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 product-requirementsgit 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/product-requirements)<a href="https://agentmods.dev/skills/cbrock84/headcount/product-requirements"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/product-requirements/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/product-requirements"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/product-requirements.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 43 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 | $0.00095 | $0.00738 |
| Opus 5 | $0.00048 | $0.00369 |
| Sonnet 5 | $0.00019 | $0.00148 |
| Haiku 4.5 | $0.00010 | $0.00074 |
Grade A, and why
product-requirements 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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product requirements
A specification exists to prevent expensive rediscovery — of decisions already made, of scope already agreed, and of the edge cases that are found either now on a page or later in production.
Lead with the problem and the number, not the solution
Open with who has the problem, what it costs them today, and what you expect to change if this ships — expressed as a measure with a target and a date. A document that starts with a solution invites the team to optimize the wrong thing and gives you no way to tell afterward whether it worked.
Decide the success measure before building, not at launch. A number chosen afterward is chosen to be met.
State scope by exclusion
Everyone reads what is in scope and assumes the rest is coming. An explicit "not in this" list is the cheapest thing in the document and prevents most scope arguments — including the ones that arrive as clarifications rather than as requests.
Say what is deferred versus what is rejected. Those are different, and conflating them means the rejected thing comes back.
Describe behavior, not implementation
Write what the user experiences and what the system guarantees. Leave the how to the people who will own it — a specification that dictates implementation gets a worse implementation and blurs who is accountable for it.
The states nobody writes down are where the rework comes from. Empty, loading, error, partial, permission-denied, offline, and the first-run case with no data. Also: what happens to records that already exist, what happens at the limits, and what happens when two people do it at once. Most "that wasn't what I meant" traces back to one of these.
Make acceptance criteria testable
Each one should be a statement someone can evaluate as true or false without asking you. "Fast" and "intuitive" are not criteria; a response-time budget and a task someone completes unaided are.
If a criterion cannot be tested, it is either a principle — say so and move it — or it is not finished being thought about.
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.
- 5d ago First seen · 68 lines · 95 tokens per session scan A 6ab261b1cec8
product-requirements is a skill published in the GitHub repository cbrock84/headcount (1,320 stars, last pushed 5d ago), licensed MIT. It adds 95 tokens to every session and 738 once invoked, about $0.0005 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 2026-09-03.
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.
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…