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 Poechant/davinci-resolve-cli --skill davinci-resolve-cligit clone --depth 1 https://github.com/Poechant/davinci-resolve-cliWrote 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/poechant/davinci-resolve-cli/davinci-resolve-cli)<a href="https://agentmods.dev/skills/poechant/davinci-resolve-cli/davinci-resolve-cli"><img src="https://agentmods.dev/badge/skills/poechant/davinci-resolve-cli/davinci-resolve-cli/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/poechant/davinci-resolve-cli/davinci-resolve-cli"><img src="https://agentmods.dev/badge/skills/poechant/davinci-resolve-cli/davinci-resolve-cli.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 | $0.00100 | $0.01312 |
| Opus 5.5 | $0.00040 | $0.00525 |
| Sonnet 5.5 | $0.00020 | $0.00262 |
| Haiku 4.5 | $0.00010 | $0.00131 |
Grade A, and why
davinci-resolve-cli 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 1mo 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
davinci-resolve-cli (dvr) — Skill
dvr is a CLI for DaVinci Resolve 18+. It bridges into a running Resolve via
DaVinciResolveScript and exposes a structured, JSON-by-default command surface
optimized for AI agents. Always pass --format json when invoking from a
non-TTY context so the output is parseable.
Preflight
Before any action, verify the bridge is healthy:
dvr doctor --format json
Expected: bridgeStatus == "ok". If not, surface the issues[] array to the
user and stop — Resolve must be launched manually.
Command Map
| Domain | Commands |
|---|---|
| Environment | dvr doctor |
| Project | project list / open / new / close / save / export / import / current |
| Media | media import / list / tag |
| Render | render presets / submit / status / list / wait / cancel |
| Timeline | timeline list / current / open / new / clips / marker add/delete/list |
All commands accept --format json|yaml|table (default: JSON for non-TTY).
All mutating timeline commands accept --dry-run.
Error Contract
Errors are emitted to stderr as JSON {"errorCode": "...", "message": "...", "hint": "..."}.
Exit code 0 = success, 1 = user error, 2 = Resolve not reachable, 3 = Resolve API failure.
Common errorCode values: resolve_not_running, version_unsupported,
api_unavailable, validation_error, not_found, api_call_failed.
Example Tasks
1. Render the current timeline as 1080p H.264
# Preflight
dvr doctor --format json | jq -e '.bridgeStatus == "ok"' >/dev/null
# Pick a preset and submit (async — returns immediately)
PRESET=$(dvr render presets --format json | jq -r '.[] | select(test("H\\.264"; "i"))' | head -1)
SUBMIT=$(dvr render submit \
--preset "$PRESET" \
--timeline cur \
--output ~/Renders/out.mp4 \
--start \
--format json)
JOB=$(echo "$SUBMIT" | jq -r .jobId)
# Block until done; progress is on stderr (safe to ignore from agents)
dvr render wait "$JOB" --format json
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 144 lines · 100 tokens per session scan A d8f492d8739d
davinci-resolve-cli is a skill published in the GitHub repository Poechant/davinci-resolve-cli (53 stars, last pushed 5mo ago), licensed MIT. It adds 100 tokens to every session and 1,312 once invoked, about $0.0004 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 skills, from other repositories
davinci-resolve
Automate DaVinci Resolve media and timelines with its scripting API, build Fusion workflows, and configure render jobs.
resolve-studio
Use when the user wants Codex to inspect, edit, version, render, or quality-check a DaVinci Resolve project through Resolve Studio Control. Keep the workflow local-first, preflighted, auditable, and safe.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.