autosearch:channel-selection

autosearch:channel-selection is a skill for Claude Code from 0xmariowu/Autosearch. It costs 87 tokens per session (1,977 once invoked), scanned A, original, MIT.

An algorithm that first chooses relevant research topic groups and then selects specific research channels within them. It is part of an automated research system.

In plain words
What is it for?
Selecting one to three topic groups and three to eight research channels from a clarified query, while applying language, freshness, and skip preferences.
Why use it?
It reduces the amount of routing information the runtime AI must inspect when choosing where to search, which can save time and context.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the autosearch plugin — 55 skills, 1 agent shipped together

Good fit Selecting one to three topic groups and three to eight research channels from a clarified query, while applying language, freshness, and skip preferences.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/0xmariowu/autosearch/channel-selection
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 channel-selection
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.

agentmods badge for autosearch:channel-selection

README.md
[![agentmods](https://agentmods.dev/badge/skills/0xmariowu/autosearch/channel-selection/github.svg)](https://agentmods.dev/skills/0xmariowu/autosearch/channel-selection)
Your own site
<a href="https://agentmods.dev/skills/0xmariowu/autosearch/channel-selection"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/channel-selection/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.

agentmods 80×15 button for autosearch:channel-selection

Your own site · 80×15
<a href="https://agentmods.dev/skills/0xmariowu/autosearch/channel-selection"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/channel-selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,977 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Tool Misuse · line 80
    Tool defaults are unsafe or overly permissive (e.g. disabled TLS verification, no authentication, world-writable permissions). Unsafe defaults widen the attack surface.
    Fix: Override unsafe defaults with secure settings (verify=True, auth required, restrictive permissions). Review and harden all tool configurations.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.01977
Opus 5 $0.00044 $0.00988
Sonnet 5 $0.00017 $0.00395
Haiku 4.5 $0.00009 $0.00198

Measured 10d ago against content hash 1034042d38fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

autosearch:channel-selection 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/channel-selection/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Channel Selection — Group-First Algorithm

Runtime AI calls this after run_clarify and before run_channel. Produces a ranked list of leaf channels to invoke, using the progressive-disclosure structure from autosearch:router + 14 group index files.

Why Group-First

Flat ranking across 41 channels means reading 41 SKILL.md bodies and scoring each. Group-first reduces the decision to:

  1. Pick 1-3 groups (from the 14 group index descriptions — short, already cached).
  2. Within picked groups, pick 3-8 leaf channels (leaf metadata is short and already in each group index).

Token savings: ~80% over flat-rank. Latency savings: sub-second at Standard tier vs. ~5s at Best tier for 41-way scoring.

Input

input:
  query: str                          # user's research question
  clarify_result:                     # from run_clarify
    mode: "fast" | "deep" | "comprehensive"
    query_type: str
    rubrics: list[str]
    channel_priority: list[str]        # clarifier's hint
    channel_skip: list[str]            # clarifier's anti-hint
  scope:                               # optional
    languages: "all" | "en_only" | "zh_only" | "mixed"
    recency: "any" | "7d" | "30d" | "90d"
    budget:
      max_channels: int                # hard cap, default 8
      max_groups: int                  # hard cap, default 3
      max_cost_usd: float | null

Algorithm

Stage 1 — Group Selection (≤ 3 groups)

Score each of the 14 groups against the query + rubrics:

Factor Weight How to score
Domain match 0.35 query entities / rubric keywords intersect group domains + keyword-hint map in autosearch:router
Scenario match 0.25 clarify.query_type matches any group scenarios
Language match 0.15 query language alignment with group's typical surface (chinese-ugc / cn-tech groups boost zh queries; community-en boosts en)
Clarifier priority overlap 0.15 proportion of channel_priority entries that belong to this group
Recency compatibility 0.10 recency-sensitive groups (chinese-ugc / channels-community-en / channels-video-audio) boost when scope.recency <= 30d

Read the full file on GitHub · 186 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.

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.

  1. 10d ago First seen · 186 lines · 87 tokens per session scan A 1034042d38fc

Subscribe to this mod's changes

autosearch:channel-selection is a skill published in the GitHub repository 0xmariowu/Autosearch (44 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 1,977 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

prior-art-search

Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification.

RobThePCGuy/Claude-Patent-Creator · 26 tokens

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

development-assistant

Guides through adding new features, MCP tools, analyzers, and extending the patent creator system.

RobThePCGuy/Claude-Patent-Creator · 24 tokens

mpep-search

Expert system for searching USPTO MPEP, 35 USC statutes, 37 CFR regulations, and post-Jan 2024 updates.

RobThePCGuy/Claude-Patent-Creator · 32 tokens

video-perception

Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.

jordanrendric/claude-video-vision · 51 tokens