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 unit-economicsgit 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/unit-economics)<a href="https://agentmods.dev/skills/cbrock84/headcount/unit-economics"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/unit-economics/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/unit-economics"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/unit-economics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 50 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00078 | $0.00674 |
| Opus 5.5 | $0.00031 | $0.00270 |
| Sonnet 5.5 | $0.00016 | $0.00135 |
| Haiku 4.5 | $0.00008 | $0.00067 |
Grade A, and why
unit-economics 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 1mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unit economics
The question is simple and usually unanswered: does one more customer make the business better off, and how long does that take?
Build it in this order
- Define the unit. A customer, an account, a seat, an order. State it, because most disagreements about unit economics are disagreements about the unit.
- Contribution margin — revenue per unit minus the costs that vary with it. Include everything that actually varies: payment processing, hosting attributable to usage, support load, delivery, third-party fees. Understating variable cost is the single most common error and it flatters everything downstream.
- Acquisition cost — fully loaded. All sales and marketing spend, including salaries, divided by customers acquired in the same period. Excluding people costs is the second most common error and typically understates by half or more.
- Payback period — acquisition cost divided by monthly contribution. This is the number that governs how fast you can grow without financing it.
- Lifetime value — contribution × expected lifetime, from observed retention. Not from a churn-rate assumption chosen because it produces a good ratio.
Read it honestly
- Ratios hide the constraint. A healthy lifetime-value ratio with a long payback still means growth consumes cash faster than it produces it. Payback governs the growth rate; the ratio governs whether it is worth doing at all.
- Segment before concluding. Blended economics almost always conceal one segment subsidizing another. The average is the least useful number.
- Use cohorts, not averages. Retention improves or decays over time, and blended figures mask which. If early cohorts retain better than recent ones, the business is deteriorating while the average looks stable.
- Do not extrapolate lifetime beyond your data. A twelve-month-old company cannot observe a three-year lifetime, and assuming one is how unprofitable businesses appear profitable.
What ships with it
1 file 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.
- 1mo ago Changed · +7 lines eac0b3d1d0c4
- 1mo ago First seen · 51 lines · 78 tokens per session scan A d46aa16467a5
unit-economics is a skill published in the GitHub repository cbrock84/headcount (2,065 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 674 once invoked, about $0.0003 per session on Opus 5.5. 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
launch-google-search
Launch a complete Google Ads Search campaign — campaign, ad group, responsive search ads, keywords, sitelinks, callouts, and negatives — built paused and ready to review. Use when the user wants to spin up a new Search campaign on Google Ads.
negative-keyword-sweep
Find wasted spend in Google Ads search terms and add negatives at the right scope (account list, campaign, or ad group). Use when the user says "find junk keywords", "stop wasting on bad searches", or wants a search-terms cleanup.
rotate-creative
Pause fatigued ads and ship fresh creative variants in their place. Works on both Meta and Google Ads. Use when CTR is dropping, frequency is climbing, or the user says "creative is tired" / "let's refresh ads". Always starts new variants paused.
spend-audit
Audits a Webshare account for wasted proxy spend and recommends plan adjustments based on the account's own historical usage, using the webshare CLI. Use periodically (e.g. monthly) or whenever asked to review proxy costs, find savings, cut spend, or right-size plans. Strictly read-only — it recommends, it never…
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.
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.