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 support-operationsgit 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/support-operations)<a href="https://agentmods.dev/skills/cbrock84/headcount/support-operations"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/support-operations/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/support-operations"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/support-operations.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 | $0.00077 | $0.00904 |
| Opus 5.5 | $0.00031 | $0.00362 |
| Sonnet 5.5 | $0.00015 | $0.00181 |
| Haiku 4.5 | $0.00008 | $0.00090 |
Grade A, and why
support-operations 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Support operations
Understand demand before designing supply
Categorize a real sample of recent contacts — a few hundred, read individually, not a report. Almost every support operation finds the same shape: a small number of causes generating most of the volume, and most of those are preventable rather than answerable.
That analysis decides everything downstream. Staffing to demand you have not examined means staffing to demand you could have eliminated.
The hierarchy of handling
In order of cost, cheapest first. Push volume up this list rather than getting faster at the bottom:
- Eliminate — fix the product defect or confusing flow generating the contact.
- Deflect — answer it in the interface at the moment of confusion, not in a help center nobody visits.
- Self-serve — findable documentation for people who go looking.
- Automate — genuine resolution of routine requests, not a bot that stalls people before a human.
- Assist — a person.
Most support improvement programs work on level 5 exclusively, because it is the visible one.
Channels
Pick by what the work needs, not by what is fashionable. Asynchronous channels are cheaper and better for anything requiring investigation. Synchronous channels are worth their cost for urgency, high-value accounts, and anything where a customer is stuck mid-task.
Every channel you open must be staffed to its expectation. An unstaffed live-chat widget is worse than no chat.
Service levels
Set by severity and customer tier, published internally, and — this is the part usually missing — checked against actual capacity before being promised. A commitment the staffing cannot meet is a commitment to fail visibly.
Measure first response and time to resolution separately. They have different causes: first response is a staffing problem, resolution is usually a product or escalation problem.
Metrics that mean something
- Contacts per active customer, trending. The only metric that captures whether the product is getting better rather than the team getting faster.
- First-contact resolution — reopens are the honest signal.
- Backlog age distribution, not average age. Averages hide the tickets rotting at the back, and those are the ones that become complaints.
- Customer-effort, asked at resolution.
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 d8c2273ccfa5
- 1mo ago Changed · +17 lines 59a89e6b8bd1
- 1mo ago First seen · 71 lines · 77 tokens per session scan A 1b4d91d82ddf
support-operations is a skill published in the GitHub repository cbrock84/headcount (2,075 stars, last pushed 2d ago), licensed MIT. It adds 77 tokens to every session and 904 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 2026-08-30.
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…