design-feature

design-feature is a skill for Claude Code from nacif-software/skills. It costs 36 tokens per session (923 once invoked), scanned A, original, MIT.

A process for turning a feature idea into a clear design document and implementation plan. It examines the existing project, identifies decisions and open questions, and compares possible approaches before coding.

In plain words
What is it for?
Use it for new features, product changes, architecture-affecting refactors, or requests whose implementation details are not yet clear.
Why use it?
Vague feature requests can lead to the wrong architecture or wasted implementation work. This process clarifies the goal, limits, trade-offs, and required changes first.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Part of the nacif-skills plugin — 23 skills shipped together

Good fit Use it for new features, product changes, architecture-affecting refactors, or requests whose implementation details are not yet clear.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nacif-software/skills/design-feature
Install

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.

Any agent
npx skills add nacif-software/skills --skill design-feature
Clone the repo
git clone --depth 1 https://github.com/nacif-software/skills

Made for: Claude Code.

Or install nacif-skills, the plugin that ships this one along with the rest of its 23 skills.

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 design-feature

README.md
[![agentmods](https://agentmods.dev/badge/skills/nacif-software/skills/design-feature.svg)](https://agentmods.dev/skills/nacif-software/skills/design-feature)
Your own site
<a href="https://agentmods.dev/skills/nacif-software/skills/design-feature"><img src="https://agentmods.dev/badge/skills/nacif-software/skills/design-feature.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 923 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 $0.00036 $0.00923
Opus 5 $0.00018 $0.00462
Sonnet 5 $0.00007 $0.00185
Haiku 4.5 $0.00004 $0.00092

Measured 8d ago against content hash 5b82f5c8e12f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

design-feature 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 8d 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.

skills/design-feature/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Feature

Purpose

Turn a feature idea into a clear design artifact before implementation. The workflow may stop at the design, continue into an implementation plan, or hand off to plan-implementation.

When to use

  • Use for new features, product changes, architecture-affecting refactors, and unclear implementation requests.
  • Use when the user says "design", "spec", "PRD", "plan this", "grill me", or "help me think through this".
  • Do not use for small mechanical edits whose requirements and files are already explicit.

Procedure

  1. Discover local context before asking questions:
    • Read repo instruction files such as AGENTS.md, CLAUDE.md, CONTRIBUTING.md, and relevant docs.
    • Inspect nearby code, tests, routes, package scripts, or schemas that define the current shape.
    • Summarize only the facts that affect the design.
  2. Start a decision map:
    • Resolved decisions.
    • Open questions.
    • Assumptions.
    • Out-of-scope items.
  3. Ask one linked question at a time. Each question must resolve a real branch in the decision map. Prefer a recommendation with trade-offs.
  4. When enough is known, present 2-3 viable approaches and recommend one.
  5. Draft the design in sections:
    • Problem and goal.
    • User-visible behavior.
    • Technical approach.
    • Interfaces, data flow, or contracts.
    • Edge cases and failure modes.
    • Test and verification strategy.
    • Out of scope.
  6. Ask the user to approve or revise the design.
  7. Write the design doc in the repo's preferred docs location. If no convention exists, use docs/designs/YYYY-MM-DD-<feature>.md.
  8. Self-review the design for placeholders, contradictions, unresolved decisions, unclear acceptance criteria, and accidental scope creep.
  9. Offer the next step:
    • Stop at design.
    • Create an implementation plan with plan-implementation.
    • Create a plan and test strategy with test-strategy.
    • Create a plan, test strategy, and PR shape with pr-boundary.
    • Create a plan, test strategy, PR shape, and review it with review-plan.
    • Create a plan, test strategy, PR shape, review it, and continue into execute-plan.
  10. If the user chooses implementation for non-trivial work, chain through plan-implementation, test-strategy, pr-boundary, review-plan, and then execute-plan. Do not jump from design directly to execution.
  11. Use verification-gate before claiming the design artifact or any chained artifact is complete.

Read the full file on GitHub · 118 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. 8d ago First seen · 118 lines · 36 tokens per session scan A 5b82f5c8e12f

Subscribe to this mod's changes

design-feature is a skill published in the GitHub repository nacif-software/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 923 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 2026-08-31.

Related

Other skills, from other repositories

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens