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 0xmariowu/Autosearch --skill channel-selectiongit clone --depth 1 https://github.com/0xmariowu/AutosearchWrote 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/0xmariowu/autosearch/channel-selection)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00087 | $0.01977 |
| Opus 5 | $0.00044 | $0.00988 |
| Sonnet 5 | $0.00017 | $0.00395 |
| Haiku 4.5 | $0.00009 | $0.00198 |
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.
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.
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:
- Pick 1-3 groups (from the 14 group index descriptions — short, already cached).
- 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 |
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.
- 10d ago First seen · 186 lines · 87 tokens per session scan A 1034042d38fc
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.
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.
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…
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…
development-assistant
Guides through adding new features, MCP tools, analyzers, and extending the patent creator system.
mpep-search
Expert system for searching USPTO MPEP, 35 USC statutes, 37 CFR regulations, and post-Jan 2024 updates.
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.