Skill Compose is an open-source platform for building and running AI agents that use modular skills. It is intended for creating skill-powered agents without workflow graphs or a command-line interface, and the catalogue skills are examples of those agent capabilities.
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 agentmods add skills/dp-archive/archive/code-to-diagramnpx skills add dp-archive/archive --skill code-to-diagramgit clone --depth 1 https://github.com/dp-archive/archiveWrote 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/dp-archive/archive/code-to-diagram)<a href="https://agentmods.dev/skills/dp-archive/archive/code-to-diagram"><img src="https://agentmods.dev/badge/skills/dp-archive/archive/code-to-diagram.svg" alt="Measured on agentmods" 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 | $0.00103 | $0.01026 |
| Opus 5 | $0.00051 | $0.00513 |
| Sonnet 5 | $0.00021 | $0.00205 |
| Haiku 4.5 | $0.00010 | $0.00103 |
Grade A, and why
code-to-diagram 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 5d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code to Diagram
Generate production-quality diagrams from source code via Mermaid.js, rendered to SVG/PNG with mmdc.
Environment
Executor required: This skill needs the diagram executor (Chromium + Node.js + mmdc pre-installed).
If mmdc is not available, install first:
npm install -g @mermaid-js/mermaid-cli
Puppeteer config for headless environments — create at /tmp/puppeteer-config.json if missing:
{"args": ["--no-sandbox", "--disable-setuid-sandbox"]}
Workflow
- Analyze — Read the codebase to understand structure (
glob,grep,read) - Plan — Decide diagram type(s) based on user request and code patterns
- Generate — Write
.mmdfile with Mermaid syntax - Render — Run
mmdcto produce SVG and PNG - Verify — Read the output image and check correctness
Diagram Type Selection
| User Intent | Diagram Type | Mermaid Keyword |
|---|---|---|
| System overview, module layout | Architecture | graph TD + subgraph |
| Database tables, ORM models | ER Diagram | erDiagram |
| API flow, request lifecycle | Sequence Diagram | sequenceDiagram |
| Inheritance, interfaces | Class Diagram | classDiagram |
| Business logic, conditionals | Flowchart | flowchart TD |
| Task states, lifecycle | State Diagram | stateDiagram-v2 |
| Import/dependency tree | Dependency Graph | graph LR |
| Timeline, project phases | Gantt Chart | gantt |
Analysis Strategy
Do NOT read every file. Use progressive analysis:
Step 1 — Directory scan:
glob("**/*.py") or glob("**/*.ts") to understand module structure.
Step 2 — Entry points:
- Python:
main.py,app.py,__init__.py,pyproject.toml - Node.js:
package.json,index.ts,app.ts - Java:
pom.xml,Application.java
Step 3 — Targeted reads by diagram type:
- ER → ORM models (
models.py,schema.prisma,*.entity.ts) - Architecture → Router registrations, dependency injection, config
- Sequence → Specific endpoint handler + service call chain
- Class → Class definitions via
grep("class ")
What ships with it
1 file 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.
- 5d ago First seen · 105 lines · 103 tokens per session scan A ef75fc67e6dd
code-to-diagram is a skill published in the GitHub repository dp-archive/archive (1,106 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 103 tokens to every session and 1,026 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…