Cost Aware LLM Pipeline
Pick the smallest model that can finish the task, and record the class of work. Use when routing a search, a multi-file edit, or an architecture review, or when a weekly model cap is close.
Install
/plugin marketplace add frankxai/claude-skills-libraryThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add frankxai/claude-skills-library --skill cost-aware-llm-pipelinegit clone --depth 1 https://github.com/frankxai/claude-skills-library.git /tmp/claude-skills-library
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills-library/absorbed/harness/cost-aware-llm-pipeline ~/.claude/skills/cost-aware-llm-pipelinePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Route the model to the job One chair still runs the session. A cheaper model is a worker for a bounded task, not a second orchestrator. | Work | Model class | | --- | --- | | Search, file lookup, doc summary | The faster smaller model | | Multi-file edits and tests | Sonnet class | | Architecture, security review, public or priced copy | Opus class | ## Rules - Do not start an unbounded local loop because a weekly cap is close. Cap the iterations in the prompt and stop. - Do not install a token proxy or a second memory store as part of routing. - Do not send private receipts, `reality.md`, or the Queen inbox to a worker. - If the same mistake is being retried, stop and write the failure down. Another model call is not a fix. - Codex on this machine needs `--no-daemon` when a Claude session calls it. Leave the Stop-hook review gate off. ## Note to leave Write one line: task class, model used, and whether the result was kept. That line is the cost record. Do not invent a dollar figure. ## Where this came from The tiered-model idea follows affaan-m/ECC `skills/cost-aware-llm-pipeline` at `4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2` (MIT). The chair rule, the cap, and the privacy list are estate law. Built on SIP.
Details
- Skill name
cost-aware-llm-pipeline- Repository
- frankxai/claude-skills-library
- Path
absorbed/harness/cost-aware-llm-pipeline/SKILL.md- License
- MIT
- Repo updated
- 18 November 2026
FAQ
What does the Cost Aware LLM Pipeline skill do?
Pick the smallest model that can finish the task, and record the class of work. Use when routing a search, a multi-file edit, or an architecture review, or when a weekly model cap is close.
How do I install the Cost Aware LLM Pipeline skill?
Claude Code plugin: /plugin marketplace add frankxai/claude-skills-library. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Cost Aware LLM Pipeline popular?
It lives in frankxai/claude-skills-library, which has 48 GitHub stars and 6 forks.
Related skills
Acos Meta
48frankxai/claude-skills-library
ACOS self-description and configuration skill. Documents how ACOS works, how to extend it, how to add new skills/commands/agents, and how to debug the hook system. Use when building new ACOS capabilities, understanding the system architecture, or onboarding to ACOS for the first time.
Acos Visual Gen
48frankxai/claude-skills-library
Generate research-grounded visuals using the InfoGenius pipeline. Use when creating infographics, diagrams, educational visuals, or any image that benefits from factual accuracy. Supports 8 visual styles (3D, technical, minimalist, photorealistic, futuristic, vintage, cartoon, standard) and 4 audience levels.
Agent Harness Construction
48frankxai/claude-skills-library
Shape an agent's tools, observations, and recovery without adding a second coordinator. Use when defining a tool, a skill, a hook, or a worktree lane.
Creator Intelligence
48frankxai/claude-skills-library
Transform Claude Code into your personal Jarvis - an AI operating system that knows your projects, preferences, and workflows across sessions. Use this skill when setting up personal AI systems, building context-aware assistants, or creating persistent memory across projects.
Context Budget
48frankxai/claude-skills-library
Count what a session loads before adding another skill or MCP server. Use when the default prompt is heavy, a new server is about to be enabled, or a skill has never been invoked.
Creator Meta
48frankxai/claude-skills-library
Creator-agnostic operating-system substrate. The abstract layer model + decision tree + brand-discipline framework that any creator can inherit and specialize. Use when designing a new creator's repo structure, asking 'what layer does X belong to?', booting a new creator's Claude Code config, or reasoning about the creator-tooling stack independent of any specific creator. Trigger phrases: creator meta, creator system map, creator OS, what layer does X go in, creator layer model, generalize for creators, bootable creator skill.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.