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 dmmdea/offload-harness --skill davinci-resolvegit clone --depth 1 https://github.com/dmmdea/offload-harnessWrote 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/dmmdea/offload-harness/davinci-resolve)<a href="https://agentmods.dev/skills/dmmdea/offload-harness/davinci-resolve"><img src="https://agentmods.dev/badge/skills/dmmdea/offload-harness/davinci-resolve/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/dmmdea/offload-harness/davinci-resolve"><img src="https://agentmods.dev/badge/skills/dmmdea/offload-harness/davinci-resolve.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 | $0.00000 | $0.04261 |
| Opus 5.5 | $0.00000 | $0.01704 |
| Sonnet 5.5 | $0.00000 | $0.00852 |
| Haiku 4.5 | $0.00000 | $0.00426 |
Grade A, and why
davinci-resolve 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 13d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DaVinci Resolve
Drive DaVinci Resolve Studio programmatically. Host-aware — check hostname first;
the live Resolve deployment is per-machine and the layers below are NOT interchangeable.
Capability matrix (read this before promising an edit)
| Capability | State |
|---|---|
| Reads: status, projects (+attributes), timelines, clips (video+audio, named timeline), selection, media pool (recursive), render presets, export-spec | VERIFIED live (2026-08-23, editing rig, Studio 21.0.4.5) |
Writes: import, page, create-project, load-project, delete-project, create-timeline, render, smoke |
VERIFIED WORKING 2026-08-31 on the editing rig — smoke --yes --timeout 180 returns SMOKE PASS end-to-end (creates a disposable project, builds a timeline, inserts a generator, RENDERS and verifies the file, deletes the project, restores the editor's project). |
| Spec→timeline build (append-from-spec), Fusion templates | The deployed CLI (build f759aaa29, 2026-08-25) DOES expose build --spec PATH [--fps] [--lut NAME=PATH] taking an edit-spec 1.0.0 — newer than this table's old "NOT BUILT". Untested, and it rides the same write path that is measured broken above, so treat as unusable until writes work. Still: do NOT hand-roll raw fusionscript writes against a live project |
| 21.1 catalog + sidecar (2026-09-09, workstation) | 146 commands VERIFIED live on Studio 21.1.0.14 through resolve_cli.py serve --port 18800: bins/clips/markers/flags/proxies, tracks, items (incl. 21.1 add-transition, set-item --speed/--fade-in, set-item-properties), multicam create/smart-switch/flatten, colour versions/CDL/LUT/DRX/groups/gallery, Fusion tool scripting (Lock/Undo wrapped), render queue/presets/quick-export/verify-render, system presets, transcription readback, validate-dctl. Branch feat/resolve-http-sidecar (PR #5). Reference: reference/09-resolve-21-1.md + 10-sidecar-and-cli.md. archive-project is refused: ArchiveProject crashes Resolve 21.1 from a script. |
Printed CLI davinci-resolve-pp-cli (2026-09-09) |
Promoted to the local printing-press library %USERPROFILE%\printing-press\library\davinci-resolve (build with go build ./cmd/davinci-resolve-pp-cli; NOT published to the public library — never publish without asking). 147 endpoint commands generated 1:1 from the sidecar catalog + 7 hand-authored history commands (runs list/show, marker search, render history, color audit, fusion titles search, timeline log, doctor history). Live dogfood 511/511 against _ref_scratch, shipcheck 7/7, scorecard 93/100. Needs the sidecar on 127.0.0.1:18800 (resolve.cmd serve --port 18800). Details + fixture recipe: reference/10-sidecar-and-cli.md §4–5. |
| Resolve AI via API | Split surface — see video-pipeline/docs/MASTER-PLAN.md §2.3. 21.1: GetTranscription() returns per-word timing (transcribe on media/cut/edit/fairlight; synchronous, ~20 s cold). Harness STT (hotwords) still owns karaoke timing; Resolve's transcript is a real cross-check now. GenerateSpeech needs the AI Speech Generator Extras pack (returns an error STRING without it) |
What ships with it
14 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.
- reference/01-hosts-hardware.md 9.0 KB
- reference/02-connection-transport.md 11 KB
- reference/03-cli-reference.md 6.9 KB
- reference/04-api-reference.md 23 KB
- reference/05-editing-playbook.md 13 KB
- reference/06-render-delivery.md 8.5 KB
- reference/07-fusion-titles-color-audio.md 14 KB
- reference/08-failure-modes.md 12 KB
- reference/09-resolve-21-1.md 18 KB
- reference/10-sidecar-and-cli.md 16 KB
- reference/api-catalog-21.1.md 61 KB
- reference/live-dump-2026-09-01.json 26 KB
- reference/PROVENANCE.md 914 B
- reference/README.md 5.8 KB
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.
- 13d ago Changed 5301a1c43943
- 27d ago First seen · 181 lines · 0 tokens per session scan A a9e0118e3cb3
davinci-resolve is a skill published in the GitHub repository dmmdea/offload-harness (4 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,261 tokens. 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 2026-09-19.
Other skills, from other repositories
gh-skill
Manage agent skills with gh skill. Use this skill to discover, preview, install, update, and publish Agent Skills so an agent can self-manage the skills available in its environment.
printing-press-amend
Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…
printing-press-import
Bring a published CLI from the public library into the internal library so it's identical to a freshly-generated copy — module path reverted, manuscripts placed alongside, ready for /printing-press-polish or /printing-press-emboss. Use when the public library has a CLI you don't have locally, or to recover from a…
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
printing-press-score
Score a generated CLI against the Steinberger bar, compare two CLIs side-by-side.
octo-drive
Octo Drive — spaces, folders, file upload/download, online-document mounts, share links, invites, IM-attachment transfer. Works with a bot token or a user API key; the CLI routes by token kind. Load after octo-shared.