Cost Optimizer

Estimate the token usage and dollar cost of the CURRENT conversation, then translate it into a break-even wage (effective hourly cost) so the user can judge whether the task was worth it. Use whenever the user asks what a conversation cost, how many tokens it used, "was this worth it", "what's the break-even wage", "effective hourly cost", "run the cost estimate", "/cost", "estimate the tokens", or any end-of-conversation cost check. Also fire when the user is weighing the value they got against what a task cost. Produces an estimate (not a billed figure) with list-price and cache-adjusted cos

39 stars 6 forksProductivity & Notes

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ShawhinT/non-coding-skills --skill cost-optimizer
Manual install
git clone --depth 1 https://github.com/ShawhinT/non-coding-skills.git /tmp/non-coding-skills
mkdir -p ~/.claude/skills
cp -r /tmp/non-coding-skills/cost-optimizer ~/.claude/skills/cost-optimizer

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Token Cost Estimator

The user wants a fast, end-of-conversation gut-check: roughly how many tokens did this
chat burn, what did it cost, and — the real point — was it worth it? The answer they care about is a break-even
wage: the effective hourly cost of having Claude do the task, so they can compare it
to what their own time is worth. This skill closes that feedback loop.

## First: which billing surface is this?

Before anything else, determine how this session is billed — it changes what the final
number *means* and which Optimize levers are real:

- **Subscription surface** (Claude desktop app, Cowork, claude.ai chat): the session runs
  under the user's subscription, not per-token metering. The figure you produce is a
  **hypothetical "what this would have cost via the API"**, translated into usage-limit
  impact. Models can't be switched mid-conversation, so tier advice is forward-looking
  only, and Optimize levers must be actionable in the app (skills, connector hygiene,
  fresh chats, model/effort settings for the *next* chat).
- **API billing** (typical Claude Code CLI, or any session on an API key): the figure is
  a **real bill** — it lands on the Console usage page. Model switching is available
  (`/model`), and Claude Code levers are in scope: `/clear`, starting fresh sessions per
  task, tightening subagent configuration, and `/context`/`/cost` where available.

Tell-tales: the environment/system prompt usually says which surface is running.
Read the full skill on GitHub

Details

Skill name
cost-optimizer
Path
cost-optimizer/SKILL.md
Repo updated
29 October 2026

FAQ

What does the Cost Optimizer skill do?

Estimate the token usage and dollar cost of the CURRENT conversation, then translate it into a break-even wage (effective hourly cost) so the user can judge whether the task was worth it. Use whenever the user asks what a conversation cost, how many tokens it used, "was this worth it", "what's the break-even wage", "effective hourly cost", "run the cost estimate", "/cost", "estimate the tokens", or any end-of-conversation cost check. Also fire when the user is weighing the value they got against what a task cost. Produces an estimate (not a billed figure) with list-price and cache-adjusted cos

How do I install the Cost Optimizer skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ShawhinT/non-coding-skills --skill cost-optimizer. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Cost Optimizer popular?

It lives in ShawhinT/non-coding-skills, which has 39 GitHub stars and 6 forks.

Related skills

Aba Brand System

39

ShawhinT/non-coding-skills

AI Builder Academy's brand and design system — colors, typography, voice/tone, components, icons, and copy patterns for aibuilder.academy and any ABA-branded surface (landing pages, decks, one-pagers, social graphics, emails, motion graphics). Use whenever Shaw is designing, mocking up, or reviewing anything that should look or sound like ABA. Triggers: "design a landing page for ABA", "make an ABA mockup", "one-pager for [ABA offer]", "what colors / font does ABA use", "ABA-ify this", "make this on brand", "what's the ABA voice", "design an ABA banner / hero / card / form", "slide template fo

Frontend & Design

Aba Plugin Updater

39

ShawhinT/non-coding-skills

Prepare a change to Shaw's aba-plugins marketplace repo (the public plugin clients install via /plugin install aba-skills@aba) as a handoff doc for Claude Code, which executes it natively in the repo. Use whenever he wants to edit, fix, or improve one of the plugin's skills (skill-helper, skill-updater, cost-optimizer), repackage dist/, validate the manifests, or land a commit there. Triggers: "update the plugin", "push a change to aba-plugins", "repackage dist", "cut a plugin release", "add this to the aba-skills plugin". Also fire whenever one of those three skill names comes up as something

AI, LLMs & Agents

Animation Builder

39

ShawhinT/non-coding-skills

Build short motion-graphic animations (1–6 seconds) as B-roll overlays for talking-head YouTube videos — icon morphs, label fade-ins, diagrams that draw themselves, side-by-side comparisons, simple flow charts. Use this skill whenever the user asks to create, design, or render an animation, motion graphic, B-roll clip, explainer overlay, or any short visual that needs to be exported as an MP4. Triggers include "make an animation for X", "build a motion graphic", "I need B-roll for this script", "animate the [icon/label/curve/flow]", "render this as a video", "create a short clip that shows X m

Frontend & Design

Email Helper

39

ShawhinT/non-coding-skills

Draft emails in Shaw's voice, and research his Gmail — this skill covers both writing mail and reading it. Use it ANY time Claude is composing or about to compose an email (drafting, replying, forwarding, following up), and ANY time Claude is searching or reading threads to answer a question, verify a fact, or gather context. The trigger is the next tool call: if it is `create_draft`, `search_threads`, `get_thread`, or `label_thread`, this skill should have been invoked first, EVEN when another skill (crm, meeting-prep, outreach, engagements, notion-helper, etc.) is already running and the ema

Productivity & Notes

Client Support

39

ShawhinT/non-coding-skills

Reply to a client or workshop participant about their own Claude work, in Shaw's voice: a how-do-I, an "it's not working" report, a request for tips, a "pick your brain" on quality or process (how do we QA what Claude makes), a question in a check-in, office-hour thread, or client Slack channel, or a check-in reply with no question in it (a status update on what they've built). The trigger is who is writing, not whether they asked something. The channel skill (email-helper, slack-helper) owns delivery and register; the answer's content, the choice between teaching, triaging, and taking it live

Productivity & Notes

Executive Briefing

39

ShawhinT/non-coding-skills

Generate Shaw's daily executive briefing by pulling today's tasks from his main Notion databases. Use this skill whenever Shaw asks for his daily briefing, rundown, what's on his plate, what he has going on today, or anything about reviewing his scheduled tasks for the day. Triggers include: "give me my briefing", "what do I have today", "daily rundown", "executive briefing", "what's on my plate", "what's scheduled today", "morning briefing", "what am I working on today", or any reference to checking tasks across his Notion databases. Even casual mentions like "what's today look like" or "run

Productivity & Notes

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.