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 xiaohei-info/oh-my-multica --skill software-design-lifecycle-tech-detailed-technical-arch-diagramminggit clone --depth 1 https://github.com/xiaohei-info/oh-my-multicaWrote 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/xiaohei-info/oh-my-multica/software-design-lifecycle-tech-detailed-technical-arch-diagramming)<a href="https://agentmods.dev/skills/xiaohei-info/oh-my-multica/software-design-lifecycle-tech-detailed-technical-arch-diagramming"><img src="https://agentmods.dev/badge/skills/xiaohei-info/oh-my-multica/software-design-lifecycle-tech-detailed-technical-arch-diagramming/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/xiaohei-info/oh-my-multica/software-design-lifecycle-tech-detailed-technical-arch-diagramming"><img src="https://agentmods.dev/badge/skills/xiaohei-info/oh-my-multica/software-design-lifecycle-tech-detailed-technical-arch-diagramming.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 | $0.00050 | $0.06553 |
| Opus 5 | $0.00025 | $0.03277 |
| Sonnet 5 | $0.00010 | $0.01311 |
| Haiku 4.5 | $0.00005 | $0.00655 |
Grade A, and why
software-design-lifecycle-tech-detailed-technical-arch-diagramming 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 12d 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 — 658 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Detailed Technical Architecture Diagramming
Overview
This skill now directly contains the merged specialist doctrine that previously lived in the legacy technical-architecture skill.
Integrated Legacy Specialist Doctrine (Preserved and Merged)
Technical Architecture Diagramming
Overview
This is the architect-private skill for drawing and reviewing 技术架构图 in the 详细设计 stage.
It is deliberately built as a two-layer skill:
- Full-fidelity drawing grammar is preserved intact in the reference file:
references/universal-arch-lifecycle-tech-detailed-technical-arch-diagramming-spec-full.md
- Architect-specific lifecycle method and review gates are added in this umbrella skill:
- where 技术架构图 sits in the architecture lifecycle
- what detailed-design questions it must answer
- how to separate it from neighboring artifacts
- how to convert solution intent into concrete technical realization
- how to review stability, operability, security, and runtime collaboration before implementation
Core principle: 技术架构图 is not a prettier system diagram. It is the detailed-design artifact that explains how the approved solution is concretely realized through technology stack, runtime units, middleware, storage, project structure, execution paths, and reliability controls.
This skill exists because many so-called “技术架构图” fail in one of five ways:
- they are only system architecture diagrams with product names sprinkled on top
- they are only deployment diagrams, showing hosts/clusters but not technical realization logic
- they are only flow/sequence diagrams, showing time order but not stable runtime structure
- they list middleware names but do not explain why these choices exist or how components collaborate
- they compress away drawing details, causing future diagrams to drift in shape/line/color semantics and lose consistency
Use this skill when you need a technology-realization artifact that is detailed enough to guide implementation, review, interface design, non-functional design, and operations handoff.
What ships with it
6 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.
- references/architecture-vs-flowchart-smells.md 3.0 KB
- references/source-basis.md 1.7 KB
- references/universal-technical-architecture-diagramming-spec-full.md 40 KB
- references/verbatim-user-draft-技术架构图Skill.md 40 KB
- references/worked-example-backend-microservice.md 7.9 KB
- references/worked-example-event-driven-pipeline.md 7.4 KB
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.
- 12d ago First seen · 658 lines · 50 tokens per session scan A f9e0e3067493
software-design-lifecycle-tech-detailed-technical-arch-diagramming is a skill published in the GitHub repository xiaohei-info/oh-my-multica (26 stars, last pushed 5d ago), licensed MIT. It adds 50 tokens to every session and 6,553 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
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.