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/org-designnpx skills add cbrock84/headcount --skill org-designgit 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/org-design)<a href="https://agentmods.dev/skills/cbrock84/headcount/org-design"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/org-design.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 | $0.00069 | $0.00591 |
| Opus 5 | $0.00034 | $0.00296 |
| Sonnet 5 | $0.00014 | $0.00118 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
org-design 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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Org design
Structure determines what is easy and what requires heroics. Most persistent coordination problems are structural and cannot be fixed by asking people to communicate better.
Design from the work
Start with the work that must happen and its natural boundaries — where handoffs are expensive, and where they are cheap. Draw team lines at the cheap handoffs.
Then check: can each team deliver something meaningful without waiting on another? A team that cannot ship without three dependencies is not a team, it is a queue.
Design the org for the work, not around the people currently in it. Then reconcile deliberately, noting where you have compromised and why. Structures built around individuals fail when those individuals leave, and everyone can see they were built that way.
Spans and layers
Wide spans push decisions down and starve people of attention. Narrow spans give attention and breed layers, which add latency to every decision.
Roughly: five to nine reports for a manager whose people need coaching; more where the work is consistent and the people are experienced. Every layer must add decision value — a layer that only passes information along should be removed, and it is usually obvious which one it is.
Ownership
Every outcome has exactly one owner. Where two teams share an outcome, neither owns it, and it fails in the gap. Where an owner lacks the authority to deliver, the accountability is fictional.
Write down the boundaries — what each team decides alone, what needs consultation, what needs approval. Ambiguity between senior teams is expensive and does not resolve itself.
Workforce planning
Plan roles against the work and the plan, not against last year plus a percentage. For each proposed role: what does not happen without it, what does it take off someone else, and what is the ramp before it contributes?
Sequence hires so each has someone to learn from. Hiring three juniors before the senior who leads them is a common and expensive ordering error.
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.
- yesterday First seen · 63 lines · 69 tokens per session scan A 3b155ada9f5f
org-design is a skill published in the GitHub repository cbrock84/headcount (1,247 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 591 once invoked, about $0.0003 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.
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.
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.
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…