Agent skill

Cost Optimization

by rampstackco in rampstackco/claude-skills

Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity.

MITAuto-check passedDevOps & Cloud

Install Cost Optimization

skills CLI
$ npx skills add rampstackco/claude-skills --skill cost-optimization -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install rampstackco/claude-skills cost-optimization --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/rampstackco/claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cost-optimization .claude/skills/cost-optimization && rm -rf skills-src

Use ~/.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/

Facts

Skill name
cost-optimization
GitHub stars
935
Token cost
~3.1k tokens
SKILL.md length
1,570 words
Files
3 (incl. references)
Skills in repo
103
Repo updated
First seen
Licence
MIT

At a glance

Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity.

  • Works in 10 steps: Pull the spend data → Categorize → Identify the biggest line items → …
  • Reviewing monthly cloud
  • SKILL.md covers When to use, When NOT to use, Required inputs and The framework: 5 levers, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Cost Optimization is an agent skill from rampstackco/claude-skills. Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity. Use this skill when reviewing monthly cloud or SaaS spend, finding unused resources, rightsizing infrastructure, negotiating vendor contracts, deciding what to consolidate, or planning for budget cuts. Triggers on cost optimization, cloud spend, SaaS spend, rightsizing, unused resources, FinOps, infrastructure audit, vendor consolidation, budget cut, cost review. Also triggers when finance flags rising costs or when a…

Its SKILL.md is about 3.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `README.md` and `references/cloud-audit-checklist.md`).

It sits in DevOps & Cloud, covering Cloud cost optimization. The repository describes itself as: Stack-agnostic Claude Skills covering the full website lifecycle: brand, design, content, SEO, dev, ops, growth, and research. Build, ship, audit, optimize. The licence is MIT.

When your agent uses it

  • Reviewing monthly cloud
  • Finding unused resources
  • Rightsizing infrastructure
  • Negotiating vendor contracts

Example prompts

  • “/cost-optimization”

Workflow steps

10 steps, taken from the step headings in SKILL.md.

  1. Pull the spend data
  2. Categorize
  3. Identify the biggest line items
  4. Apply the 5 levers
  5. Prioritize
  6. Execute the easy wins
  7. Plan the larger work
  8. Set up ongoing visibility
  9. Negotiate at renewal
  10. Document the policy

What it can do on your machine

Read from SKILL.md and the folder at commit 482c9bf. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    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.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cost Optimization loads about 3.1k tokens when it runs, and up to ~5.2k if it reads all its reference files. Until then it costs about 140 tokens; SKILL.md has 1,570 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~140
When it runs · the whole SKILL.md, loaded when a task matches
~3.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.2k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from rampstackco/claude-skills at commit 482c9bf, republished under its MIT licence (© rampstackco). 1,570 words, ~3,055 tokens.

Download SKILL.mdSave it as .claude/skills/cost-optimization/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
cost-optimization
description
Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity. Use this skill when reviewing monthly cloud or SaaS spend, finding unused resources, rightsizing infrastructure, negotiating vendor contracts, deciding what to consolidate, or planning for budget cuts. Triggers on cost optimization, cloud spend, SaaS spend, rightsizing, unused resources, FinOps, infrastructure audit, vendor consolidation, budget cut, cost review. Also triggers when finance flags rising costs or when a contract renewal is up.
category
cross-cutting
catalog_summary
Infrastructure spend audits, rightsizing, contract negotiation
display_order
5

Cost Optimization

Audit cloud, SaaS, and infrastructure spend. Cut what's not earning its keep. Rightsize what's oversized. Negotiate what's negotiable. Without breaking what works.


When to use

  • Quarterly or annual cost review
  • Finance flags rising spend
  • Vendor contract renewal coming up
  • Budget cut required
  • New leadership wants the numbers
  • Migrating between providers (cost is part of the case)
  • Audit before scaling significantly (catch waste before it scales)

When NOT to use

  • Active incident response (use incident-response)
  • Performance issues that happen to involve infrastructure (use performance-optimization)
  • Vendor evaluation for a new purchase (use vendor-evaluation)
  • Personnel or org costs (out of scope for this skill)

Required inputs

  • Current cost (monthly, ideally for the last 12 months)
  • Cost broken down by service or vendor
  • Inventory of cloud resources (instances, databases, storage, etc.)
  • Inventory of SaaS subscriptions
  • Owners per cost line (who decided to spend this, who uses it)
  • Constraints (compliance, performance, contract terms)

The framework: 5 levers

Every cost optimization opportunity falls into one of these levers.

Lever 1: Eliminate

Stop paying for things that aren't used.

  • Idle resources (instances, databases, environments running but unused)
  • Subscriptions where no one logs in
  • Duplicate tools (multiple tools doing the same job)
  • Old projects still incurring cost
  • Test environments that should have been torn down
  • Forgotten domains, backups, snapshots, logs

This is usually the largest opportunity in the first audit. Often 10-30% of spend.

Lever 2: Rightsize

Pay for what you actually use, not what you provisioned for the worst case three years ago.

  • Oversized instances (CPU and memory utilization low)
  • Over-provisioned databases (storage and throughput far above usage)
  • Over-purchased SaaS seats
  • Premium plans where standard would suffice
  • High-availability setups for non-critical systems

Rightsizing requires real usage data, not theoretical needs.

Lever 3: Restructure

Use cheaper structures for the same workload.

  • Reserved or committed-use pricing (1-3 year commitments at 30-70% discount)
  • Spot or preemptible instances for fault-tolerant work
  • Cold storage for data accessed rarely
  • Tiered storage (hot/warm/cold) by access pattern
  • CDN caching to reduce origin load
  • Compression and deduplication
  • Serverless for spiky workloads
  • Reserved instances for steady workloads

The right structure depends on the access pattern. Mismatch costs money.

Lever 4: Negotiate

Pay less for the same thing.

  • Annual contracts at lower rates than monthly
  • Volume discounts at higher tiers
  • Multi-year commitments for predictable workloads
  • Bundle deals (consolidating services with one vendor)
  • Renewal negotiation (vendors expect you to ask)
  • RFP / competitive bid (using alternatives as leverage)

Most enterprise vendors negotiate. Most SaaS vendors don't, except at higher tiers. Consumer-tier services usually don't.

Lever 5: Reframe

Change the question.

  • Build vs buy: maybe in-house is cheaper at scale
  • Buy vs build: maybe outsourcing is cheaper at small scale
  • Different architecture (e.g., monolith vs microservices) has different cost profiles
  • Different audience (do all customers need the same tier?)
  • Different stack (open source vs commercial)

Reframe is the longest-lead lever. Worth thinking about even if not actionable now.


Workflow

Step 1: Pull the spend data

Get monthly costs by service, vendor, and (where possible) team or project.

For cloud (AWS, GCP, Azure): the billing console and cost-explorer tools. For SaaS: each vendor's billing portal, plus an SaaS-management tool if available. For everything else: bank statements and accounting export.

12 months minimum. Trends matter as much as absolute numbers.

Step 2: Categorize

Organize spend into categories:

  • Hosting / compute
  • Storage
  • Database
  • Networking / CDN
  • Monitoring / observability
  • Email
  • CMS / hosting platforms
  • Analytics / marketing
  • Productivity / collaboration
  • Development tools
  • Security / compliance
  • Other

The categories vary by business. The point is: similar costs grouped, easy to compare.

Step 3: Identify the biggest line items

80/20 rule. Usually 20% of vendors account for 80% of spend.

Focus the audit on the top 80%. The long tail can be cleaned up but rarely yields big savings per item.

Step 4: Apply the 5 levers

For each major line item, walk the levers:

LeverQuestion
EliminateIs it used? Could we stop using it?
RightsizeAre we paying for capacity we don't use?
RestructureIs there a cheaper pricing model or service tier?
NegotiateWhen was the last renewal? Did we negotiate?
ReframeIs this even the right approach?

Document the opportunity, the effort, the risk, and the savings estimate.

Step 5: Prioritize

Plot opportunities on a 2x2:

  • Y axis: savings
  • X axis: effort

Quadrants:

  • High savings, low effort: do first
  • High savings, high effort: plan
  • Low savings, low effort: do as time allows
  • Low savings, high effort: skip

Also consider risk:

  • Eliminate something used by no one: low risk
  • Rightsize a database: medium risk (test in staging first)
  • Replace a critical dependency: high risk (plan carefully)
Step 6: Execute the easy wins

For each easy-win opportunity:

  • Document the change
  • Get owner approval
  • Make the change
  • Monitor for unexpected impact
  • Confirm cost reduction in next billing cycle

Easy wins typically include:

  • Canceling unused subscriptions
  • Tearing down idle resources
  • Switching off dev environments outside business hours
  • Moving cold data to cheaper storage tiers
Step 7: Plan the larger work

For higher-effort opportunities:

  • Spec the change (use pm-spec-writing for the plan)
  • Test in staging
  • Roll out incrementally
  • Validate cost impact

Examples:

  • Migrating to reserved instances
  • Consolidating monitoring vendors
  • Migrating from one CMS to another with cost benefit
Step 8: Set up ongoing visibility

Optimization isn't one-time. Costs creep back up.

  • Monthly cost review (at least)
  • Cost dashboard (current, trend, by category)
  • Alerts on cost spikes (e.g., daily spend exceeds threshold)
  • Tagging or labeling on cloud resources (cost by team or project)
  • Quarterly deeper review
Step 9: Negotiate at renewal

For vendor contracts up for renewal:

  • Start the conversation 60-90 days before renewal
  • Have alternatives identified (even if you don't switch)
  • Ask for a multi-year discount
  • Ask about volume tiers
  • Ask if usage rightsizing is possible
  • Be willing to walk (most vendors find a way to keep you)

Pre-pandemic, many vendors auto-renewed at increases. Post-pandemic, many are hungry for retention. Ask.

Show full SKILL.md (601 more words)Show less
Step 10: Document the policy

Going forward:

  • New vendor evaluation requires cost justification
  • Resource provisioning has approval thresholds
  • Tagging and labeling are required for cloud resources
  • Quarterly review is calendared
  • Cost attribution is clear

Without policy, costs creep.


Common opportunities by category

Hosting and compute
  • Reserved or committed-use pricing for predictable workloads (30-70% off)
  • Spot or preemptible for fault-tolerant batch
  • Auto-scaling for variable loads
  • Right instance family (compute-optimized, memory-optimized, etc.)
  • Dev/staging instances stopped outside business hours
Storage
  • Lifecycle policies to move old data to cheaper tiers
  • Delete old logs, backups, snapshots
  • Compression for archival
  • Object versioning costs (every version is a stored object)
Database
  • Right size based on actual CPU/memory usage
  • Reserved capacity for predictable workloads
  • Read replicas for read-heavy workloads (cheaper than scaling primary)
  • Drop unused indexes (indexes cost storage and write performance)
  • Old data archived or deleted
Networking and CDN
  • CDN reduces origin egress costs (often the biggest cost category)
  • Compression on the wire
  • Image and video optimization
  • Region-aware routing
Monitoring and observability
  • Sample logs (don't ingest 100% of high-volume sources)
  • Retention policies (do you need 90 days or 30?)
  • Consolidate tools where possible
  • Free or open-source tooling for non-critical needs
SaaS
  • Audit logins per seat (inactive users on $X/seat = $X waste)
  • Renegotiate at renewal
  • Move to annual billing for the discount
  • Consolidate overlapping tools

Failure patterns

Cost-cutting that breaks something. Aggressive rightsizing without testing causes outages. The cost of an outage is usually larger than the savings.

Optimization that takes more time than it saves. A team spends a quarter saving $5K/year. Math doesn't work. Focus on opportunities where savings exceed effort.

Renewal autopilot. Annual renewals go through without review. Calendar them.

No tagging. Cloud spend grows; no one knows whose. Tag everything from day one.

Free tier overruns. "It's on the free tier." Then it's not, and bills surprise. Set alerts on free-tier services.

No environment differentiation. Production-grade staging "to match prod." Costs as much as prod. Often unnecessary.

Untouched legacy. "The old project still runs." Why? Often: nothing actually uses it. Audit and shut down.

Premium tiers for non-premium needs. Enterprise plan because someone wanted a feature that's been since added to lower tiers. Recheck.

Vendor lock-in justifying cost. "We can't switch." That's not a reason to overpay; it's a strategic problem to plan around.

Optimizing the small stuff while ignoring the big stuff. Saving $50/month on tools while $5K/month sits in oversized infrastructure. Top-down first.

Penny-wise, pound-foolish. Cutting a useful tool to save $20/month, then losing hours to manual work. Tools that pay for themselves shouldn't be cut.

No reinvestment. Every dollar saved goes to bottom line; nothing reinvested in upgrades or capacity. Saved costs and improved capability aren't either/or.


Output format

A cost optimization document includes:

  • Current state: total spend, by category, trended
  • Top line items: the biggest costs
  • Opportunities: by lever (eliminate / rightsize / restructure / negotiate / reframe)
  • Prioritized list: with savings, effort, risk
  • Action plan: owners, dates
  • Easy wins executed: what's already done, results
  • Ongoing governance: dashboard, review cadence, tagging, approval thresholds

If required data is unavailable

This skill's output depends on data, measurements, or tool results it cannot generate on its own. When a required input, tool, or data source is unavailable or unverifiable, the sanctioned output is the deliverable with the gap stated: what was needed, what was actually obtained or verified, and which parts of the output are affected. Fabricating, estimating, or interpolating a required number to complete the deliverable is never sanctioned. A stated gap is a complete answer.


Reference files

  • references/cloud-audit-checklist.md: A practical walkthrough for auditing a cloud account (compute, storage, database, network, monitoring) for waste and rightsizing opportunities.

© rampstackco, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/cost-optimization of rampstackco/claude-skills.

  • SKILL.md
  • README.md
  • references/cloud-audit-checklist.md

Open the folder on GitHubat commit 482c9bf

Compare with similar skills

Cost Optimization 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.

Cost Optimization compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cost Optimization this skillrampstackco/claude-skills935—~3.1kAutomated safety check: PassMIT
Vercel Optimize Auditvercel-labs/agent-skills32k8 repos~4.3kAutomated safety check: PassNone
Cloud Cost Optimizationwshobson/agents40k13 repos~1.7kAutomated safety check: PassMIT
Trigger.dev Cost Savings Auditpapermark/papermark9.2k—~1.3kAutomated safety check: PassCustom licence
Kubernetes SpecialistJeffallan/claude-skills12k1 repos~2.1kAutomated safety check: PassMIT
Axiom Cost Controlopenclaw/clawhub9.5k—~1.7kAutomated safety check: PassMIT

Similar skills

  • Vercel Optimize Audit

    vercel-labs/agent-skills

    Official

    Runs a metrics-first audit of a deployed Vercel project, gating investigations on real signals to produce ranked, citation-backed cost and performance recommendations.

    32k GitHub starsUsed in 8 repos~4.3k tokens
    DevOps & CloudAuto-check passed
  • Cuts cloud spend across AWS, Azure, GCP and OCI with cost tagging, rightsizing, commitment and spot pricing models, and architecture changes.

    40k GitHub starsUsed in 13 repos~1.7k tokens
    DevOps & CloudAuto-check passed
  • Audits Trigger.dev tasks, schedules and run history for wasteful machine sizes, retries, polling and cron frequency to cut spend.

    9.2k GitHub stars~1.3k tokensUpdated 1 mo ago
    DevOps & CloudAuto-check passed
  • Kubernetes Specialist

    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.

    12k GitHub starsUsed in 1 repo~2.1k tokens
    DevOps & CloudAuto-check passed
  • Axiom Cost Control

    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.

    9.5k GitHub stars~1.7k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Spotinfo

    alexei-led/spotinfo

    Query Spot/preemptible VM prices, savings and interruption risk across AWS, GCP and Azure with the spotinfo CLI.

    164 GitHub stars~1.8k tokensUpdated 2 days ago
    DevOps & CloudAuto-check passed

More from rampstackco/claude-skills

All 103 skills in this repo
  • After Action Report

    rampstackco/claude-skills

    Run a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline, root cause analysis, contributing factors, and actionable lessons.

    935 GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • Analytics Strategy

    rampstackco/claude-skills

    Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy.

    935 GitHub starsUsed in 1 repo~2.4k tokens
    Auto-check passed
  • Brand Style Guide

    rampstackco/claude-skills

    Build or audit a comprehensive brand style guide that documents the full brand system including story, logo system, color, typography, imagery, voice, applications, and dos/don'ts.

    935 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Brand Voice

    rampstackco/claude-skills

    Develop or document a complete brand voice and tone system covering voice attributes, tone shifts by context, vocabulary preferences, grammar rules, and copy examples.

    935 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Content And Copy

    rampstackco/claude-skills

    Write or edit website copy, blog content, and editorial pieces with attention to voice, structure, and goal.

    935 GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Content Strategy

    rampstackco/claude-skills

    Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning.

    935 GitHub stars~2.6k tokensUpdated today
    Auto-check passed

Categories

Questions about Cost Optimization

What does Cost Optimization do?

Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity. Cost Optimization is an agent skill from rampstackco/claude-skills. Audit and reduce infrastructure and tooling costs without sacrificing reliability or velocity.

When should I use Cost Optimization?

Cost Optimization fits situations like: reviewing monthly cloud; finding unused resources; rightsizing infrastructure; negotiating vendor contracts.

How do I install Cost Optimization in Claude Code?

Run `npx skills add rampstackco/claude-skills --skill cost-optimization -a claude-code`. Or copy the skill folder (skills/cost-optimization in rampstackco/claude-skills) into .claude/skills/cost-optimization in your project. Claude Code loads it when a task matches its description.

How do I install Cost Optimization in Codex?

Run `npx skills add rampstackco/claude-skills --skill cost-optimization -a codex`. Or copy the skill folder (skills/cost-optimization in rampstackco/claude-skills) into .agents/skills/cost-optimization in your project. Codex loads it when a task matches its description.

Can I use Cost Optimization in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add rampstackco/claude-skills --skill cost-optimization -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cost-optimization, .gemini/skills/cost-optimization, .github/skills/cost-optimization and .opencode/skills/cost-optimization in your project.

What does Cost Optimization need to run?

SKILL.md names no scripts, command-line tools or credentials: Cost Optimization is instructions for the agent only.

Does Cost Optimization access the network?

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.

Is Cost Optimization safe to install?

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.

What licence does Cost Optimization use?

Cost Optimization is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cost Optimization use?

About 3.1k tokens (SKILL.md is roughly 12k 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 2.1k tokens, read only when the agent opens those files.

What are the alternatives to Cost Optimization?

Skills that share tags, products or a category with Cost Optimization: Vercel Optimize Audit (vercel-labs/agent-skills, 32k stars), Cloud Cost Optimization (wshobson/agents, 40k stars), Trigger.dev Cost Savings Audit (papermark/papermark, 9.2k stars) and Kubernetes Specialist (Jeffallan/claude-skills, 12k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cost Optimization?

rampstackco (a GitHub organization) maintains it in rampstackco/claude-skills, which has 935 GitHub stars. The repository holds 103 skills in this directory. The repository was last updated on October 7, 2026.

Source: rampstackco/claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.