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 referral-programsgit 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/referral-programs)<a href="https://agentmods.dev/skills/cbrock84/headcount/referral-programs"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/referral-programs/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/referral-programs"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/referral-programs.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 | $0.00065 | $0.00703 |
| Opus 5.5 | $0.00026 | $0.00281 |
| Sonnet 5.5 | $0.00013 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
referral-programs 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Referral programs
Qualify the channel first
Referral programs amplify existing word of mouth. They do not create it.
If customers are not already recommending you unprompted, a program will not produce them — it will produce incentive-motivated signups that churn. Check first: is anyone referring today, and what do they say when they do?
Incentive design
- Two-sided beats one-sided in most cases. It gives the referrer something to offer rather than something to gain, which removes the awkwardness that stops most referrals.
- Match the reward to the product's value, not to a round number. Account credit usually outperforms cash, and costs less.
- Reward the outcome you want. Paying on signup buys signups; paying on a retained, activated customer buys customers.
- Cash rewards attract fraud, and fraud scales faster than the program does. Budget for detection before launch, not after.
Mechanics
The referral has to be effortless at the moment of enthusiasm, which means the ask must appear right after a success moment — not in a settings page nobody visits.
- One-click share with pre-written text the referrer can edit.
- A link that works everywhere and survives being pasted into any app.
- Visible status: who was invited, what stage they reached, what has been earned. Ambiguity kills repeat referrals.
- The referred person's experience must be better than a normal signup. Landing them on the generic homepage wastes the introduction.
Fraud control
Self-referral, disposable accounts, and coordinated rings. Minimum viable controls: reward only on a qualifying event well past signup, hold a payout window, deduplicate on payment method and device, and cap per-referrer volume pending review.
Affiliates are a different program
Affiliates are a paid channel with commercial terms, not enthusiastic customers. They need attribution rules, cookie windows, prohibited-methods terms — brand bidding and coupon-site behavior in particular — and monitoring. Run without terms and you will pay commission on customers you already had.
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 19c35cd546cf
- 1mo ago First seen · 63 lines · 65 tokens per session scan A 482da7f81b9e
referral-programs is a skill published in the GitHub repository cbrock84/headcount (2,077 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 703 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
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.
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.
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.
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.
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…