New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Cost

by Houseofmvps in Houseofmvps/ultraship

AI Build Cost Tracker — track how much AI is costing you per feature.

MITAuto-check: notesDevelopment

Install Cost

skills CLI
$ npx skills add Houseofmvps/ultraship --skill cost -a claude-code

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

GitHub CLI
$ gh skill install Houseofmvps/ultraship cost --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/Houseofmvps/ultraship.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cost .claude/skills/cost && 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
GitHub stars
123
Token cost
~1.1k tokens
SKILL.md length
551 words
Files
1
Skills in repo
28
Repo updated
First seen
Licence
MIT

At a glance

AI Build Cost Tracker — track how much AI is costing you per feature.

  • Works in 6 steps: Show Current State → Cost Dashboard → Cost Insights → …
  • User wants to track AI spending
  • SKILL.md covers Process, Logging Guide and Key Principles
  • Calls node

What it does

Cost is an agent skill from Houseofmvps/ultraship. AI Build Cost Tracker — track how much AI is costing you per feature. Use when user wants to track AI spending, understand cost per feature, optimize AI usage, or budget their Claude/GPT costs.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering LLM cost and token optimization. The repository describes itself as: "ULTRASHIP" Claude Code plugin — 39 skills, 33 tools, 11 agents for ship-ready workflows: planning, review, pentesting, safety guardrails, canary monitoring, SEO/AI-readiness… The licence is MIT.

When your agent uses it

  • User wants to track AI spending
  • Understand cost per feature
  • Optimize AI usage
  • Budget their Claude/GPT costs

Example prompts

  • “/cost”

Requirements

  • Pre-approved tools (allowed-tools): Bash, Read, Write, Grep

Workflow steps

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

  1. Show Current State
  2. Cost Dashboard
  3. Cost Insights
  4. Logging New Costs
  5. Recommendations
  6. Build vs. Buy Framework

What it can do on your machine

Read from SKILL.md and the folder at commit ed232cb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Read
    • Write
    • Grep

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • node

    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 loads about 1.1k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 551 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, Grep

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 Houseofmvps/ultraship at commit ed232cb, republished under its MIT licence (© Houseofmvps). 551 words, ~1,072 tokens.

Download SKILL.mdSave it as .claude/skills/cost/SKILL.md (or your agent's skills folder).
name
cost
description
AI Build Cost Tracker — track how much AI is costing you per feature. Use when user wants to track AI spending, understand cost per feature, optimize AI usage, or budget their Claude/GPT costs.
allowed-tools
Bash, Read, Write, Grep

AI Build Cost Tracker

Know exactly what each feature costs to build with AI. Budget smarter, spend less.

Process

Phase 1: Show Current State
bash
node ${CLAUDE_PLUGIN_ROOT}/tools/cost-tracker.mjs <project-directory> show

Parse the JSON output for cost history and summary.

Phase 2: Cost Dashboard

Present spending overview:

Total Spend:

  • All-time total cost
  • This week / this month breakdown
  • Average cost per task

By Task/Feature:

  • Ranked list of features by cost (most expensive first)
  • Flag any outliers (tasks costing 3x+ the average)

By Model:

  • Cost breakdown by AI model used
  • Potential savings from model switching

Daily Trend:

  • Last 30 days of daily spending
  • Identify high-spend days
Phase 3: Cost Insights

Generate actionable insights:

  1. Where money goes — what types of tasks cost the most (debugging? features? refactoring?)
  2. Optimization opportunities — tasks that could use a cheaper model
  3. Budget projection — at current rate, monthly spend estimate
  4. Cost per line of code — rough estimate based on git diff
Phase 4: Logging New Costs

To log a new cost entry:

bash
node ${CLAUDE_PLUGIN_ROOT}/tools/cost-tracker.mjs <project-directory> log "<label>" <input_tokens> <output_tokens> --model=claude-opus-4-6

Labels should be descriptive kebab-case: auth-feature, bug-fix-login, refactor-api, seo-optimization

Phase 5: Recommendations

Based on spending patterns:

If debugging > 30% of spend:

  • "Consider investing in more tests upfront — debugging is your biggest cost driver"
  • Suggest running /test-driven-development skill

If a single task > 3x average:

  • "The [task] cost $X — consider breaking large tasks into smaller chunks"

Model optimization:

  • "Routine refactoring with Sonnet instead of Opus would save ~$X/month"
  • "Code review tasks can use Haiku — potential savings of ~$X/month"

Logging Guide

Help the user understand when and how to log costs:

  • Log at the END of each task/feature (not during)
  • Use consistent labels across sessions
  • Include ALL tokens (input + output) from the conversation
  • Estimate if exact numbers aren't available (Claude Code shows token usage in the UI)
Show full SKILL.md (267 more words)Show less
Phase 6: Build vs. Buy Framework

When reviewing cost data, help the user think about the economics of building with AI:

Worth building with AI (high ROI):

  • Features that would take 2+ days manually but 2 hours with AI
  • Boilerplate-heavy work (CRUD, migrations, test suites, API endpoints)
  • Exploration and prototyping (try 3 approaches, keep the best one)

Consider alternatives:

  • If a feature costs >$100 in AI tokens, check if a library or SaaS already does it
  • If debugging the same issue costs >$20 in AI tokens, the root cause is architectural — fix the architecture, not the symptom
  • If AI-generated code needs significant manual correction, the prompt needs work, not more tokens

Cost benchmarks for solo founders:

Task TypeExpected CostIf Higher, Investigate
New API endpoint$1-5Complex business logic or unclear spec
Bug fix$0.50-3Missing tests or hard-to-reproduce issue
Full feature (frontend + backend)$5-20Large scope or frequent rework
Refactoring$2-10Unclear boundaries or missing tests
Content/copy generation$0.25-1Too many revision cycles

Key Principles

  • AI is an investment, not a cost. The goal isn't to minimize spend — it's to maximize ROI. A $50 feature that generates $5K MRR is a great investment. But a $50 bug fix that should have cost $5 with better tests is waste.
  • Track to learn, not to punish. Cost data reveals where your process is inefficient. High debugging costs mean insufficient tests. High rework costs mean unclear specs.
  • Optimize the expensive tasks, not the cheap ones. Switching from Opus to Haiku for a $0.10 task saves nothing. Reducing a $50 debugging session by improving test coverage saves real money.

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

Files

Just SKILL.md in skills/cost of Houseofmvps/ultraship.

Open the folder on GitHubat commit ed232cb

Compare with similar skills

Cost 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cost this skillHouseofmvps/ultraship123—~1.1kAutomated safety check: NotesMIT
LobeHub Alint Rule Set Maintenancelobehub/lobehub83k—~1.9kAutomated safety check: PassCustom licence
Levyra Context EfficiencyLUC4N3X/Levyra-deepsound533—~1.3kAutomated safety check: NotesGPL-3.0
Docs Impact Classifiermicrosoft/apm4k—~1.8kAutomated safety check: PassMIT
Token Efficiencyrohitg00/pro-workflow2.9k—~1kAutomated safety check: PassNone
Skill Reviewermicrosoft/GitHub-Copilot-for-Azure255—~482Automated safety check: PassMIT

Similar skills

  • LobeHub Alint Rule Set Maintenance

    lobehub/lobehub

    Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.

    83k GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed

  • Levyra Context Efficiency

    LUC4N3X/Levyra-deepsound

    A skill your agent uses for genuinely high-volume Levyra work such as builds, tests, lint, logs, broad searches, dependency output, Git/GitHub or CodeRabbit inspection, CI diagnostics, agent setup…

    533 GitHub stars~1.3k tokensUpdated today
    DevelopmentAuto-check: notes

  • Docs Impact Classifier

    microsoft/apm

    Official

    A skill your agent uses to classify the documentation impact of a pull request diff, returning one of three verdicts -- no-change, in-place edit, or structural change -- with bounded LLM cost.

    4k GitHub stars~1.8k tokensUpdated yesterday
    DevelopmentAuto-check passed

  • Token Efficiency

    rohitg00/pro-workflow

    Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement.

    2.9k GitHub stars~1k tokensUpdated 10 days ago
    DevelopmentAuto-check passed

  • Skill Reviewer

    microsoft/GitHub-Copilot-for-Azure

    Official

    Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, and repo conventions.

    255 GitHub stars~482 tokensUpdated today
    DevelopmentAuto-check passed

  • Speckit Token Budget Compact

    haru/redmine_ai_helper

    Compact one or more Spec-Driven Development artifacts in place to reduce token cost on subsequent /speckit.

    106 GitHub stars~1.8k tokensUpdated today
    DevelopmentAuto-check passed

More from Houseofmvps/ultraship

All 28 skills in this repo

  • Using Ultraship

    Houseofmvps/ultraship

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    123 GitHub stars~2.2k tokensUpdated 3 mo ago
    Auto-check passed

  • A11y

    Houseofmvps/ultraship

    Accessibility audit + auto-fix (WCAG 2.2 A/AA). An agent skill from Houseofmvps/ultraship.

    123 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check: notes

  • Architecture

    Houseofmvps/ultraship

    Living Architecture Map — auto-generate Mermaid diagrams of your codebase.

    123 GitHub stars~708 tokensUpdated 3 mo ago
    Auto-check: notes

  • Clone Patterns

    Houseofmvps/ultraship

    Learn From the Best — analyze patterns from any codebase and apply them to yours.

    123 GitHub stars~682 tokensUpdated 3 mo ago
    Auto-check: notes

  • Code Review

    Houseofmvps/ultraship

    Code review with principal-engineer-level depth. An agent skill from Houseofmvps/ultraship.

    123 GitHub stars~1.5k tokensUpdated 3 mo ago
    Auto-check passed

  • Compete

    Houseofmvps/ultraship

    Competitive X-Ray — analyze any competitor URL vs your site.

    123 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check: notes

Categories

Questions about Cost

What does Cost do?

AI Build Cost Tracker — track how much AI is costing you per feature. Cost is an agent skill from Houseofmvps/ultraship. AI Build Cost Tracker — track how much AI is costing you per feature.

When should I use Cost?

Cost fits situations like: user wants to track AI spending; understand cost per feature; optimize AI usage; budget their Claude/GPT costs.

How do I install Cost in Claude Code?

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

How do I install Cost in Codex?

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

Can I use Cost 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 Houseofmvps/ultraship --skill cost -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, .gemini/skills/cost, .github/skills/cost and .opencode/skills/cost in your project.

What does Cost need to run?

Going by SKILL.md and its folder, Cost needs the command-line tools its instructions call (node). Its frontmatter pre-approves these tools: Bash, Read, Write, Grep.

Does Cost 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 safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Cost use?

Cost 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 use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cost?

Skills that share tags, products or a category with Cost: LobeHub Alint Rule Set Maintenance (lobehub/lobehub, 83k stars), Levyra Context Efficiency (LUC4N3X/Levyra-deepsound, 533 stars), Docs Impact Classifier (microsoft/apm, 4k stars) and Token Efficiency (rohitg00/pro-workflow, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cost?

Houseofmvps (a GitHub user) maintains it in Houseofmvps/ultraship, which has 123 GitHub stars. The repository holds 28 skills in this directory. The repository was last updated on July 8, 2026.

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