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 customer-researchgit 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/customer-research)<a href="https://agentmods.dev/skills/cbrock84/headcount/customer-research"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/customer-research/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/customer-research"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/customer-research.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 | $0.00079 | $0.00568 |
| Opus 5.5 | $0.00032 | $0.00227 |
| Sonnet 5.5 | $0.00016 | $0.00114 |
| Haiku 4.5 | $0.00008 | $0.00057 |
Grade A, and why
customer-research 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer research
Research earns its cost only if a decision hangs on it. Name that decision before recruiting anyone.
Choose the method by question
- Why did this happen / what do they actually do — interviews. Small n, deep.
- How common is this — survey. Only after interviews have told you what to ask; a survey written from assumptions returns your assumptions.
- Why did we win or lose — win-loss, with losses weighted higher. Losses are where the truth is and are systematically under-sampled.
- Which framing works — message testing against a real choice, not a preference rating.
Interviewing
Ask about the past, not the future. "What did you do last time" is evidence; "would you use this" is politeness.
- Open broad, follow the energy, and go quiet after their first answer — the second one is where the substance is.
- Chase specifics: when, what happened next, what did that cost you, who else was involved.
- Never describe your solution before you have their problem in their words. Once they know what you want to hear, the interview is over.
- Watch for the workaround. Anything someone has built a spreadsheet to survive is a validated problem.
Synthesizing
Code the transcripts before forming a view — findings assembled to support an existing belief will be. For each finding record: the claim, how many independently said it, a verbatim quote, and what would change if it is true. A finding that changes nothing is trivia.
Separate what people said, what they did, and what you inferred. Conflating the three is the most common way research misleads.
Sources
references/sources.md in this skill lists the outside authorities that settle the questions
here — what each one is authoritative for, and what you may do with it. Check them before
answering on anything they cover, and cite what you used. Most are free to read and not free
to reproduce; the use note on each is binding.
Never
- Recruit only happy customers. The sample that answers your email is not your market.
- Lead: "How much would this feature help?" has one answer.
- Present a single interview as a finding.
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 0c7fab661d99
- 1mo ago First seen · 46 lines · 79 tokens per session scan A 2343f67eb3d4
customer-research is a skill published in the GitHub repository cbrock84/headcount (2,077 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 568 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.
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…