A design-phase guide for turning approved project requirements into technical documents such as architecture, data-model, and API plans.

Use it to choose the right design documents, draft or update them, and check whether the design is complete.

It prevents teams from starting technical design before the requirements and earlier project work are ready.

How pangon/ai-sdlc-framework configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to pangon/ai-sdlc-framework. 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/pangon/ai-sdlc-framework/main/.claude/skills/SDLC-design/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/pangon/ai-sdlc-framework

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pangon/ai-sdlc-framework/sdlc-design.svg)](https://agentmods.dev/skills/pangon/ai-sdlc-framework/sdlc-design)

Your own site

<a href="https://agentmods.dev/skills/pangon/ai-sdlc-framework/sdlc-design"><img src="https://agentmods.dev/badge/skills/pangon/ai-sdlc-framework/sdlc-design.svg" alt="Measured on agentmods" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,742 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.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.03742
Opus 5	$0.00023	$0.01871
Sonnet 5	$0.00009	$0.00748
Haiku 4.5	$0.00005	$0.00374

Measured 7d ago against content hash 68142fbe8830, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

SDLC-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 7d 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/SDLC-design/SKILL.md · 219 lines

How it starts

The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instructions

You are working in the Design phase, creating or updating architecture, data model, or API design documents.

Phase Validation

Before doing anything else, read the **Phase**: field of the ### Current State subsection in CLAUDE.md. Then follow the matching case below:

Not initialized — Stop, recommend /SDLC-init, and do not proceed.
Specification — design work would cross the Spec → Design phase gate. Recommend running /SDLC-validate first: gate evaluation trusts the assessment lines in Current State, and validation verifies their freshness against the actual git history. Then evaluate all three Spec → Design preconditions from the Phase Gates table in CLAUDE.md (using its "How to verify" column), and respond based on the results:
- If any artifact precondition is not met (stakeholders defined, at least one requirement Approved) — elicitation is incomplete. Stop, list what is missing, recommend /SDLC-elicit, and do not proceed.
- If the artifact preconditions are met but the gap-analysis precondition is not (no gap analysis, stale, or open Critical issues) — strongly recommend running a gap analysis via /SDLC-elicit before design. Proceed only if the user explicitly accepts the gaps.
- If all preconditions are met — inform the user of any remaining Important/Minor gaps (non-blocking) and ask the user to confirm the advancement to the Design phase (phase gate advancement is an "always ask" action). Proceed with Setup only after confirmation.
In every proceed case, the **Phase**: field is set to Design when the first user-approved design change is applied (see Current State Tracking) — not at validation time.
Design — proceed normally with the Setup steps below.
Code — the project has advanced beyond Design. Warn that modifying Design artifacts may impact downstream tasks or deployed code. If the user confirms, proceed but flag downstream dependencies that could be affected.

Read the full file on GitHub · 219 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.

7d ago First seen · 219 lines · 46 tokens per session scan A 68142fbe8830

Subscribe to this mod's changes

SDLC-design is a skill published in the GitHub repository pangon/ai-sdlc-framework (126 stars, last pushed 14d ago), licensed Apache-2.0. It adds 46 tokens to every session and 3,742 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.

Planning Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

ai-sdlc-framework: Skill for Claude Code