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 ngocsangyem/MeowKit --skill tech-graphgit clone --depth 1 https://github.com/ngocsangyem/MeowKitWrote 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/ngocsangyem/meowkit/tech-graph)<a href="https://agentmods.dev/skills/ngocsangyem/meowkit/tech-graph"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/tech-graph/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/ngocsangyem/meowkit/tech-graph"><img src="https://agentmods.dev/badge/skills/ngocsangyem/meowkit/tech-graph.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 | $0.00088 | $0.01313 |
| Opus 5 | $0.00044 | $0.00656 |
| Sonnet 5 | $0.00018 | $0.00263 |
| Haiku 4.5 | $0.00009 | $0.00131 |
Grade B, and why
mk:tech-graph scanned grade B with 1 finding 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 9d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt install librsvg2-bin # Debian/Ubuntu How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech Graph
Generate production-quality SVG technical diagrams, optionally exported as PNG.
Route by Intent
- Choose a diagram type or UML notation: load diagram catalog.
- Choose semantic shapes, arrow meanings, or layout rules: load visual vocabulary and layout.
- Choose a style: load style matrix, then Style 1, Style 2, Style 3, Style 4, Style 5, Style 6, Style 7, or Style 8; default to Style 1.
- Use product icons: load icons.
- Author SVG, prevent syntax errors, or recover from errors: load SVG authoring and recovery.
- Need SVG syntax/layout validation detail: load SVG layout best practices.
Workflow
- Classify the request with the diagram catalog; extract layers, nodes, edges, flows, and groups.
- Load the selected style reference. Style 8 requires hand-authored SVG; do not use the template generator.
- Load visual vocabulary/layout guidance, map nodes and arrows, and use a legend for two or more arrow types.
- Generate with the relevant helper: run
python3 .claude/skills/tech-graph/scripts/generate-from-template.pyfor supported templates, or runpython3 .claude/skills/tech-graph/scripts/generate-svg-from-lines.py <output.svg>and pipe SVG lines to stdin for hand-authored output. - Run
bash .claude/skills/tech-graph/scripts/validate-svg.sh <output.svg>. If available, runrsvg-convert <output.svg> -o /dev/nullas an additional check. - Check
rsvg-convertbefore PNG export. When absent, keep the SVG and report the install hint; never auto-install or fail the task. - If image reading is available, inspect the exported PNG and correct collisions, overflow, crossings, or covered legends before delivery.
What ships with it
34 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.
- fixtures/agent-memory-types-style4.json 4.5 KB
- fixtures/api-flow-style7.json 3.3 KB
- fixtures/mem0-style1.json 7.8 KB
- fixtures/microservices-style3.json 5.2 KB
- fixtures/multi-agent-style5.json 3.9 KB
- references/diagram-catalog.md 5.5 KB
- references/icons.md 15 KB
- references/style-1-flat-icon.md 3.2 KB
- references/style-2-dark-terminal.md 3.0 KB
- references/style-3-blueprint.md 3.3 KB
- references/style-4-notion-clean.md 2.8 KB
- references/style-5-glassmorphism.md 3.8 KB
- references/style-6-claude-official.md 6.9 KB
- references/style-7-openai.md 6.8 KB
- references/style-8-dark-luxury.md 7.7 KB
- references/style-diagram-matrix.md 7.6 KB
- references/svg-authoring-and-recovery.md 2.8 KB
- references/svg-layout-best-practices.md 3.8 KB
- references/visual-vocabulary-and-layout.md 3.5 KB
- scripts/generate-diagram.sh 5.2 KB runs code
- scripts/generate-from-template.py 64 KB runs code
- scripts/generate-svg-from-lines.py 911 B runs code
- scripts/test-all-styles.sh 4.0 KB runs code
- scripts/validate-svg.sh 8.3 KB runs code
- templates/agent-architecture.svg 1.3 KB
- templates/architecture.svg 1.0 KB
- templates/comparison-matrix.svg 612 B
- templates/data-flow.svg 1.3 KB
- templates/er-diagram.svg 1003 B
- templates/flowchart.svg 860 B
- templates/sequence.svg 856 B
- templates/state-machine.svg 846 B
- templates/timeline.svg 832 B
- templates/use-case.svg 947 B
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.
- 9d ago First seen · 96 lines · 88 tokens per session scan B 56b642c8b589
mk:tech-graph is a skill published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,313 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
svg-press
Teaches agents how to hand-craft self-contained SVG diagrams that render correctly in browsers, tags, and Playwright PDF/PNG. Covers containment math, viewBox sizing, arrow construction, text hierarchy, KDCube brand color tokens, semantic zone fills, badges, the PNG inspection loop, writepng parameters, multi-diagram…
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
code-to-diagram
Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts. Uses AST parsing to map import dependencies for Python, JS/TS, Go, and Java, outputting Mermaid or SVG files. Triggered when users ask to visualize code architecture, understand dependencies, draw a flowchart, or create a…
fin-arch-diagram
A tool for creating architecture diagrams, process flowcharts, and hierarchy trees. These show how system parts, business steps, decisions, or organizational levels relate to one another.
pptx-press
Teaches agents how to author slide-structured HTML that renders professionally to PPTX via writepptx, with proper sizing, styling, brand and domain-adaptive color schemes, SVG diagram integration, citation handling, deck narrative flow, and content budgets for business presentations, technical decks, and executive…
mermaid
Teaches agents how to write syntactically correct Mermaid diagrams that render without errors across all supported diagram types. Covers quoting rules, common syntax pitfalls, diagram-type-specific syntax (flowchart, sequence, class, ER, Gantt, state, pie, mindmap), subgraphs, styling with classDef and theme…