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 VectorPeak/vectorpeak-agent-skills --skill xiaohei-daily-query-vpgit clone --depth 1 https://github.com/VectorPeak/vectorpeak-agent-skillsWrote 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/vectorpeak/vectorpeak-agent-skills/xiaohei-daily-query-vp)<a href="https://agentmods.dev/skills/vectorpeak/vectorpeak-agent-skills/xiaohei-daily-query-vp"><img src="https://agentmods.dev/badge/skills/vectorpeak/vectorpeak-agent-skills/xiaohei-daily-query-vp/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/vectorpeak/vectorpeak-agent-skills/xiaohei-daily-query-vp"><img src="https://agentmods.dev/badge/skills/vectorpeak/vectorpeak-agent-skills/xiaohei-daily-query-vp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00094 | $0.00641 |
| Opus 5.5 | $0.00038 | $0.00256 |
| Sonnet 5.5 | $0.00019 | $0.00128 |
| Haiku 4.5 | $0.00009 | $0.00064 |
Grade A, and why
xiaohei-daily-query-vp 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 2mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xiaohei Daily Query
Core Rule
Before every user request, fetch the latest API Markdown document from:
GET http://192.168.11.212:8088/
Do not rely on a memorized endpoint list. Read the live Markdown, parse the available endpoint paths, methods, parameters, request examples, and response shape, then choose the correct endpoint for the user's request.
Supported User Intents
Handle natural-language requests for:
- Work timeline records for a date or date range.
- Work reports for a date or date range, returned as Markdown content.
- Hourly heat-map data for a date range.
- App usage duration summaries for a date or date range.
If the user does not specify a date, omit startDate and endDate so the service uses its current default. For timeline, report, and app usage this normally means today; for heat-map this normally means the recent default window described in the live docs.
Use YYYY-MM-DD dates unless the user explicitly asks for a precise time range.
Recommended Script
Use the bundled helper:
& "C:\Users\ZXY\.cache\codex-runtimes\codex-primary-runtime\dependencies\python\python.exe" `
"C:\Users\ZXY\.codex\skills\xiaohei-daily-query-vp\scripts\query_xiaohei.py" `
--intent report --start-date 2026-06-29 --end-date 2026-06-29
The script always fetches GET / first, extracts the live GET endpoints from the Markdown, maps the requested intent to the currently documented path, calls the selected endpoint, validates the unified JSON envelope, and prints a compact Markdown summary.
Intent values:
timelinereportheat-mapapp-usage
The script also accepts --query for lightweight natural-language intent detection:
& "<python>" "<skill>\scripts\query_xiaohei.py" --query "查一下今天应用使用时长"
Response Style
Summarize the returned data directly for the user:
- For reports, preserve useful Markdown report content and mention report titles/date ranges.
- For timelines, group records by time and category.
- For heat maps, highlight focus minutes, active period, top category, and hourly distribution if relevant.
- For app usage, convert seconds into readable hours/minutes and list apps in returned order.
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.
- 2mo ago First seen · 66 lines · 94 tokens per session scan A c7192b150923
xiaohei-daily-query-vp is a skill published in the GitHub repository VectorPeak/vectorpeak-agent-skills (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 94 tokens to every session and 641 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
live-transcript-summary
A real-time note-taking skill that watches audio transcription in the current WPS note and periodically organizes it. WPS is an office and note-taking application.
content-digest
A skill for turning supplied material into structured knowledge notes and saving them to WPS Notes, a note-taking service.
tag-organize-cli
A command-line workflow for organizing file-level tags in WPS Notes, a cloud note-taking service. It uses the wpsnote-cli program and does not require an MCP server connection.
tag-organize
A workflow for organizing file-level tags in WPS Notes, a cloud note-taking service. It uses note statistics, tag searches, note details, note searches, and tag-management tools.
note-calendar
A macOS workflow connecting WPS Notes with the system Calendar. It can query, create, move, and delete calendar events, and link notes and calendar items in both directions.
audhd-executive-function
AUDHD executive function accommodations. Apply to all output the founder will act on.