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/othmanadi/mddesign/design-bridgenpx skills add OthmanAdi/MDDesign --skill design-bridgegit clone --depth 1 https://github.com/OthmanAdi/MDDesignWrote 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/othmanadi/mddesign/design-bridge)<a href="https://agentmods.dev/skills/othmanadi/mddesign/design-bridge"><img src="https://agentmods.dev/badge/skills/othmanadi/mddesign/design-bridge.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 5.1 | $0.00080 | $0.01254 |
| Opus 5 | $0.00040 | $0.00627 |
| Sonnet 5 | $0.00016 | $0.00251 |
| Haiku 4.5 | $0.00008 | $0.00125 |
Grade A, and why
design-bridge 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Bridge
Runtime companion. Lives between DESIGN.md and findings.md.
When you (Claude) should run this skill
You are running this skill when ANY of the following is true:
- The active phase in
task_plan.mdmentions UI keywords (button, card, modal, layout, color, typography, spacing, dialog, navigation, form, input, page, screen, theme, brand, design, component, header, footer, sidebar, hero, cta). - The user just asked you to build, change, or review a UI element.
- The PreToolUse hook fired before a
WriteorEditagainst a file matching*.tsx|*.jsx|*.vue|*.svelte|*.html|*.css|*.scss. - The user explicitly ran
/mddesign:inject.
What to do
Step 1: Detect DESIGN.md
- Glob for
DESIGN.mdat the project root (CWD). - If absent, do nothing. Surface a one-line note ONLY if the user explicitly invoked the skill: "No DESIGN.md found at project root. Run
/mddesign:harvestto generate one from your codebase."
Step 2: Detect the relevant token slice
- Read
DESIGN.mdonce. - Identify the token categories the current task touches. Heuristics:
- "button|cta|link" → components.button, colors.primary, colors.secondary, typography (button), rounded
- "card|panel|tile" → components.card, colors.surface, rounded, spacing
- "modal|dialog|overlay" → components.modal, colors.surface, rounded, elevation
- "form|input|field" → components.input, colors.border, typography (body), rounded
- "color|theme|palette" → all colors
- "type|font|heading" → all typography
- "layout|grid|spacing" → spacing scale, layout section
- default → colors (primary, secondary), typography (heading, body)
Step 3: Find the existing "## Design Context" block in findings.md
- Read
findings.md. - Look for a section header
## Design Context(case-sensitive). - If absent, you will append a fresh block.
- If present, you will replace the block contents.
Step 4: Build the new block
The block format:
## Design Context
> Auto-injected by MDDesign on <ISO timestamp>. Source: DESIGN.md.
> Phase trigger: <phase id or "manual">
### Tokens in scope
<bulleted list of token references with values, format `colors.primary = #3B82F6`>
### Component specs in scope
<for each touched component, copy its spec from DESIGN.md verbatim>
### Do's and Don'ts (relevant excerpt)
<copy the relevant Do/Don't lines from DESIGN.md if any>
> If you stray from these tokens, name the deviation explicitly in findings.md before writing code.
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 · 113 lines · 80 tokens per session scan A 8315491dfe69
design-bridge is a skill published in the GitHub repository OthmanAdi/MDDesign (13 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,254 once invoked, about $0.0004 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
kanban-orchestrator
Kanban orchestrator: decompose, route, verify. No executing.
review
M-1.5 review skill — 在 patch 跟 contract 之间找 finding，produce Finding 一等对象。.
fix-self-check
M-1.6 envelope self-check——独立性保证不自欺欺人 (5 blockingcheck)。由 CLI ./tw fix complete --self-check-mode fork(默认即 fork)自动派起,不经 Skill 工具调用;fix 主会话产 FixCompleted 前直读本文,是为理解双层验证关系。.
plan-decompose
从 completioncondition + conceptgraph 递归分解出 primitive task 提案。主 planner session 决定接受/调整/拆得更细。.
review-plan-creator
我在设计阶段（不是 review 真正发生时）产 reviewplan——因为只有设计者知道 task 的完整 intent picture + 隐含约束 + 长期演化方向。只有设计者能写 VoI criteria（什么样的 finding 在某 dimension 下是有效的）。.
downtime-recovery
停机后复工的标准安全流程（水位线追平/积压泄流/服务分批重启）。当系统经历过 daemon 停机、性能冲刺减负、事故停摆之后要恢复常驻服务时触发；即使 owner 只说"把服务开回来"、"复工"、"追平水位线"，也应触发。核心使命：绝不让"重启"变成"积压喷发"（2026-07-04 实锤：orchestrator 停机后水位线落后 3240 条，直接重启把机器负载打到 22+，owner 被迫立即紧急关停）。.