Least Cost Capable
Compare declared relative cost ranks among catalogued agent models after checking task capability, availability, authorization, workload, and cost evidence.
Install
npx skills add kanibal-studio/least-cost-capable --skill least-cost-capablegit clone --depth 1 https://github.com/kanibal-studio/least-cost-capable.git /tmp/least-cost-capable
mkdir -p ~/.claude/skills
cp -r /tmp/least-cost-capable/. ~/.claude/skills/least-cost-capablePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Least-cost capable model selection Compare candidates in the user's supplied catalogue. This is a decision aid based only on supplied facts; it does not establish the completeness or truth of the catalogue, promise actual savings, call providers, spend credits, change settings, or launch agents. 1. Define the task's required capabilities from the requested work and risk. Treat capability claims as supplied evidence, not as assumptions based on model names. 2. Treat only explicit `true`/`false` availability and authorization as known. Unknown or omitted values stay unresolved. A candidate marked unavailable or unauthorized is excluded with that reason. 3. Treat a capability list as complete only when the catalogue explicitly says so. Missing or incomplete lists remain unresolved; a missing capability excludes a candidate only when its list is confirmed complete. Never infer capability from a model name. 4. Compare relative rank only when each capable candidate supplies the same metric, unit, workload, and observation window, plus a source and `as_of` date. API input-token cost and output-token cost are different metrics; currency cost, provider credits, and quota units are not interchangeable. Missing, stale per the user's own freshness requirement, or conflicting evidence remains unknown. Do not browse or invent prices to fill gaps.
Details
- Skill name
least-cost-capable- Repository
- kanibal-studio/least-cost-capable
- License
- MIT
- Repo updated
- 24 October 2026
- Listed in
- karanb192/awesome-claude-skills
FAQ
What does the Least Cost Capable skill do?
Compare declared relative cost ranks among catalogued agent models after checking task capability, availability, authorization, workload, and cost evidence.
How do I install the Least Cost Capable skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add kanibal-studio/least-cost-capable --skill least-cost-capable. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Related skills
Orchestrating Subagents
PapiScholz/symphony
Use when about to spawn one or more subagents, agent teams, or a workflow — a single delegated search, a parallel fan-out, or a repeated batch — and whenever choosing which model a delegated task runs on instead of letting it inherit yours. Also use when writing or editing a .claude/agents definition, when a delegated run hit a rate limit or cost more than expected, or when a subagent came back after far more or far fewer turns than the work warranted.
Fresh Review
roman-s8o/workflow-pack-free
Review an artifact with an independent agent that has no access to the author's reasoning, then classify its findings.
Reels Setup
VishiATChoudhary/reels
Use when setting up, installing or onboarding the reels studio (github.com/VishiATChoudhary/reels), when a user or agent wants to start making story reels with it, or when its setup is broken (missing whisper-cli, model, yt-dlp, ffmpeg, node deps). Clones, installs, verifies, and stars the repo (one [Y/n] prompt).
Aeo Check
pchewlo/aeo-check
Run aeo-check on a website's code (or a live URL) to find answer engine optimisation problems that stop ChatGPT, Claude, Perplexity, Gemini and Google AI Overviews from crawling, understanding, citing or buying from the site, then fix them. Use when asked to check or improve AEO, GEO, AI search visibility, llms.txt, robots.txt for AI crawlers, structured data, or agent readiness.
Session Handoff
alapha888/session-handoff-kit
Use this skill when context usage approaches capacity (>60%), before running /clear or /compact, when switching tasks, when ending a coding session across Claude Code, Cursor, or Codex, or as a mid-session diagnostic — if the agent cannot fill the handoff fields from actual state, the session has drifted. Produces a structured handoff artifact that transfers execution state to a fresh agent session without loss of context or drift.
Stipend
1stipend-sh/stipend
A non-custodial USDC wallet on Base that an AI agent installs by itself, with spending limits enforced in the signing path rather than in a prompt. Receive payments, pay HTTP 402 / x402 charges automatically, and answer whether you are worth running. No account and no API key: the only approval needed is from the person who runs you.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.