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 cost-accountinggit 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/cost-accounting)<a href="https://agentmods.dev/skills/cbrock84/headcount/cost-accounting"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/cost-accounting/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/cost-accounting"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/cost-accounting.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 72 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 | $0.00092 | $0.00909 |
| Opus 5.5 | $0.00037 | $0.00364 |
| Sonnet 5.5 | $0.00018 | $0.00182 |
| Haiku 4.5 | $0.00009 | $0.00091 |
Grade A, and why
cost-accounting 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost accounting
Most bad pricing decisions, bad product-line decisions, and bad margin arguments come from the same place: nobody agrees what the thing costs.
Classify cost behavior before you allocate anything
- Fixed costs do not move with volume — within a relevant range. Outside that range they step, and the step is usually large: another shift, another facility, another tier of licensing.
- Variable costs move with each unit: materials, payment processing, per-unit fulfillment, usage-based infrastructure.
- Mixed costs have both, and most real accounts are mixed. Split them with high-low or a regression on historical volume rather than guessing the proportion.
The split is not academic. Variable cost sets the floor for one more incremental order. Fully loaded cost sets the floor for the business as a whole. Confusing the two is how companies price themselves into volume that loses money.
Know which costing basis you are looking at
Absorption costing puts fixed production overhead into inventory and releases it when the unit sells. Variable costing expenses that overhead as incurred.
Absorption is what external reporting requires. Variable is what decisions want. The consequence worth carrying: under absorption, producing more than you sell moves fixed cost onto the balance sheet and raises reported profit without a single additional sale. When margin improves and inventory grows in the same period, check whether that is what happened.
Match the costing method to how the work actually runs
- Job-order — distinct, identifiable jobs. Construction, custom manufacture, print runs, agency engagements. Cost accumulates per job.
- Process — continuous, homogeneous output. Chemicals, food, high-volume components. Cost accumulates per period and divides across equivalent units.
- Activity-based — worth the overhead when indirect cost is large and consumed unevenly. Its value is rarely precision; it is discovering that a low-volume product consumes a disproportionate share of support, setup, or handling.
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 88feb85ae659
- 1mo ago First seen · 74 lines · 92 tokens per session scan A 5af23a805aca
cost-accounting is a skill published in the GitHub repository cbrock84/headcount (2,085 stars, last pushed 6d ago), licensed MIT. It adds 92 tokens to every session and 909 once invoked, about $0.0004 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.
spend-audit
Audits a Webshare account for wasted proxy spend and recommends plan adjustments based on the account's own historical usage, using the webshare CLI. Use periodically (e.g. monthly) or whenever asked to review proxy costs, find savings, cut spend, or right-size plans. Strictly read-only — it recommends, it never…
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.
turbo-pipeline
Use when the user wants a feature built end to end after answering one round of questions and then being left alone — "turbo", "ask me once, then just build it", "I'll answer up front, don't come back to me", "decide the rest yourself". Not for a run that wants a spec approval and no tests (superb:fast-pipeline), one…