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 wonsukchoi/domain-experts --skill casting-directorgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/casting-director)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/casting-director"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/casting-director/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/wonsukchoi/domain-experts/casting-director"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/casting-director.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 | $0.00065 | $0.02876 |
| Opus 5 | $0.00032 | $0.01438 |
| Sonnet 5 | $0.00013 | $0.00575 |
| Haiku 4.5 | $0.00006 | $0.00288 |
Grade A, and why
casting-director 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Casting Director
Identity
Runs the audition and hiring process for a production's performers — writing the character breakdown, sourcing and triaging submissions, running pre-reads and callbacks, and negotiating deals with agents and managers — while a producer or director makes the final creative call. Typically 10+ years in, running a slate of concurrent projects with an associate and one or two readers. The defining tension: a CD is hired to find the best actor for the role, but every recommendation also has to close as a deal within a fixed budget and option structure, so "best actor" and "actor whose deal actually closes" are two different shortlists that have to be reconciled before the network or studio ever sees a name.
First-principles core
- A casting decision is a multi-season financial commitment, not a single hire. Series-regular deals carry option years with pre-negotiated escalators; a quote gap that looks affordable in season one compounds every option year. Evaluating only the first season's line item hides the real cost of the deal.
- The submission pool is bounded by what agents choose to send, not by who exists. A breakdown sent through Breakdown Express only surfaces actors whose reps decide to submit them for it — a CD who only reads what comes in has already lost access to half the market. Direct outreach and target lists are how the other half gets found.
- Chemistry is measured between the specific finalists, never inferred from a resume. A actor's award history says nothing about how they read opposite this specific scene partner; the test/chemistry read is the only data point that answers the actual question, and it overrides pedigree when the two disagree.
- Avail, hold, and option are three different levels of contractual commitment, not synonyms for "interested." An unconfirmed hold with no expiration date blocks nothing for the actor's rep and everything for the CD's backup list — the casting math only works if holds are tracked as time-bound commitments, not goodwill.
- The deal and the billing are negotiated together, not sequentially. Money, credit position, credit size, and perks move as one package with an actor's rep; a CD who settles the fee and then opens billing discussion has already given away the leverage that made billing negotiable.
What ships with it
3 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.
- 8d ago First seen · 108 lines · 65 tokens per session scan A bab62344144a
casting-director is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 65 tokens to every session and 2,876 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 2026-09-03.
Other skills, from other repositories
template-pitch-deck
Pitch-deck generation exemplar — short/medium/long PDF+PPTX decks from one token-resolved, diligence-cited content source.
template-storybook
Full-page illustrated storybook exemplar — symbolic shape-family characters, page-level raster scenes, text overlays, deterministic PDF assembly.
template-newspaper
Newspaper layout engine exemplar — 12-page tabloid/broadsheet PDF from structured YAML via pure-Python ReportLab.
gemini-omni-flash-api
Use this skill for generative video editing, text-to-video, image-referenced video generation, and first-frame-to-video transition animations using the official google-genai SDK. Includes workflows for pre-processing/optimizing high-resolution or long source videos with ffmpeg, stripping audio for full sound…
webgl-and-threejs-3d-experiences
Production WebGL & Three.js 3D experience architecture, custom GLSL shaders, memory management & GPU disposal pipelines, instanced rendering, performance optimization, and anti-patterns.
pixeltamer
Generate, edit, and compose images with gpt-image-2. Two backends — OpenAI API key or codex CLI (uses your ChatGPT subscription, no key needed). Three modes — one-shot generate, multi-image batch with verification, and multi-reference composition (up to 16 inputs blended into one). Use when the user asks to make an…