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 hxy91819/mason-skills --skill tech-doc-htmlgit clone --depth 1 https://github.com/hxy91819/mason-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/hxy91819/mason-skills/tech-doc-html)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/tech-doc-html"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/tech-doc-html/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/hxy91819/mason-skills/tech-doc-html"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/tech-doc-html.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 | $0.00023 | $0.02901 |
| Opus 5.5 | $0.00009 | $0.01160 |
| Sonnet 5.5 | $0.00005 | $0.00580 |
| Haiku 4.5 | $0.00002 | $0.00290 |
Grade A, and why
tech-doc-html 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 1mo 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Design HTML Visualization
Turn technical design content into vivid, interactive single-file HTML pages that help readers understand system design quickly.
仅在用户显式调用 $tech-doc-html 时运行。
Core principles
- Interaction first — Not static document prettification; use interaction so readers can explore technical concepts hands-on
- Single-file, open directly — Inline CSS/JS; complex diagrams may use Mermaid via CDN (see chart selection and security below)
- Serves understanding — Every interaction and animation must serve the goal of helping readers understand
- Fixed identity, free layout — Color and font tokens are the shared visual identity (use them consistently); page structure, section composition, and layout are designed fresh for each document's content
Workflow
Step 1: Analyze the technical design
Read the user's technical design document and identify information types:
- System architecture / component relationships
- Algorithm or mechanism explanations
- Multi-option comparisons
- Data flows / request paths
- Implementation steps / milestones
- Risk assessment
- Key metrics / performance data
- Terminology-heavy concept explanations
Step 2: Choose visualization + interactive components
The table below is a menu of proven options, not an assignment — combine entries, adapt them, or invent components not listed here. The deciding criterion is always "does this help the reader understand", not table coverage.
| Information type | Recommended component | Interaction |
|---|---|---|
| Architecture / deployment / sequence / state machine | Mermaid (preferred) | Static diagram; node details in sidebar text |
| Complex data flow / multi-branch process | Mermaid flowchart | Same as above |
| Few nodes + must click diagram | SVG flowchart + sidebar (§8) | Click node for details |
| Algorithm / mechanism | Interactive SVG diagram (§9) | Slider adjusts params in real time |
| Option comparison | Comparison table | good/bad coloring + hover highlight |
| Implementation steps | Timeline / milestones | Collapsible code sections |
| Simple flow animation accent | SVG lines (§11) | Dashed CSS flow animation |
| Risk assessment | Risk matrix table | Severity color codes (HIGH/MED/LOW) |
| Key metrics | Summary metric bar | Top-of-page overview |
| Terminology | Sticky glossary sidebar | Hover-linked highlight |
| Multi-perspective explanation | Tab panels | Click to switch views |
| Process demo | Step highlight | "Next step" button highlights progressively |
What ships with it
10 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.
- agents/openai.yaml 284 B
- assets/example_output.html 32 KB
- README.md 4.4 KB
- references/component_patterns.md 25 KB
- references/design_system.md 8.9 KB
- references/mermaid_security.md 7.3 KB
- scripts/qa/check_runtime.mjs 4.6 KB runs code
- scripts/qa/screenshot.mjs 3.6 KB runs code
- scripts/security/check_mermaid_insecure_config.py 5.1 KB runs code
- scripts/security/check_mermaid_syntax.mjs 3.2 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.
- 1mo ago Changed · +2 lines a6e0e23de6c6
- 1mo ago Changed · +2 lines e98ffa79e5fd
- 2mo ago Changed · +3 lines · -27 tokens per session a13b8a424cfd
- 2mo ago First seen · 220 lines · 50 tokens per session scan A aa2f46ce3a85
tech-doc-html is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 2,901 once invoked, about $0.0001 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.
tech-doc-html compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tech-doc-htmlhxy91819/mason-skills | Skill | 3 | today | MIT | A | 23 | Claude Code, Codex |
| kami-landingnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 81 | Claude Code, Codex |
| applying-brand-guidelinesanthropics/claude-cookbooks | Skill | 54k | 3d ago | MIT | A | 27 | Claude Code, Codex |
| html-ppt-obsidian-claude-gradientnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| surfsense-htmlMODSetter/SurfSense | Skill | 17k | today | Apache-2.0 | A | 89 | Claude Code, Codex |
| kamitw93/Kami | Skill | 12k | 3d ago | MIT | A | 78 | Claude Code |
| readtw93/Waza | Skill | 7.5k | 6d ago | MIT | A | 61 | Claude Code |