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 agentmods add skills/cbrock84/headcount/video-contentnpx skills add cbrock84/headcount --skill video-contentgit 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/video-content)<a href="https://agentmods.dev/skills/cbrock84/headcount/video-content"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/video-content.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 | $0.00089 | $0.00851 |
| Opus 5 | $0.00044 | $0.00426 |
| Sonnet 5 | $0.00018 | $0.00170 |
| Haiku 4.5 | $0.00009 | $0.00085 |
Grade A, and why
video-content 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 yesterday.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video content
This covers video as a format across platforms — short-form, long-form, and the packaging that
decides whether either gets watched. youtube-producer covers one platform in depth: channel
strategy, idea selection against a channel's history, and retention teardowns against YouTube's
own curves. When the question is about a channel rather than a video, it belongs there.
Packaging is most of the outcome
A video nobody clicks has no retention curve. Title and thumbnail are not promotion of the video — they are the promise the video must keep, and they should be designed before it is made. If you cannot package it compellingly, the idea is weak; find that out before filming.
Titles — specific over clever. Curiosity that a real answer resolves, not a withheld one. Front-load the distinguishing word, since titles truncate.
Thumbnails — one subject, readable at thumbnail size on a phone. High contrast. Text under about four words, or none. Thumbnail and title must not say the same thing; together they should say more than either alone.
Openings
The first fifteen seconds decide the rest. Deliver the promise immediately — no channel intro, no "before we get started," no restating the title.
Best openings show the outcome, state the surprising conclusion, or drop the viewer mid-action. Then say what the video will cover, briefly, so they know the shape of the commitment.
Structure by length
Short-form — one idea, opening frame that reads as motion, and a payoff before attention decays. No setup. The loop matters: end where the beginning makes sense again.
Long-form — chapters that each work standalone, with an explicit reason to continue at every seam. Retention is lost at transitions, not in the middle of sections. Vary pace deliberately; a uniformly intense video is as tiring as a flat one.
Diagnosing underperformance
- Low click-through — packaging problem. Title and thumbnail, not content.
- High click-through, early drop — the opening did not pay the promise. Or the promise was unpayable.
- Steady mid-video decline — normal. Look at the slope against your own baseline, not absolutes.
- Sharp mid-video cliff — find the timestamp and watch it. It is almost always a transition, a tangent, or a sponsor read placed badly.
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.
- yesterday First seen · 74 lines · 89 tokens per session scan A 8f2280e402f5
video-content is a skill published in the GitHub repository cbrock84/headcount (1,247 stars, last pushed 2d ago), licensed MIT. It adds 89 tokens to every session and 851 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.
dns
This skill should be used when the user asks about "DNS", "domain resolution", "GeoDNS / geo routing", "latency-based routing", "weighted / failover routing", "Route 53 / Cloud DNS", an "A/CNAME/ALIAS record", "anycast", or "DNS TTL / propagation". It gives the global front door that maps a name to the right IP and…