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 rules/sordi-ai/skill-everything/drawiogit clone --depth 1 https://github.com/sordi-ai/skill-everythingWhat 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 | $0.00016 | $0.00507 |
| Opus 5 | $0.00008 | $0.00253 |
| Sonnet 5 | $0.00003 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
drawio 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 3d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sub-Skill: Diagrams (draw.io / Mermaid)
Purpose: Ensure diagrams are version-controlled as source, rendered consistently, and kept in sync with the system they describe.
Rules
Source Control
- Commit source, not just exports. Always commit diagram source files (
.drawio,.mmd,.puml) alongside or instead of rendered image exports. Reference: ERR-2026-027 - No binary-only diagrams. Never commit only a PNG or SVG export without the editable source; reviewers cannot diff or modify a raster image.
- One source file per diagram. Use a single canonical source file per diagram; avoid duplicating the same diagram in multiple formats.
Format Selection
- Prefer diagram-as-code. Prefer Mermaid or PlantUML over draw.io XML when the diagram fits a supported diagram type; text diffs are reviewable.
- Match diagram type to content. Use
sequenceDiagramfor request flows,flowchartfor decision logic,C4Context/C4Containerfor architecture,erDiagramfor data models. - Set layout direction explicitly. Always declare layout direction (
LR,TD) in Mermaid flowcharts; never rely on the default, which varies by renderer.
Rendering Pipeline
- Document the render command. Always include the render command or CI step in the repo README or Makefile so any contributor can regenerate exports.
- Regenerate exports in CI. Ensure CI regenerates diagram exports from source and fails if the committed export differs from the generated one.
- Pin renderer version. Always pin the Mermaid CLI or draw.io CLI version in CI to prevent silent rendering changes across upgrades.
Quality & Consistency
- Use consistent node naming. Always use the same label for the same system component across all diagrams in the repo; divergent names cause confusion.
- Add alt text to exported images. Always add descriptive alt text to diagram images embedded in documentation for accessibility.
- Review diagrams in PRs. Before merging, verify that any diagram change accurately reflects the system change described in the PR.
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.
- 3d ago First seen · 44 lines · 16 tokens per session scan A 5a40e72e8109
drawio is a cursor rule published in the GitHub repository sordi-ai/skill-everything (19 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 507 once invoked, about $0.0001 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 cursor rules, from other repositories
00-stack
Stack, runtimes, and MCP servers for this repository.
20-testing
How to run tests and MCP smoke checks.
30-security
Secrets, gitleaks, age encryption, telemetry redaction.
obsidian-memory
Markdown vault memory protocol (vkm-kit).
10-style
Style conventions and contribution hygiene.
retention-predictor
Skill — retention-predictor. Predicts retention potential via usage frequency, habit formation mechanics, and churn risk factors.