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 perspective-questioninggit 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/perspective-questioning)<a href="https://agentmods.dev/skills/0xmariowu/autosearch/perspective-questioning"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/perspective-questioning/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/perspective-questioning"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/perspective-questioning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.00974 |
| Opus 5 | $0.00039 | $0.00487 |
| Sonnet 5 | $0.00016 | $0.00195 |
| Haiku 4.5 | $0.00008 | $0.00097 |
Grade A, and why
autosearch:perspective-questioning 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perspective Questioning — Multi-Persona Question Generation
Before searching, enumerate 3-6 relevant personas for the research topic and ask each persona "what would you want to know?". The union of those questions becomes the research scope.
STORM originally used this for Wikipedia-style article generation. autosearch uses it to widen the coverage of a query before decomposition / channel selection.
Persona Catalog (starting points)
Runtime AI picks 3-6 from the list that match the query's domain:
- End user — what does it feel like? what's the most common pain point?
- Power user — edge cases, advanced features, integration patterns.
- Maintainer — design tradeoffs, known issues, roadmap.
- Security researcher — attack surface, CVEs, hardening.
- Investor / business analyst — market position, funding, revenue model.
- Regulator / compliance — licensing, data handling, disclosure.
- Competitor — differentiation, feature comparison, pricing.
- New user — onboarding friction, docs clarity.
- Journalist — recent events, controversies, PR statements.
- Academic — published research, theoretical basis, citations.
Output
perspectives:
- persona: "security researcher"
rationale: "Query involves a new ML framework; attack surface is non-trivial."
questions:
- "What authentication mechanism does X use?"
- "Are there known CVEs or advisories for X?"
- "Does X have a security policy and disclosure channel?"
- persona: "end user"
rationale: "Users are the primary audience of the final report."
questions:
- "What's X's learning curve?"
- "What are the most-complained-about workflows?"
# ... 1-4 more personas
union_questions: list[str] # deduped merge of all persona questions
Usage Policy
- Minimum 3 personas, maximum 6. Fewer than 3 → fall back to
decompose-task. More than 6 → cost not justified for most tasks. - Skip personas whose rationale is weak. Don't force "Journalist" onto a pure code-architecture query just because the catalog has it.
- Do NOT generate persona answers here — this skill only generates the question set. Channel calls + synthesis happen downstream.
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 · 94 lines · 78 tokens per session scan A 08710ff245d7
autosearch:perspective-questioning is a skill published in the GitHub repository 0xmariowu/Autosearch (44 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 974 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
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…
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.
prior-art-search
Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification.
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.