headcount is an organization of independently installable Claude Code plugins, each grouping skills for a department such as finance, security, or demand generation. Claude Code users install the departments they need and invoke their skills for specialized work; the catalogue entries are skills and related agent tooling from that organization.
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 cbrock84/headcount --skill youtube-producergit clone --depth 1 https://github.com/cbrock84/headcountWrote 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/cbrock84/headcount/youtube-producer)<a href="https://agentmods.dev/skills/cbrock84/headcount/youtube-producer"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/youtube-producer/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/cbrock84/headcount/youtube-producer"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/youtube-producer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00086 | $0.01057 |
| Opus 5 | $0.00043 | $0.00528 |
| Sonnet 5 | $0.00017 | $0.00211 |
| Haiku 4.5 | $0.00009 | $0.00106 |
Grade A, and why
youtube-producer 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube producer
Package before you produce
Title and thumbnail decide whether a video is watched at all. Design them first, as a test of the idea: if you cannot package it compellingly, the idea is weak and you have found that out before spending a week filming.
Titles. Specific over clever. Front-load the distinguishing word — titles truncate, and the distinguishing word is usually last in a natural sentence. Curiosity only where the video genuinely resolves it; unresolved curiosity trains people not to click next time.
Thumbnails. One subject, readable at phone-thumbnail size. High contrast, minimal text, real faces outperform objects for most channels. Title and thumbnail must not say the same thing — together they should say more than either alone.
Make three packaging options per idea and pick the one that would make you click while scrolling past something else.
Idea selection
The best ideas sit where audience demand, your unusual knowledge, and a packageable hook overlap. Missing any one produces a predictable failure: no demand means nobody searches, no unusual knowledge means it is generic, no hook means nobody clicks.
Check what already exists on the topic. Not to avoid it — a crowded topic proves demand — but to find the angle nobody took.
The first thirty seconds
Deliver the promise immediately. No channel intro, no "before we get started," no restating the title. Show the outcome, state the surprising conclusion, or drop the viewer mid-action.
Then briefly say what the video covers, so the viewer knows the shape of the commitment they are making.
Retention structure
Retention is lost at seams, not in the middle of sections. Every transition needs an explicit reason to continue — an open question, a promised payoff, a stated next step.
- Chapter it. Each section should work standalone and end pointing forward.
- Vary pace deliberately. A uniformly intense video is as tiring as a flat one.
- Front-load value. Withholding the good part until the end optimizes for a viewer who is no longer watching.
- Place sponsor reads after the first payoff, never before it.
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 · 97 lines · 86 tokens per session scan A ad856a50c044
youtube-producer is a skill published in the GitHub repository cbrock84/headcount (1,356 stars, last pushed 9d ago), licensed MIT. It adds 86 tokens to every session and 1,057 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
save
Save durable decisions, findings, plans, and implementation knowledge from the visible Codex conversation into a new or existing NeatContext context. Use only when the user explicitly invokes this skill or asks to preserve the current conversation as reusable context.
mode
Show or set NeatContext routing to auto, ask, or manual for Codex, with an optional default shared with every other NeatContext host. Use only when the user explicitly invokes this skill or clearly asks to change routing behavior.
status
Report the NeatContext context and routing mode active in Codex, including missing-file or stale-routing warnings. Use when the user asks which context is connected or explicitly invokes this skill.
list
List the local NeatContext Contexts available to Codex. Use when the user asks what contexts exist, what can be connected, or explicitly invokes this skill.
build-oxpecker-web-app
Build or modify an Oxpecker web application in idiomatic F#, using endpoint routing, functional EndpointHandler and EndpointMiddleware composition, ASP.NET Core metadata, and focused endpoint tests.
go
Compatibility entry for Visual Stack's former /vstack:go command. Runs the wireframe and UI review tool, now called review. Use only when the user invokes /vstack:go.