squadai: Skill for Claude Code

.claude/skills/sdd/sdd-design/SKILL.md

sdd-design is a skill for Claude Code from PedroMosquera/squadai. It costs 12 tokens per session (565 once invoked), scanned A, original, MIT.

A design guide for turning a software specification into an architecture. It defines modules, interfaces, data movement, diagrams, and error handling before coding starts.

In plain words
What is it for?
Breaking systems into modules, defining how components communicate, mapping inputs and outputs, and deciding how errors move through the system.
Why use it?
It makes the system's boundaries and contracts clear, reducing confusion and costly structural changes later.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is PedroMosquera/squadai's own configuration. It tells Claude Code how to work on squadai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything squadai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to PedroMosquera/squadai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/PedroMosquera/squadai/main/.claude/skills/sdd/sdd-design/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/PedroMosquera/squadai

Made for: Claude Code.

Wrote 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.

agentmods badge for sdd-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/pedromosquera/squadai/sdd-design/github.svg)](https://agentmods.dev/skills/pedromosquera/squadai/sdd-design)
Your own site
<a href="https://agentmods.dev/skills/pedromosquera/squadai/sdd-design"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/sdd-design/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.

agentmods 80×15 button for sdd-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/pedromosquera/squadai/sdd-design"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/sdd-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 565 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00565
Opus 5 $0.00006 $0.00282
Sonnet 5 $0.00002 $0.00113
Haiku 4.5 $0.00001 $0.00056

Measured 9d ago against content hash 2f1f28d5a6a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sdd-design 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 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.

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.

.claude/skills/sdd/sdd-design/SKILL.md · 91 lines

What it actually says

SDD Design Skill

Translate a specification into a concrete architecture. Define module boundaries, interface contracts, and data flow before any code is written.

Steps

  1. Identify modules: Break the system into coherent units.

    • Each module should have a single responsibility
    • Modules communicate through defined interfaces (not direct access)
    • Internal implementation of each module is hidden from others
  2. Define interfaces: Specify the contract between modules.

    • Interface name and methods with full signatures
    • Which module implements each interface
    • Which modules consume each interface
    • Avoid leaking implementation details through interfaces
  3. Design data flow: Map how data moves through the system.

    • Input sources and entry points
    • Transformation steps
    • Storage points (databases, files, caches)
    • Output destinations
  4. Draw architecture diagrams: Use text-based diagrams.

    [Input] → [Parser] → [Validator] → [Processor] → [Output]
                                             ↓
                                        [Storage]
    
  5. Specify error propagation: Define how errors flow.

    • Which errors are recoverable vs fatal?
    • Where are errors wrapped with context?
    • Which errors bubble up to the caller vs are handled locally?
    • Sentinel error values for expected failures
  6. Identify extension points: Design for known future needs.

    • Where will new implementations be added (registry, plugin patterns)?
    • Which interfaces should be kept minimal to avoid coupling?
    • What should remain internal to allow refactoring?
  7. Validate against the spec: Check each design decision against constraints.

    • Does the design satisfy all interface contracts in the spec?
    • Does it meet non-functional requirements?
    • Is it testable (can dependencies be injected or mocked)?

Output Format

## Design: <feature name>

### Module Structure
- **<module>**: <responsibility>
  - Implements: <interface>
  - Depends on: <interfaces>

### Interfaces

#### <InterfaceName>
```go
type InterfaceName interface {
    Method(param Type) (ReturnType, error)
}

Implemented by: Consumed by:

Data Flow

[source] → [module] → [module] → [destination]

Error Handling

Error Type Where handled How propagated

Architecture Diagram

<ASCII diagram>

Design Decisions

  1. :
Changes

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.

  1. 9d ago First seen · 91 lines · 12 tokens per session scan A 2f1f28d5a6a0

Subscribe to this mod's changes

sdd-design is a skill published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 565 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 2026-08-31.

Related

Other skills, from other repositories

harness-engineering

Use when the user asks to improve, fix, or build their repository's AI harness — AGENTS.md, rules, skills, commands, hooks, guardrails, CI sensors — or to act on harness-score audit findings and raise their maturity level.

paladini/harness-score · 55 tokens

reap

Report how much of the context this agent loads is never used - unused skills, MCP servers, subagents, hooks and always-loaded prose - measured from real session transcripts. Use when asked why the context window is full, what is wasting tokens, or what is safe to remove.

thousandflowers/skillreaper · 56 tokens

gap

Measure the loaded-versus-fired gap - what fraction of each category of loaded context is ever actually invoked, and which MCP tools return mostly noise. Use when asked how much of the context is earning its place, or which categories are worst.

thousandflowers/skillreaper · 48 tokens

replay

Find, analyze, and share AI coding sessions with vibe-replay. Use when the user asks for a replay, wants to find a past session, run a session retro, share Cursor/Claude/Codex session context, or attach session context to a PR.

tuo-lei/vibe-replay · 56 tokens

skill-doctor

Use the skill-doctor CLI or UI to inspect and manage AI-agent skills, rules, instructions, MCP resources, and context cost across supported platforms. Trigger when the user asks to scan or audit agent skills, find duplicates or trigger conflicts, investigate unsafe instructions, estimate context-token cost, compare…

evilstar2016/skill-doctor · 103 tokens

skill-doctor-context-optimizer

Interactively keep the skills, MCP servers/tools, and plugins relevant to the user's current task, preview project-local disables for the rest, apply only explicitly confirmed controls through skill-doctor, and report approximate context-token savings. Trigger when the user asks to slim, optimize, prune, or reduce the…

evilstar2016/skill-doctor · 79 tokens