What is autosearch:model-routing?

Guidance for choosing among Fast, Standard, and Best model tiers for different research tasks. It advises the runtime AI but does not change models itself.

Labeling research steps with a suggested tier and deciding when to move to a stronger or simpler model.

It helps match routine work with cheaper models while reserving stronger models for tasks such as clarification, planning, and evaluation.

autosearch:model-routing — Skill for Claude Code by 0xmariowu

Install

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.

Any agent

npx skills add 0xmariowu/Autosearch --skill model-routing

Clone the repo

git clone --depth 1 https://github.com/0xmariowu/Autosearch

Made for: Claude Code.

Or install autosearch, the plugin that ships this one along with the rest of its 55 skills, 1 agent.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/0xmariowu/autosearch/model-routing/github.svg)](https://agentmods.dev/skills/0xmariowu/autosearch/model-routing)

Your own site

<a href="https://agentmods.dev/skills/0xmariowu/autosearch/model-routing"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/model-routing/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/0xmariowu/autosearch/model-routing"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/model-routing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,356 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00068	$0.01356
Opus 5	$0.00034	$0.00678
Sonnet 5	$0.00014	$0.00271
Haiku 4.5	$0.00007	$0.00136

Measured 10d ago against content hash 2b84c941d078, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

autosearch:model-routing 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (__init__.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

autosearch/skills/meta/model-routing/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Tier Routing — Advisory

Routing principle: most steps use the runtime's cheapest model; only the critical 1–2 steps use the best model.

Autosearch stamps every leaf skill with a model_tier suggestion. This skill tells the runtime AI what the three tiers mean, which skills default to which tier, and when to escalate or de-escalate.

Three Tiers

Tier	Typical runtime pick	When used	Share of skills
Fast	Claude Haiku / GPT-5-mini / Gemini 2.5 Flash / Qwen local	Retrieval, normalization, schema checks, URL reading, metadata	~60%
Standard	Claude Sonnet / GPT-5.4 / Gemini 2.5 Pro	Semantic ranking, evidence extraction, mid-complexity planning	~25%
Best	Claude Opus / GPT-5 / Gemini 2.5 Ultra	Clarify, decompose, synthesize, evaluate delivery, skill evolution — the 1-2 steps that shape everything	~15%

Tier Assignments

Each autosearch skill carries model_tier: Fast|Standard|Best in its frontmatter. The runtime AI reads that field before choosing which provider/model to call.

Best (~13 skills — the critical 1-2 steps per session)

clarify — disambiguate intent (wrong clarification cascades)
systematic-recall — global recall planning (missed angles compound)
decompose-task — breaking a multi-part problem
synthesize-knowledge — produce frameworks, not link lists
evaluate-delivery — quality gate on final output
knowledge-map — cross-evidence relation graph
check-rubrics / generate-rubrics — rubric-driven evaluation
auto-evolve / create-skill — anything that changes future behavior
goal-loop — multi-round goal convergence
graph-search-plan (when present) — research plan as graph
perspective-questioning (when present) — multi-persona question generation
reflective-search-loop (when present) — explicit gaps / visited / bad-URLs loop

Standard (~20 skills — semantic judgment, structurable)

select-channels — pick 5-10 channels from 41
gene-query — combinatorial query generation
consult-reference — prior art lookup
rerank-evidence — semantic ranking of results
llm-evaluate — per-item relevance score
anti-cheat — spam / score-gaming detection
assemble-context — token-budgeted context assembly
extract-knowledge — structured extraction from text
fetch-crawl4ai / fetch-playwright / fetch-firecrawl / follow-links
experience-compact — rule promotion
observe-user — user preference inference
research-mode — speed vs. deep choice
delegate-subtask (when present) / trace-harvest / citation-index / recent-signal-fusion
interact-user / pipeline-flow / outcome-tracker

Read the full file on GitHub · 105 lines

Files

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.

__init__.py 397 B runs code

Changes

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.

10d ago First seen · 105 lines · 68 tokens per session scan A 2b84c941d078

Subscribe to this mod's changes

autosearch:model-routing is a skill published in the GitHub repository 0xmariowu/Autosearch (44 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 1,356 once invoked, about $0.0003 per session on Opus 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.

Building agents agentic-search chinese-search claude-code-plugin deep-research mcp-server research-agent

sanity-best-practices

Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, and the App SDK. Use this…

sanity-io/agent-toolkit · 164 tokens

portable-text-serialization

Render and serialize Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, and plain text. Use when implementing Portable Text rendering in any frontend framework, building custom serializers for non-standard block types, converting Portable Text to HTML strings server-side, converting Portable Text to Markdown…

sanity-io/agent-toolkit · 85 tokens

autosearch:model-routing