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/systems-administrationnpx skills add cbrock84/headcount --skill systems-administrationgit 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/systems-administration)<a href="https://agentmods.dev/skills/cbrock84/headcount/systems-administration"><img src="https://agentmods.dev/badge/skills/cbrock84/headcount/systems-administration.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 | $0.00067 | $0.00602 |
| Opus 5 | $0.00034 | $0.00301 |
| Sonnet 5 | $0.00013 | $0.00120 |
| Haiku 4.5 | $0.00007 | $0.00060 |
Grade A, and why
systems-administration 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systems administration
Well-run systems are boring. The work is in the routine that keeps them that way, and almost every serious incident traces back to a routine that was skipped.
Cloud environment design belongs to technology:cloud-infrastructure; this is operating the systems
the company runs on.
Configuration baselines and drift
Every system class needs a defined baseline: build, hardening, agents, logging, accounts. Systems built by hand from memory diverge immediately and cannot be reasoned about as a group.
Drift is the real enemy. Detect it continuously and correct rather than document — a system that no longer matches its baseline is a system whose behavior under patching or failover is unknown.
The strongest form is disposability: rebuild rather than repair. A system you can rebuild in an hour never accumulates the sediment of a decade of manual fixes.
Patching as a cadence
Set a regular, predictable window and hold it. Ad hoc patching means patching happens when someone worries, which is never in proportion to actual risk.
Tier by exposure: internet-facing systems on the shortest cycle, then internal, then isolated.
Emergency patching is a separate path with its own authority, used for actively exploited
vulnerabilities — security:vulnerability-management decides what is urgent, this skill executes it.
Track coverage, not activity. "Patching is running" is not an answer; "97% of servers are within 30 days, here are the twelve that are not and why" is.
Change control proportionate to risk
Heavyweight approval for trivial changes produces circumvention, and circumvention produces unrecorded changes, which is worse than no process.
Tier it: standard pre-approved changes, normal changes with review, emergency changes with after-the-fact record. Every change needs an owner, a back-out plan, and a record — the back-out plan being the part most often assumed rather than written.
Maintenance windows exist to make disruption predictable. Announce them, keep them, and finish inside them.
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 · 61 lines · 67 tokens per session scan A 793896ab0df1
systems-administration is a skill published in the GitHub repository cbrock84/headcount (1,247 stars, last pushed 2d ago), licensed MIT. It adds 67 tokens to every session and 602 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
cloud-deployment-routing-workflow
Choose a cloud deployment path before implementation. Route AWS work to the official AWS Agent Toolkit and Azure work to Microsoft's Azure Skills plugin while keeping credentials, regions, and mutation boundaries explicit.
blob-store
This skill should be used when the user wants a "blob store" or "object storage", names "S3" or an S3-compatible store, needs to "store images / video / files", asks about "multipart upload" or "resumable upload", "signed / presigned URLs", "media storage", "unstructured data at scale", object "versioning", storage…
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…
macos-distribution-workflow
Inspect, prepare, validate, and troubleshoot exported macOS distribution artifacts. Use when checking signing identities, entitlements, hardened runtime, nested code, Gatekeeper, notarization readiness/results, stapling, or distribution-only launch failures.
prepare-isolated-analysis-lab
Prepare a verified disposable Linux or macOS analysis lab from an approved isolation decision. Use before active research to control host integration, networking, baseline, monitoring, evidence export, reset, and teardown.
flash
Write code locally, iterate with flash dev — it runs your functions on remote Runpod GPUs/CPUs with hot-reload and live worker logs — then flash deploy to ship. Endpoint handles provisioning.