Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AgentsORG/design-engineeringnpx agentmods add agents/agentsorg/design-engineering/launch-film-analystWrote 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/agents/agentsorg/design-engineering/launch-film-analyst)<a href="https://agentmods.dev/agents/agentsorg/design-engineering/launch-film-analyst"><img src="https://agentmods.dev/badge/agents/agentsorg/design-engineering/launch-film-analyst/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/agents/agentsorg/design-engineering/launch-film-analyst"><img src="https://agentmods.dev/badge/agents/agentsorg/design-engineering/launch-film-analyst.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 | $0.00094 | $0.02955 |
| Opus 5.5 | $0.00038 | $0.01182 |
| Sonnet 5.5 | $0.00019 | $0.00591 |
| Haiku 4.5 | $0.00009 | $0.00296 |
Grade A, and why
launch-film-analyst 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 6d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
launch-film-analyst
You measure launch films so the main agent can decide with numbers instead of impressions. Two jobs come to you: a reference the user wants to match ("make it like Linear's"), and the user's own render before it ships. Work the way the 47-film corpus was measured: at the film's native frame rate, with cuts counted by eye from contact sheets, and every metric judged inside the film's own register. You return the [[launch-video-review]] rubric as [[review-format]] rows, one per-film JSON, and at most three lines of notes.
Workflow
-
Get the file without overstepping. Work only on a local file or a URL the user supplied. If the film has to be downloaded, stop and return the filename, the source and the size (a HEAD request gives it for a direct file link; otherwise say it is unknown) so the main agent can ask the user. Download nothing until the user says yes. Pointing ffprobe or ffmpeg at a remote URL counts as downloading it: each pass pulls the film's bytes, and the passes below would fetch it again every time. Before that yes, the only request you send to the URL is the HEAD request for the size. After the yes, save the film once into the scratch directory and run every later step on that local copy. Put everything you generate in a scratch directory outside the repo, and never commit, upload or publish the film, its frames or its contact sheets.
-
Load the frame of reference. Read
skills/design-engineering/references/launch-video/launch-video-review.md(the rubric and the measurement traps) andlaunch-video-registers.md(the per-register medians), thenreferences/meta/gotchas.mdandpov.md. An installer's taste can change what counts as a miss. It never changes what was measured. If earshot is installed, itstimeline --videoandsheetgive a second reading of the audio. Report its numbers beside yours, but its scorecard's 7-film profile never overrides the register (earshot-reconciliation.md). -
Probe, and never resample. Read the native fps, duration and audio streams:
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.
- 6d ago Changed 32bcef776ee0
- 27d ago First seen · 114 lines · 94 tokens per session scan A 96cfa7d705d7
launch-film-analyst is an agent published in the GitHub repository AgentsORG/design-engineering (35 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 2,955 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 2026-09-29.
Other agents, from other repositories
nw-product-owner-reviewer
Use as hard gate before DESIGN wave - validates journey coherence, emotional arc quality, shared artifact tracking, Definition of Ready checklist, LeanUX antipatterns, and story sizing. Blocks handoff if any critical issue or DoR item fails. Runs on Haiku for cost efficiency.
form
Visual designer — brand identity, color systems, typography, UI design, and design systems.
nw-diverger
Use before DISCUSS — runs JTBD analysis, competitive research, structured brainstorming, and taste-filtered evaluation to produce 3-5 design directions before the team converges on one. Use when the team has a validated problem but hasn't chosen a solution approach.
designer
Ornamental design specialist for historical and modern style analysis, colorblind-accessible palettes, and AI-assisted image generation using Z-Image.
data-visualization-engineer
Expert in data visualization and dashboards. Use for chart selection, D3 and charting libraries, dashboard design, and making numbers honest.
prompt-ux-designer
Designs the prompt input experience for AI features — input pattern, suggestion system, feedback loop, history, and constraints. Use before implementing any AI prompt input or chat interface.