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 shikidmsh-rgb/mochibot --skill perceptiongit clone --depth 1 https://github.com/shikidmsh-rgb/mochibotWrote 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/shikidmsh-rgb/mochibot/perception)<a href="https://agentmods.dev/skills/shikidmsh-rgb/mochibot/perception"><img src="https://agentmods.dev/badge/skills/shikidmsh-rgb/mochibot/perception/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/shikidmsh-rgb/mochibot/perception"><img src="https://agentmods.dev/badge/skills/shikidmsh-rgb/mochibot/perception.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 | $0.00026 | $0.00246 |
| Opus 5 | $0.00013 | $0.00123 |
| Sonnet 5 | $0.00005 | $0.00049 |
| Haiku 4.5 | $0.00003 | $0.00025 |
Grade A, and why
perception 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 7d 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.
What it actually says
Tools
look_around (resident)
读取 Observer 最近一次内存缓存的安全投影。省略 sources 或传空数组时返回所有已发现来源的概览；指定 1–3 个来源时按请求顺序返回详情。
| Parameter | Type | Required | Description |
|---|---|---|---|
| sources | array (items: string) | no | 可选来源名，最多 3 个且不可重复；空数组表示所有来源概览 |
Capability Context
look_around只读取 Observer 已有缓存的安全投影，不是摄像头、截图、GPS 或实时设备查看，也不会触发采集。- 返回值会标明来源、缓存时间、是否过期和不可用原因；读取不会改变 Attention 的 unresolved 状态。
- 它只提供结构化事实，不会自动写入 Core、Memory Items、Diary、Todo 或 Reminder。
What ships with it
2 files 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.
- 7d ago Changed · +5 lines · +14 tokens per session 996e80bad4d2
- 12d ago First seen · 18 lines · 12 tokens per session scan A 8faf287062ef
perception is a skill published in the GitHub repository shikidmsh-rgb/mochibot (83 stars, last pushed 5d ago), licensed MIT. It adds 26 tokens to every session and 246 once invoked, about $0.0001 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
wecom-mcp-doc
A connection for working with WeCom documents and smart spreadsheets, including their content, columns, rows, and uploaded files. WeCom is the enterprise messaging and collaboration service made by Tencent.
wecom-doc-manager
A Chinese-language tool guide for creating, reading, and editing WeCom documents and smart tables. WeCom is an enterprise messaging and collaboration platform; the guide uses document IDs or URLs to locate files.
wecom-preflight
A pre-call check for WeCom, an enterprise messaging and collaboration platform, before using its document or smart-table tools.
ai-boyfriend
A dating service for AI agents on inbed.ai that matches profiles by personality compatibility and supports conversations between matched agents. It is framed around finding a virtual boyfriend.
wecom-smartsheet-data
A skill for managing rows in WeCom smart tables, which are shared online tables inside WeCom documents.
wecom-smartsheet-schema
A tool for managing the structure of WeCom smart spreadsheets. It works with spreadsheet tabs and fields, which are the columns that define what each row stores.