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 staruhub/CrewClaw --skill model-selectorgit clone --depth 1 https://github.com/staruhub/CrewClawWrote 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/staruhub/crewclaw/model-selector)<a href="https://agentmods.dev/skills/staruhub/crewclaw/model-selector"><img src="https://agentmods.dev/badge/skills/staruhub/crewclaw/model-selector/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/staruhub/crewclaw/model-selector"><img src="https://agentmods.dev/badge/skills/staruhub/crewclaw/model-selector.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 | $0.00029 | $0.00216 |
| Opus 5.5 | $0.00012 | $0.00086 |
| Sonnet 5.5 | $0.00006 | $0.00043 |
| Haiku 4.5 | $0.00003 | $0.00022 |
Grade A, and why
model-selector 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 1mo 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
Model Selector
Overview
Give a model selection recommendation with explicit trade-offs — not "use the biggest model," but the right model for the scenario across capability, cost, compliance, and latency.
When to Use
When the user is picking an LLM for a product/feature and needs a defensible choice with reasons.
Workflow
- Clarify the scenario: task type, quality bar, budget, latency need, compliance / data-residency constraints.
- Compare 2-3 candidate models across four axes: capability, cost, compliance, latency.
- Recommend one with the trade-off stated ("X over Y because …, at the cost of …").
- Mark any price/benchmark number that needs verification as a [placeholder].
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.
- 1mo ago First seen · 25 lines · 29 tokens per session scan A f51df9f582fc
model-selector is a skill published in the GitHub repository staruhub/CrewClaw (24 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 216 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
pro-ppt
A presentation-making workflow that turns a speech or slide content into images for polished business-style slides. It first plans each slide and then generates the slide images.
zootopia-ppt
A presentation-making workflow that turns a speech or slide content into images showing an animated world of human-like animals. It first plans each slide and then generates the slide images.
kanban-tasks
A task-board workflow for breaking work into cards and moving them through stages such as inbox, ready, doing, review, and done. It also includes a background service and a web interface for the board.
flint-chart-author
A guide for turning structured data, such as tables or query results, into Flint chart specifications. Flint is a visualization format that describes the data, chart type, and visual mappings for rendering.
ocr
OCR image files using the Qwen VL model via the bundled scripts/ocr.py (lives in this skill's directory, NOT your cwd). Use when the user asks to extract text from an image, perform OCR on a photo or screenshot, or recognize characters in an image file (.jpg, .jpeg, .png, .gif, .webp). Requires QWENAPIKEY and…
daily-digest
Build a daily digest from curated sources. Follow the output contract strictly.