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 HKUSTDial/Supervisor-Skills --skill drawio-reconstructiongit clone --depth 1 https://github.com/HKUSTDial/Supervisor-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/hkustdial/supervisor-skills/drawio-reconstruction)<a href="https://agentmods.dev/skills/hkustdial/supervisor-skills/drawio-reconstruction"><img src="https://agentmods.dev/badge/skills/hkustdial/supervisor-skills/drawio-reconstruction/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/hkustdial/supervisor-skills/drawio-reconstruction"><img src="https://agentmods.dev/badge/skills/hkustdial/supervisor-skills/drawio-reconstruction.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 | $0.00102 | $0.04391 |
| Opus 5 | $0.00051 | $0.02195 |
| Sonnet 5 | $0.00020 | $0.00878 |
| Haiku 4.5 | $0.00010 | $0.00439 |
Grade A, and why
drawio-reconstruction 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 11d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
23 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.
- .gitignore 262 B
- agents/openai.yaml 302 B
- assets/cases/data_lake_drawio.png 481 KB
- assets/cases/data_lake_original.png 1259 KB
- assets/cases/data_man_drawio.png 637 KB
- assets/cases/data_man_original.png 1832 KB
- assets/cases/data_sci2_drawio.png 761 KB
- assets/cases/data_sci2_original.png 1757 KB
- examples/data_lake.drawio 371 KB
- examples/data_lake.png 1259 KB
- examples/data_man.drawio 479 KB
- examples/data_man.png 1832 KB
- examples/data_sci2.drawio 407 KB
- examples/data_sci2.png 1757 KB
- LICENSE 1.0 KB
- README.md 8.8 KB
- README.zh-CN.md 8.4 KB
- requirements.txt 13 B
- scripts/batch_manifest.py 4.1 KB runs code
- scripts/batch_verify.py 2.8 KB runs code
- scripts/check_drawio.py 12 KB runs code
- scripts/crop_assist.py 13 KB runs code
- scripts/export_drawio.py 3.3 KB runs code
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.
- 11d ago First seen · 352 lines · 102 tokens per session scan A ccc4e5fa5ccd
drawio-reconstruction is a skill published in the GitHub repository HKUSTDial/Supervisor-Skills (6,814 stars, last pushed 5d ago), with no licence file. It adds 102 tokens to every session and 4,391 once invoked, about $0.0005 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
codex-skin-pack-installer
Install Codex themes and Codex skin packs with npx skills. Use this skill when a user wants Codex to find, download, validate, apply, switch, remix, or restore Codex desktop themes such as caishen-readable, caishen-lite, mythic-guardian-noir, global-founder-bright, export-night, or caishen-max. It stages verified…
separateweb-capture
Capture a URL into a full-page screenshot, cropped UI item PNGs, and a JSON manifest. Use when the user says separateweb capture , asks to capture a website, or wants UI extraction assets without running the SeparateWeb web app.
design-director
A design-planning role for Codex Project Autopilot, a workflow that coordinates project work. It defines the visual direction and interaction approach for a selected project phase.
frontend-ui-ux-system
A company-level guide for designing web interfaces and user experiences. It covers visual styles, design tokens (named values for colors, spacing, and typography), layout, interaction, accessibility, motion, and review checks.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.