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 agentmods add skills/cbrock84/headcount/financial-modelingnpx skills add cbrock84/headcount --skill financial-modelinggit 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/financial-modeling)<a href="https://agentmods.dev/skills/cbrock84/headcount/financial-modeling"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/financial-modeling.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00076 | $0.00867 |
| Opus 5 | $0.00038 | $0.00434 |
| Sonnet 5 | $0.00015 | $0.00173 |
| Haiku 4.5 | $0.00008 | $0.00087 |
Grade A, and why
financial-modeling 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 2d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Financial modeling
A model is an argument about how the business works, expressed in arithmetic. Its value is the argument, not the output precision.
Structure
Three separated layers, always:
- Inputs — every assumption, in one place, each with a source and a date. An assumption buried inside a formula is invisible and therefore never challenged.
- Calculations — no hard-coded numbers. Ever. A constant inside a formula is an untraceable assumption.
- Outputs — the statements and the summary a decision-maker actually reads.
One row, one calculation, carried consistently across periods. Models become unauditable through inconsistent rows more than through complexity.
Build revenue from drivers
Never grow a top-line by a percentage. Build it: volume × price, or accounts × retention × expansion. Driver-based models can be argued with, and being argued with is the point — a growth rate cannot be wrong, only optimistic.
Cost structure separated into fixed, variable, and step-fixed. The step-fixed items are where plans break, because they move in jumps nobody modeled.
Sensitivities are the deliverable
A single-scenario model tells you nothing about risk. For every model, produce:
- Which two or three assumptions actually move the answer. Usually far fewer than expected.
- Breakeven on each — how wrong can this be before the decision reverses?
- Downside case — not a haircut on the base case, but a coherent story where things go badly.
If a plan only works in the base case, that is the finding.
Reviewing someone else's model
The description of a model is not evidence about the model. Check these, in this order, because each one invalidates everything after it.
- Trace one number end to end. Pick an output that matters and follow it back to inputs. If you cannot, nobody else has either, and the model has never actually been reviewed.
- Find the hard-coded constants. Search the calculation area for typed numbers. Each one is an assumption that escaped the input sheet, and they are where overrides hide.
- Check the row consistency. A formula that differs partway across a row is either a deliberate change nobody documented or an error, and the two look identical.
- Test the extremes. Set a key driver to zero and to double. Models frequently break, go negative in impossible ways, or fail to respond at all — which tells you the driver is decorative.
- Check that the statements tie. Cash flow reconciles to the balance sheet movement; the balance sheet balances in every period, not just the first.
- Ask what is missing. Working capital, hiring lag, churn, price changes, tax, and the step costs that come with growth are the omissions that flatter a plan most.
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.
- 2d ago First seen · 78 lines · 76 tokens per session scan A 40ea00eb7d60
financial-modeling is a skill published in the GitHub repository cbrock84/headcount (1,247 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 867 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 2026-09-03.
Other skills, from other repositories
stockbit-auth
Log in to Stockbit and capture the session for this server — opens the browser login flow and verifies the token was stored. Use when the user asks to log in or re-authenticate to Stockbit, or after a status check reports the session expired, HTTP 401, or logged out.
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.
morning-scan
The pre-open and first-hour routine for IDX — session state, movers, a scan over a universe, and a catalyst check on the leaders. Use when the user asks what is moving today, for a morning briefing, or what to watch.
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.
swiftui-app-architecture-workflow
Guide SwiftUI app-structure decisions for Apple apps across App, scenes, commands, focus, environment, preferences, window and document coordination, and reusable view composition. Use when the user wants help deciding where ownership belongs in a SwiftUI app, which data-flow mechanism fits a responsibility, or how to…