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 ai-ml-governancegit 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/ai-ml-governance)<a href="https://agentmods.dev/skills/cbrock84/headcount/ai-ml-governance"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/ai-ml-governance/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/ai-ml-governance"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/ai-ml-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00083 | $0.00768 |
| Opus 5 | $0.00042 | $0.00384 |
| Sonnet 5 | $0.00017 | $0.00154 |
| Haiku 4.5 | $0.00008 | $0.00077 |
Grade A, and why
ai-ml-governance 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 10d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI and ML governance
Regimes governing automated decision-making differ by jurisdiction and sector and are changing quickly. Anything affecting credit, employment, housing, insurance, healthcare, or education carries specific legal obligations — involve Legal & Risk and qualified counsel rather than treating it as an engineering question.
Define intended use before evaluating anything
Write down what the system is for, what it is not for, who is affected by its output, and what happens when it is wrong. Most AI failures are use outside intended scope by someone who did not know the scope existed.
Then decide the consequence tier, because it sets everything after it:
- Advisory — a human decides, the model suggests. Lightest oversight.
- Assistive — the model acts, a human reviews before effect.
- Autonomous — the model acts with effect. Highest bar, and rarely appropriate where a person is materially affected.
Evaluation
A held-out evaluation set that reflects real inputs, including the awkward ones. Built before deployment and kept stable, or you cannot compare versions.
- Measure the failure that matters. Aggregate accuracy hides the errors you care about. A model that is 95% accurate and wrong disproportionately on one group is not 95% good.
- Evaluate by segment, always. This is where fairness problems and quiet degradation appear.
- Both error directions. False positives and false negatives usually have different costs, and the threshold should reflect that ratio rather than a default.
- Establish a baseline. Compare against the current process — often a simple rule — not against zero. Plenty of models fail to beat the heuristic they replaced.
Monitoring
Models degrade silently: the world moves, inputs drift, and accuracy falls without any error being raised.
Monitor input distribution against training, output distribution over time, performance against whatever ground truth arrives later, and the rate of human override. A rising override rate is the best early warning you have, and it is usually already visible in a queue nobody reads.
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.
- 10d ago First seen · 74 lines · 83 tokens per session scan A 0c632fd3da05
ai-ml-governance is a skill published in the GitHub repository cbrock84/headcount (1,335 stars, last pushed 6d ago), licensed MIT. It adds 83 tokens to every session and 768 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 2026-08-30.
Other skills, from other repositories
companion-clis
Companion CLIs for Runpod workflows — HuggingFace, GitHub, Docker, and AWS.
cloud-inference-routing-workflow
Choose the right cloud AI inference, model training, model conversion, or GPU infrastructure path before implementation. Use when Codex works with Runpod, Hugging Face, AWS, AWS Lambda inference, Vast.ai, CoreWeave, GPU Pods, Serverless GPU endpoints, model weights, vLLM, TGI, SGLang, custom containers, LoRA/adapters…
vision-coreml-recognition-workflow
Guide custom Core ML image classification, object detection, semantic segmentation, and feature-output integration through Apple Vision, including model provenance, configuration, image constraints, crop-and-scale behavior, typed observations, confidence, postprocessing, compute units, evaluation, and performance…
vision-image-analysis-workflow
Guide Apple Vision implementation and repair for text, barcode, face, landmark, rectangle, contour, saliency, trajectory, pose, segmentation, tracking, feature-print, and image-location analysis across still images and video. Use when Apple-provided Vision requests, observations, orientation, normalized coordinates…
build-dotnet-agent-service
Build a local-first F# or C# Semantic Kernel agent service with explicit tools, model capability checks, evaluation fixtures, and draft-before-write promotion.
prompt-cookbook
Build a prompt cookbook for one company's actual vertical and roles rather than generic examples. Each recipe names the job it does, who runs it, the prompt itself, what good output looks like, and how to tell when it went wrong. Written for people who have never written a prompt and will not read documentation about…