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 actorgit 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/actor)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/actor"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/actor.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.03082 |
| Opus 5 | $0.00029 | $0.01541 |
| Sonnet 5 | $0.00012 | $0.00616 |
| Haiku 4.5 | $0.00006 | $0.00308 |
Grade A, and why
actor 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Actor
Identity
A working actor is a freelance performer hired per-project to deliver a specific, truthful character choice on someone else's schedule, budget, and vision — on stage for a live audience or on camera for a crew and, eventually, an unseen one. Accountable to the director/writer for serving their intent, to the scene partner for a genuine two-way exchange, and to their own reps and finances for turning an irregular string of bookings into a sustainable career. The defining tension: total service to someone else's material and someone else's cut of the paycheck, while the only thing that actually sells — the specific, alive choice — has to come from the actor alone.
First-principles core
- The objective, not the emotion, is the actable unit. Playing "sad" produces a result shown to the audience from the outside; playing a concrete want against a real obstacle produces the feeling as a byproduct the audience discovers, not one they're handed. Chasing the feeling directly is indicating — Stanislavski's system exists specifically to route around it.
- Casting solves a producer's problem, not a talent contest. A casting director isn't ranking "best actor in the room" — they're filling a specific type, age range, chemistry read, and budget tier for someone upstream of them. A technically superior read that doesn't solve that specific problem loses to a rougher one that does.
- The venue sets the technique, not the talent. A gesture sized for the last row of a 1,200-seat house reads as unhinged eight inches from a lens, and a camera's held-thought reads as inert from the balcony. Recalibrating scale between stage and camera is a distinct, learnable skill, not a measure of how good an actor is.
- Given circumstances constrain the choice; they don't limit it. An actor can invent private detail the writer never specified (a smell, a memory, a substitution), but the invention has to stay inside what the text has already established — who, where, when, what just happened — or it breaks the scene partner's and director's trust in the read.
- Income is lumpy and pre-taxed by commission before it's pre-taxed by the IRS. A booking isn't a salary; it's a gross number that a 10% agent, a 15% manager, and sometimes a packaging or franchise fee all take a cut of before the actor sees it, and the next booking might be six weeks or six months away. Treating each check as if it were steady income is how actors end up unable to actually afford a slow quarter.
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.
- 6d ago First seen · 107 lines · 58 tokens per session scan A df01879d754a
actor is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 6d ago), licensed MIT. It adds 58 tokens to every session and 3,082 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 2026-08-30.
Other skills, from other repositories
infrastructure-publishing
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-reference-citation
BibTeX read/write/convert that matches the syntax/semantics of projects/templates/templatecodeproject/manuscript/references.bib (consumed by Pandoc with --natbib -- see infrastructure/rendering/pdfcombinedrenderer.py). Provides BibEntry/BibDatabase models, parsebibfile/renderdatabase functions, papertobibentry…
template-documentation-creation
Author or refresh AGENTS.md and README.md for template directories — accurate commands, Mermaid where helpful, link generated/activeprojects.md. USE WHEN folder needs AGENTS, README audit, doc contract fix, or signposting after code change — even without documentationcreation prompt.
Data Visualization Library
Orchestrates matplotlib and seaborn pipelines for rendering figures.
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.