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 voice-of-customergit 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/voice-of-customer)<a href="https://agentmods.dev/skills/cbrock84/headcount/voice-of-customer"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/voice-of-customer/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/voice-of-customer"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/voice-of-customer.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 74 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 | $0.00082 | $0.00839 |
| Opus 5 | $0.00041 | $0.00419 |
| Sonnet 5 | $0.00016 | $0.00168 |
| Haiku 4.5 | $0.00008 | $0.00084 |
Grade A, and why
voice-of-customer 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice of customer
Most feedback programs collect diligently and change nothing. The collection is the easy half; the loop is the whole value.
Sources, weighted honestly
- Support contacts — the highest-volume and least prompted source, and the most under-used. People contacting you have a real problem nobody asked them about. But the sample is strongly self-selected: it excludes everyone who silently churned, worked around the problem, or would never contact you. Treat it as operational evidence to be normalized per active account and triangulated against churn and behavioral data — never as representative of the customer base.
- Churn and loss reasons — the most valuable and most under-sampled. People leaving have no reason to be polite.
- Interviews — depth, small n, best for understanding why something in the data is happening.
- Surveys — breadth, and only meaningful once you know what to ask.
- Public reviews and forums — biased toward extremes, useful for what people say when you are not in the room.
Anything a customer built a workaround for outranks anything they merely said in a survey.
On CSAT and NPS
Both are useful as trends and misleading as targets. The moment a team is measured on a score, the score improves faster than the experience does — asking at the favorable moment, coaching for the rating, excluding difficult segments.
Treat the score as a prompt for the free-text answer, which is where the information is. Segment before concluding: an overall score is an average of experiences that have nothing in common.
Never target a number without also watching the behavior it is supposed to predict.
Turning feedback into change
The failure is not collection, it is triage. Feedback needs:
- Categorization against a stable taxonomy, so volume per cause is countable across periods.
- Quantification. "Several customers mentioned" loses every argument. "Eighty-one contacts this quarter, four percent of active accounts, twelve of them on enterprise plans" wins.
- A named owner per theme, outside the feedback function. A theme owned by the team collecting it goes nowhere.
- A standing review where product, support, and success look at the same list together.
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 Changed · +11 lines caf3ba7f581a
- 12d ago First seen · 66 lines · 82 tokens per session scan A e45e1c232843
voice-of-customer is a skill published in the GitHub repository cbrock84/headcount (1,351 stars, last pushed 8d ago), licensed MIT. It adds 82 tokens to every session and 839 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 2026-08-30.
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.