uso, 1) transcribir (word-level, local) and 3) renderizar.
vlog-auto-edit
A workflow that turns raw travel or everyday video clips into a finished vlog, a short edited video built around a person's experiences.
davinci-resolve
Comprehensive operational skill specification for Anthropic Claude to automate, script, troubleshoot, and optimize DaVinci Resolve Studio 19, Python Scripting API, Fusion VFX nodes, ACES/DWG color management, and Deliver batch rendering.
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.