Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add frankxai/claude-skills-library --skill cost-aware-llm-pipelinegit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/frankxai/claude-skills-library/cost-aware-llm-pipeline)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/cost-aware-llm-pipeline"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/cost-aware-llm-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/cost-aware-llm-pipeline"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/cost-aware-llm-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00377 |
| Opus 5.5 | $0.00020 | $0.00151 |
| Sonnet 5.5 | $0.00010 | $0.00075 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
cost-aware-llm-pipeline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
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-daemonwhen 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.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 34 lines · 50 tokens per session scan A aa513139d6e9
cost-aware-llm-pipeline is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 377 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
Other skills, from other repositories
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
prompt-refiner
Lints an existing user-supplied prompt for prompt-engineering defects and prompt-injection risks. Produces a diagnostic report with rule IDs, severity, line/column, quoted evidence, rationale, and optional JSON output. Does not rewrite prompts or impose prompt frameworks.
prompt-modeler
Generate structured strategic prompts with diagnostic and multiple options. Triggers on: /modelar-prompt.
guidance
Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.
prompt-library
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.
outlines
Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library.