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 experience-capturegit 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/experience-capture)<a href="https://agentmods.dev/skills/0xmariowu/autosearch/experience-capture"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/experience-capture/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/experience-capture"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/experience-capture.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 | $0.00068 | $0.01181 |
| Opus 5 | $0.00034 | $0.00590 |
| Sonnet 5 | $0.00014 | $0.00236 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
autosearch:experience-capture 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
experience-capture — Per-Skill Event Writer
Appends one line of JSON per skill execution to <skill_dir>/experience/patterns.jsonl.
Why This Skill Exists
Each autosearch leaf skill is treated as a small project that grows over time. Every time the runtime AI calls a skill, this capture skill logs what the call looked like and whether it worked, so the companion experience-compact skill can later promote recurring winning patterns into experience.md.
Three independent files per leaf skill:
autosearch/skills/channels/<skill>/
SKILL.md # static, versioned via git
experience.md # compacted digest (≤120 lines, read by runtime before calling skill)
experience/
patterns.jsonl # append-only raw events, grows, archived monthly
archive/YYYY-MM.jsonl # monthly-rotated archives
Event Schema
One JSON object per line:
{
"ts": "2026-04-22T08:15:00+08:00",
"session_id": "<session-id or null>",
"skill": "search-xiaohongshu",
"group": "channels-chinese-ugc",
"task_domain": "product-research",
"query_type": "recent-user-opinion",
"input_shape": "brand + feature + 近30天",
"method": "tikhub:xhs_search",
"environment": {"auth": "paid", "locale": "zh-CN"},
"outcome": "success",
"metrics": {
"yield": 18,
"relevant": 9,
"unique_sources": 7,
"latency_ms": 4200,
"cost_usd": 0.02,
"user_feedback": "accepted"
},
"winning_pattern": "品牌词 + 痛点词 + 近30天 比 '评测' 召回更准",
"failure_mode": null,
"good_query": "某品牌 某功能 翻车 2026",
"bad_query": null,
"evidence_refs": [],
"promote_candidate": true,
"notes": "适合和 search-douyin 交叉验证"
}
Invocation Pattern
The runtime AI calls this skill after executing any leaf channel / fetch / transcription skill:
capture_event({
"skill": "search-xiaohongshu",
"task_domain": "product-research",
"outcome": "success", # or "failure" or "partial"
"metrics": {...},
"good_query": "...",
"notes": "..."
})
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 · 127 lines · 68 tokens per session scan A 079c9da14a54
autosearch:experience-capture 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 1,181 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.
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.