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/jtsang4/efficient-coding/i-diagramnpx skills add jtsang4/efficient-coding --skill i-diagramgit clone --depth 1 https://github.com/jtsang4/efficient-codingWhat 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 | $0.00151 | $0.04108 |
| Opus 5 | $0.00076 | $0.02054 |
| Sonnet 5 | $0.00030 | $0.00822 |
| Haiku 4.5 | $0.00015 | $0.00411 |
Grade A, and why
i-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 2d 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagram Generator
Create professional SVG diagrams across multiple diagram types. All output is a single self-contained .svg file with embedded styles and fonts.
Theme Selection
Two themes are supported: light (default) and dark.
- Use the light theme unless the user explicitly asks for dark (e.g. "暗色" "深色主题" "dark mode" "dark theme")
- All colors in this document are defined as theme tokens — pick the column matching the selected theme and use those literals consistently throughout the SVG
- Never mix tokens from both themes in one diagram
Supported Diagram Types
| Type | When to Use | Key Characteristics |
|---|---|---|
| Architecture | System components & relationships | Grouped boxes, connection arrows, region boundaries |
| Flowchart | Decision logic, process steps | Diamond decisions, rounded step boxes, directional flow |
| Sequence | Time-ordered interactions between actors | Vertical lifelines, horizontal messages, activation bars |
| Structural | Class diagrams, ER diagrams, org charts | Compartmented boxes, typed relationships (inheritance, composition) |
| Mind Map | Brainstorming, topic exploration | Central node, radiating branches, organic layout |
| Timeline | Chronological events | Horizontal/vertical axis, event markers, period spans |
| Illustrative | Conceptual explanations, comparisons | Free-form layout, icons, annotations, visual metaphors |
| State Machine | State transitions, lifecycle | Rounded state nodes, labeled transitions, start/end markers |
| Data Flow | Data transformation pipelines | Process bubbles, data stores, external entities |
Design System
All colors below are theme tokens. After selecting the theme, substitute every token with its literal value from the matching column. Token placeholders like {bg}, {text}, {line} appear in code snippets throughout this document and the reference files.
Base Tokens
| Token | Light (default) | Dark | Use For |
|---|---|---|---|
{bg} |
#f8fafc |
#0f172a |
Canvas background, masking rects |
{grid} |
#e2e8f0 |
#1e293b |
Background grid lines |
{text} |
#0f172a |
white |
Primary labels, component names |
{text-sub} |
#64748b |
#94a3b8 |
Sublabels, descriptions, annotations |
{text-msg} |
#334155 |
#e2e8f0 |
Message/arrow labels |
{line} |
#64748b |
#64748b |
Default arrows, connection lines |
{line-soft} |
#94a3b8 |
#334155 |
Lifelines, dividers, subtle lines |
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.
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.
- 2d ago First seen · 274 lines · 151 tokens per session scan A ca3fd0a616b0
i-diagram is a skill published in the GitHub repository jtsang4/efficient-coding (2 stars, last pushed 7d ago), licensed MIT. It adds 151 tokens to every session and 4,108 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
visual-acceptance
UI/视觉改动交付前的终验方法论——多主题截图矩阵复现、像素真值判据链、CSS 层叠陷阱、布局漂移审查、before/after 存证。当视觉改动需要验收（而非实现）时使用：交付前最后一环，回答「看得见的部分真的对吗」。.
frame-bold-poster
A 1970s European editorial poster in motion — a red rule draws across, a giant tilted figure drops in, a three-line headline rises line-by-line, an italic serif standfirst fades.
frame-data-chart-nyt
NYT-newsroom typography, staggered reveal animation, and editorial-grade charts (line, bar, or range band).
frame-build-minimal
Luxury-minimal whitespace hero — single word reveals letter by letter, warm-gold hairline, breathing indicators.
frame-creative-voltage
Electric split with hand-drawn script — offset panels slide in, display title rises with an outlined word, script strokes itself in.
frame-electric-studio
Two-panel split with quote as hero — white/blue panels open from center, accent bar grows, quote reveals line by line.