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 enterprise-riskgit 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/enterprise-risk)<a href="https://agentmods.dev/skills/cbrock84/headcount/enterprise-risk"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/enterprise-risk.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 | $0.00081 | $0.00731 |
| Opus 5 | $0.00041 | $0.00365 |
| Sonnet 5 | $0.00016 | $0.00146 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
enterprise-risk 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enterprise risk
The register is the artifact
A risk that is not written down with an owner is not managed. Each entry carries:
- The risk stated as a cause and consequence — "if X happens, then Y." "Cybersecurity" is a category, not a risk. "If an employee's credentials are phished, an attacker reaches customer records" is a risk you can do something about.
- Likelihood and impact, on a stated scale, with the reasoning. The reasoning matters more than the score.
- Current controls and an honest view of whether they work.
- Residual risk after those controls — the number that actually matters and the one most often omitted.
- A named owner. A person, not a department.
- Treatment and a date.
Treatment is a decision with four options
Mitigate (reduce it), transfer (insure or contract it away), avoid (do not do the thing), or accept. Accepting is legitimate and often correct — but acceptance must be explicit, at the right level of authority, and recorded. Risk accepted by silence is risk nobody owns.
Anything above the threshold that only the chief executive can accept goes to them. Never let an unacceptable risk be quietly downgraded to fit an existing authority.
Scoring honestly
Two failure modes, both common:
- Everything is high. The register stops discriminating and gets ignored.
- Scores drift downward as items age without the underlying exposure changing.
Re-assess on a schedule and require evidence for any reduction. A control's existence is not evidence it works; a test of the control is.
Audit readiness
Continuous, not a project. What auditors need: documented policies, evidence they are followed, records of exceptions and approvals, and a clear line from the framework's requirement to your control to the evidence.
Collect evidence as work happens. Assembling a year of it retrospectively is expensive, and gaps found then cannot be fixed retroactively.
Reporting
Leadership needs the few risks whose residual exposure is above appetite, what is being done, and what needs a decision. Not the whole register. A risk report that requires reading forty rows to find the three that matter will not be read.
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 · 73 lines · 81 tokens per session scan A cc5206c0efb8
enterprise-risk is a skill published in the GitHub repository cbrock84/headcount (1,284 stars, last pushed 3d ago), licensed MIT. It adds 81 tokens to every session and 731 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
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…