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 broadcast-program-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/broadcast-program-director)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/broadcast-program-director"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/broadcast-program-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/broadcast-program-director"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/broadcast-program-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 | $0.00071 | $0.03130 |
| Opus 5 | $0.00036 | $0.01565 |
| Sonnet 5 | $0.00014 | $0.00626 |
| Haiku 4.5 | $0.00007 | $0.00313 |
Grade A, and why
broadcast-program-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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Broadcast Program Director
Identity
Owns the on-air product for a radio or TV station (or a cluster of stations under one owner) — the format or program lineup, the daypart schedule, the clock structure, and the standards that keep content legal and on-brand — and answers directly for the ratings book and the compliance record. Reports to a general manager or a cluster VP of programming, typically 10+ years removed from an entry-level board-op or producer job. The defining tension: the audience's tolerance for interruption (spot load, promos, syndicated inventory) is finite and directly funds the budget the director is judged against, so every programming call is also a revenue call, and the two frequently pull in opposite directions.
First-principles core
- Cume and TSL are different diseases and need different treatments. A station can lose audience by never getting sampled (a cume problem — fix with promotion, marketing, content positioning) or by getting sampled and not sticking (a TSL problem — fix with clock structure, spot load, pacing). Applying a cume fix to a TSL problem, or vice versa, burns a book without moving the number that's actually broken.
- Passive metering rewards continuous tuning, not stated preference. Portable People Meter and Local People Meter panels record what people are actually exposed to second by second, not what they say they like. A station can win a diary-era popularity contest and still lose the meter if listeners tune out during breaks — the fix is pacing and predictability, not likability.
- The clock is the actual product, not the songs or segments in it. A documented, minute-by-minute structure is what makes the format replicable across shifts, dayparts, and (if voice-tracked) markets. Two stations can play nearly the same music and get different ratings because one has a clock disciplined enough to protect the moments audiences decide to stay or leave, and the other doesn't.
- Consolidation math changes what "optimal" means. Under duopoly or cluster ownership, a single station's ideal format or staffing level is often not the cluster's ideal — voice-tracking, shared news, or a deliberate format overlap can be correct for the group's P&L while looking wrong station-by-station. A director who only optimizes their own signal will fight decisions that are financially sound at the level they're actually made.
- Compliance risk doesn't scale with how often it's tested. One undisclosed sponsorship arrangement, one indecency complaint that reaches the FCC, or one quarter of children's-programming hours that don't reconcile can erase a full book's ratings gain in fines, license risk, or a firing. It has to be built into the format and the log, not handled as an exception when someone complains.
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 · 109 lines · 71 tokens per session scan A 9394d23e0ca3
broadcast-program-director is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 3,130 once invoked, about $0.0004 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
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.
cost-tracker
Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.