Capacity And Cost Engineering
magnus919/agent-skills
Model technical capacity, unit cost, and budget constraints connected to demand, performance, and reliability decisions.
Administers the cloud the company runs on rather than the one it sells — tenant and subscription structure, the SaaS estate and who owns each app, identity as the real perimeter, cloud spend that…
$ npx skills add cbrock84/headcount --skill cloud-administration -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cbrock84/headcount cloud-administration --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cbrock84/headcount.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/it-operations/skills/cloud-administration .claude/skills/cloud-administration && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "cloud-administration" agent skill from https://github.com/cbrock84/headcount/tree/main/plugins/it-operations/skills/cloud-administration into .claude/skills/cloud-administration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cloud-administration", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cbrock84/headcount/tree/main/plugins/it-operations/skills/cloud-administrationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cbrock84/headcount --skill cloud-administration -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cbrock84/headcount cloud-administration --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cbrock84/headcount.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/it-operations/skills/cloud-administration .agents/skills/cloud-administration && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cloud-administration" agent skill from https://github.com/cbrock84/headcount/tree/main/plugins/it-operations/skills/cloud-administration into .agents/skills/cloud-administration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cloud-administration", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cbrock84/headcount --skill cloud-administration -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cbrock84/headcount cloud-administration --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cbrock84/headcount.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/it-operations/skills/cloud-administration .cursor/skills/cloud-administration && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "cloud-administration" agent skill from https://github.com/cbrock84/headcount/tree/main/plugins/it-operations/skills/cloud-administration into .cursor/skills/cloud-administration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cloud-administration", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cbrock84/headcount.git --path plugins/it-operations/skills/cloud-administration--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cbrock84/headcount --skill cloud-administration -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cbrock84/headcount cloud-administration --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cbrock84/headcount.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/it-operations/skills/cloud-administration .gemini/skills/cloud-administration && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "cloud-administration" agent skill from https://github.com/cbrock84/headcount/tree/main/plugins/it-operations/skills/cloud-administration into .gemini/skills/cloud-administration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cloud-administration", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cbrock84/headcount cloud-administrationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cbrock84/headcount --skill cloud-administration -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cbrock84/headcount.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/it-operations/skills/cloud-administration .github/skills/cloud-administration && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "cloud-administration" agent skill from https://github.com/cbrock84/headcount/tree/main/plugins/it-operations/skills/cloud-administration into .github/skills/cloud-administration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cloud-administration", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cbrock84/headcount --skill cloud-administration -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cbrock84/headcount cloud-administration --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cbrock84/headcount.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/it-operations/skills/cloud-administration .opencode/skills/cloud-administration && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "cloud-administration" agent skill from https://github.com/cbrock84/headcount/tree/main/plugins/it-operations/skills/cloud-administration into .opencode/skills/cloud-administration/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cloud-administration", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
cloud-administrationAdministers the cloud the company runs on rather than the one it sells — tenant and subscription structure, the SaaS estate and who owns each app, identity as the real perimeter, cloud spend that…
Cloud Administration is an agent skill from cbrock84/headcount. Administers the cloud the company runs on rather than the one it sells — tenant and subscription structure, the SaaS estate and who owns each app, identity as the real perimeter, cloud spend that arrives as a surprise, and what the provider does not do for you. Use this to structure subscriptions or tenants, get control of sprawling SaaS, cut a cloud bill, work out who owns an application nobody admits to buying, or decide what corporate workloads belong in cloud at all.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/sources.md`).
It sits in DevOps & Cloud, covering Cloud cost optimization. The repository describes itself as: An agent organization structured as a company — 15+ departments, 125+ skills, each independently installable, citing the standards and regulators that settle the question. Runs… The licence is MIT.
Read from SKILL.md and the folder at commit 98d1c17. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Cloud Administration loads about 1.5k tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 124 tokens; SKILL.md has 830 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from cbrock84/headcount at commit 98d1c17, republished under its MIT licence (© cbrock84). 830 words, ~1,524 tokens.
.claude/skills/cloud-administration/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Corporate cloud is bought, not architected. Someone needed a tool, expensed it, and it entered the estate without a review, an owner, or an offboarding path. The characteristic failure is not a bad design — it is discovering the estate years later, one invoice at a time.
This is the cloud the business runs on. For the cloud a product is built on — environments,
infrastructure as code, scaling, region failure — see technology:cloud-infrastructure. The two
follow different rules and the boundary is worth keeping sharp.
Subscription and account structure encodes what you can later separate: billing, access, policy, and blast radius. Retrofitting it means moving live workloads, so the cheap moment is the first one.
A workable default is to separate by what you would want to bill, govern, or lose independently — production corporate services, non-production, and anything with a distinct compliance obligation. Resist a subscription per team; teams reorganize, and the structure outlives them.
Tag at creation with owner, cost center, and environment, and enforce it with policy rather than documentation. Untagged resources become unattributable spend within a quarter, and nobody volunteers to claim them.
Most companies underestimate their application count by a wide margin, because the ones they know about were bought by IT and the rest were bought by everyone else. The discovery methods that actually work are financial, not technical: expense reports, corporate card statements, and the identity provider's sign-in logs. Network monitoring finds less than the accounting system does.
Every application needs a named business owner, a renewal date, and a data classification. Without the owner there is nobody to ask at renewal. Without the renewal date the negotiation happens after auto-renewal. Without the classification, nobody knows which breach notification obligations apply when the vendor is compromised.
An application that stores customer or employee data belongs in the review that
legal-risk:privacy-and-data-protection describes, and a departing employee's access to it is
it-operations:identity-lifecycle-administration's problem — which it cannot solve for an
application it does not know exists.
Once the estate is cloud, network location protects nothing and the identity provider is the only consistent control point. Single sign-on is therefore not a convenience feature; it is what makes deprovisioning possible in one place instead of forty.
The practical rule is to refuse applications that cannot federate, or to accept them knowingly with a documented manual offboarding step. Vendors that charge extra for SSO are charging for the security baseline, and that cost belongs in the purchase decision rather than being discovered later.
Conditional access, MFA, and privileged role activation are the controls worth the effort. See
security:access-and-identity for the design; this skill owns operating it across a real estate.
Cloud bills grow because nothing in the system stops them. Resources are easy to create, nobody is billed personally, and consumption is invisible until the invoice.
Three habits catch most of it: a budget alert on every subscription before workloads land, a monthly review of the largest movers rather than the whole bill, and a scheduled look at anything running that nobody has logged into. Reserved and committed pricing is real money for steady workloads, but it is a bet on a run rate — commit only where the load is genuinely predictable.
Non-production environments running overnight and at weekends are the most common single line of waste, and shutting them on a schedule is a change nobody notices.
The provider keeps the platform available. Almost everything else — configuration, access, and in most cases the data itself — stays yours.
The one that catches organizations out is backup. A major SaaS suite protects itself against its
own failures, not against a user deleting a mailbox or a ransomware event propagating through
sync. Retention settings are not backups, and the recycle bin is not a recovery point. Decide
deliberately what needs independent protection under it-operations:backup-and-recovery rather
than assuming the vendor's durability promise covers your mistakes.
references/sources.md in this skill lists the outside authorities that settle the questions
here — what each one is authoritative for, and what you may do with it. Check them before
answering on anything they cover, and cite what you used. Most are free to read and not free
to reproduce; the use note on each is binding.
Platforms: AWS, Microsoft Azure, Google Cloud, and similar.
Infrastructure as code: Terraform, OpenTofu, Pulumi, Bicep, CloudFormation, and similar.
Cost visibility: the native cost tools, or CloudZero, Vantage, Finout, and similar. Guardrails: AWS Control Tower, Azure Policy, Wiz, and similar.
Console changes nobody can reproduce in code become the outage you cannot rebuild from.
© cbrock84, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in plugins/it-operations/skills/cloud-administration of cbrock84/headcount.
Open the folder on GitHubat commit 98d1c17
Cloud Administration next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Cloud Administration this skillcbrock84/headcount | 2k | — | ~1.5k | Automated safety check: Pass | MIT | |
| Capacity And Cost Engineeringmagnus919/agent-skills | 113 | — | ~4.7k | Automated safety check: Pass | MIT | |
| Vercel Optimize Auditvercel-labs/agent-skills | 32k | 9 repos | ~4.3k | Automated safety check: Pass | None | |
| Cloud Cost Optimizationwshobson/agents | 40k | 14 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Trigger.dev Cost Savings Auditpapermark/papermark | 9.2k | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| Kubernetes SpecialistJeffallan/claude-skills | 12k | 1 repos | ~2.1k | Automated safety check: Pass | MIT |
magnus919/agent-skills
Model technical capacity, unit cost, and budget constraints connected to demand, performance, and reliability decisions.
vercel-labs/agent-skills
Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.
wshobson/agents
Cuts cloud spend across AWS, Azure, GCP and OCI with cost tagging, rightsizing, commitment and spot pricing models, and architecture changes.
papermark/papermark
Audits Trigger.dev tasks, schedules and run history for wasteful machine sizes, retries, polling and cron frequency to cut spend.
Jeffallan/claude-skills
Creates and checks Kubernetes manifests, Helm charts, RBAC and network policies, and helps debug pod problems, with kubectl checks and rollback steps.
openclaw/clawhub
Finds unused data in Axiom by analyzing query patterns, then deploys a cost dashboard and ingest monitors to keep spend under the contract limit.
cbrock84/headcount
Designs orchestrator-and-subagent hierarchies for a repository — splitting agents by exclusive write surface, pairing every producer with an independent auditor, and enforcing the split with a…
cbrock84/headcount
Designs and audits who can reach what — authentication, authorization models, privileged access, service credentials, and joiner-mover-leaver process.
cbrock84/headcount
Concentrates marketing and sales effort on a named set of accounts rather than on volume — qualifying whether the model fits your economics at all, building the account list and the buying group…
cbrock84/headcount
Gets new users from signup to first real value — signup flow, onboarding, time-to-value, and the early experience that determines whether someone becomes a user or a lapsed account.
cbrock84/headcount
Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit.
cbrock84/headcount
Optimizes for AI assistants and AI-generated answers — being retrievable, being cited, and being represented accurately when a model answers on your behalf.
Categories
Administers the cloud the company runs on rather than the one it sells — tenant and subscription structure, the SaaS estate and who owns each app, identity as the real perimeter, cloud spend that…. Cloud Administration is an agent skill from cbrock84/headcount. Administers the cloud the company runs on rather than the one it sells — tenant and subscription structure, the SaaS estate and who owns each app, identity as the real perimeter, cloud spend that arrives as a surprise, and what the provider does not do for you.
Cloud Administration fits situations like: tasks that involve Cloud cost optimization.
Run `npx skills add cbrock84/headcount --skill cloud-administration -a claude-code`. Or copy the skill folder (plugins/it-operations/skills/cloud-administration in cbrock84/headcount) into .claude/skills/cloud-administration in your project. Claude Code loads it when a task matches its description.
Run `npx skills add cbrock84/headcount --skill cloud-administration -a codex`. Or copy the skill folder (plugins/it-operations/skills/cloud-administration in cbrock84/headcount) into .agents/skills/cloud-administration in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cbrock84/headcount --skill cloud-administration -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cloud-administration, .gemini/skills/cloud-administration, .github/skills/cloud-administration and .opencode/skills/cloud-administration in your project.
SKILL.md names no scripts, command-line tools or credentials: Cloud Administration is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Cloud Administration is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.5k tokens (SKILL.md is roughly 6.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 626 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Cloud Administration: Capacity And Cost Engineering (magnus919/agent-skills, 113 stars), Vercel Optimize Audit (vercel-labs/agent-skills, 32k stars), Cloud Cost Optimization (wshobson/agents, 40k stars) and Trigger.dev Cost Savings Audit (papermark/papermark, 9.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
cbrock84 (a GitHub user) maintains it in cbrock84/headcount, which has 2,007 GitHub stars. The repository holds 175 skills in this directory. The repository was last updated on September 17, 2026.
Source: cbrock84/headcount on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.