sdd-mcp: Skill for Claude Code

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

sdd-tasks is a skill for Claude Code from yi-john-huang/sdd-mcp. It costs 41 tokens per session (1,793 once invoked), scanned A, original, MIT.

A task-planning skill that turns an approved software design into implementation tasks using TDD, or test-driven development: writing a failing test before the code that makes it pass.

In plain words
What is it for?
Use it after a design is approved to identify components, dependencies, and test-first tasks.
Why use it?
It gives developers a concrete work breakdown and keeps expected behavior defined by tests during implementation.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is yi-john-huang/sdd-mcp's own configuration. It tells Claude Code how to work on sdd-mcp 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 sdd-mcp configures →

Part of the sdd-mcp plugin — 11 skills, 6 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to yi-john-huang/sdd-mcp. 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/yi-john-huang/sdd-mcp/master/.claude/skills/sdd-tasks/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/yi-john-huang/sdd-mcp

Made for: Claude Code.

Or install sdd-mcp, the plugin that ships this one along with the rest of its 11 skills, 6 agents.

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-tasks

README.md
[![agentmods](https://agentmods.dev/badge/skills/yi-john-huang/sdd-mcp/sdd-tasks/github.svg)](https://agentmods.dev/skills/yi-john-huang/sdd-mcp/sdd-tasks)
Your own site
<a href="https://agentmods.dev/skills/yi-john-huang/sdd-mcp/sdd-tasks"><img src="https://agentmods.dev/badge/skills/yi-john-huang/sdd-mcp/sdd-tasks/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-tasks

Your own site · 80×15
<a href="https://agentmods.dev/skills/yi-john-huang/sdd-mcp/sdd-tasks"><img src="https://agentmods.dev/badge/skills/yi-john-huang/sdd-mcp/sdd-tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,793 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00041 $0.01793
Opus 5 $0.00020 $0.00897
Sonnet 5 $0.00008 $0.00359
Haiku 4.5 $0.00004 $0.00179

Measured 13d ago against content hash f2f59de25d8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

sdd-tasks 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 13d 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-tasks/SKILL.md · 248 lines

How it starts

The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD Task Breakdown Generation

Generate comprehensive TDD-based task breakdowns that translate approved designs into implementable work items.

Prerequisites

Before generating tasks:

  1. Design must be generated using /sdd-design
  2. Design phase should be approved (use sdd-approve design MCP tool)
  3. Review the design document in .spec/specs/{feature}/design.md

Workflow

Step 1: Verify Prerequisites

Use sdd-status MCP tool to verify:

  • design.generated: true
  • design.approved: true (recommended before tasks)

Step 2: Review Design

  1. Read .spec/specs/{feature}/design.md
  2. Identify all components to implement
  3. Note interfaces and data models
  4. Understand dependencies between components

Step 3: Apply TDD Workflow

For each task, follow the Red-Green-Refactor cycle:

┌─────────────────────────────────────────────────────────────┐
│                    TDD CYCLE                                │
├─────────────────────────────────────────────────────────────┤
│                                                             │
│   1. RED    ──────>  Write failing test first              │
│                      (Test describes expected behavior)     │
│                                                             │
│   2. GREEN  ──────>  Write minimal code to pass            │
│                      (Just enough to make test green)       │
│                                                             │
│   3. REFACTOR ────>  Clean up, maintain tests passing      │
│                      (Improve design without breaking)      │
│                                                             │
│   ─────────────────────────────────────────────────────    │
│                      REPEAT                                 │
└─────────────────────────────────────────────────────────────┘

Step 4: Apply Test Pyramid

Structure tests following the 70/20/10 ratio:

                    ╱╲
                   ╱  ╲
                  ╱ E2E╲         10% - Critical user journeys
                 ╱──────╲
                ╱        ╲
               ╱Integration╲    20% - Component interactions
              ╱────────────╲
             ╱              ╲
            ╱   Unit Tests   ╲  70% - Individual functions
           ╱──────────────────╲

Read the full file on GitHub · 248 lines

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. 13d ago First seen · 248 lines · 41 tokens per session scan A f2f59de25d8b

Subscribe to this mod's changes

sdd-tasks is a skill published in the GitHub repository yi-john-huang/sdd-mcp (52 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,793 once invoked, about $0.0002 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.