agentmods.dev

specify

specify is a skill for Claude Code from YuDefine/nuxt-supabase-starter. It costs 81 tokens per session (1,121 once invoked), scanned A, original, MIT.

A requirements-planning skill that turns a natural-language feature request into a new, numbered plan package. The package contains a specification, a requirements checklist, and an initial record of specification changes.

In plain words
What is it for?
Use it to start an iteration, define user goals and acceptance requirements, set scope and limits, and prepare the handoff to technical and system planning.
Why use it?
It preserves old plans as history while clearly defining what the next change should do. It also identifies unclear decisions that must be settled before detailed planning.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

not rated 45repo changed today A scan 81 tokens original MIT

Good fit Use it to start an iteration, define user goals and acceptance requirements, set scope and limits, and prepare the handoff to technical and system planning.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yudefine/nuxt-supabase-starter/specify
View source ↗ YuDefine/nuxt-supabase-starter
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 YuDefine/nuxt-supabase-starter --skill specify
Clone the repo
git clone --depth 1 https://github.com/YuDefine/nuxt-supabase-starter

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 specify

README.md
[![agentmods](https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/specify/github.svg)](https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/specify)
Your own site
<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/specify"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/specify/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 specify

Your own site · 80×15
<a href="https://agentmods.dev/skills/yudefine/nuxt-supabase-starter/specify"><img src="https://agentmods.dev/badge/skills/yudefine/nuxt-supabase-starter/specify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,121 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 $0.00081 $0.01121
Opus 5 $0.00041 $0.00561
Sonnet 5 $0.00016 $0.00224
Haiku 4.5 $0.00008 $0.00112

Measured today against content hash 0033e806ceac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

specify 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 today.

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.

template/.claude/skills/specify/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Specify

specify 是每次迭代的 plan 起點。它只描述「這次要改什麼」，不直接修改系統 truth。即使本次需求是修改或刪除既有行為，也建立新的 plan package，讓舊 plan 保持歷史，讓 specs/truth/** 代表目前系統真相。

SOP

Phase 1 -- 建立新的 plan package

  1. READ 讀取使用者需求、呼叫者要求、目前 specs/plans/ 下既有編號與 specs/truth/** 的高層現況，確認本次功能主題、範圍、語言要求與明示限制。
  2. READ 讀取 templates/spec.template.md、templates/spec.example.md、templates/requirements-checklist.md 與 templates/requirements-checklist.example.md，確認 spec 與 checklist 的固定結構。
  3. READ 讀取 rules/Feature目錄命名與輸出定位判準.md，確認下一個 NNN-<slug> plan package 命名方式與輸出定位。
  4. READ 讀取 .agents/constitution/CONSTITUTION.md、.agents/constitution/shared.md、.agents/constitution/skills/specify/spec.md 與 .agents/constitution/skills/specify/requirements-checklist.md，並將其中規則視為高於本地 artifact 規範的約束。
  5. WRITE 建立 specs/plans/NNN-<slug>/ 與 checklists/，並初始化 truth-delta.md 骨架；本 phase 不建立或修改 specs/truth/**。

Phase 2 -- 收斂需求缺口與 clarify 策略

  1. THINK 從需求與現有 truth 整理主要使用者目標、核心流程、顯性限制、品質期望、可能的 ADD / MODIFY / DELETE 意圖與可辨識範圍邊界。
  2. READ 若需要判斷哪些缺口必須升級為 clarify，讀取 rules/Clarify升級門檻與提問預算判準.md。
  3. DELEGATE 若缺口會改變使用者故事切分、需求歸戶、主要流程、正式驗收標準，或會高影響修改/刪除既有 truth 行為，呼叫 /clarify 先訪談使用者；未收斂前停止，不自行假設答案。

Phase 3 -- 重建 spec 語意骨架

  1. READ 需要切分故事或需求歸戶時，讀取 rules/使用者故事切分與優先級判準.md 與 rules/FR與NFR歸戶到UserStory與全域需求判準.md。
  2. THINK 依已載入規則收斂可獨立驗證的 User Stories、Priority、驗收情境、故事專屬 FR / NFR、全域需求、邊界情況、關鍵實體、成功標準與假設。
  3. THINK 對涉及既有 truth 的需求，明確標示它預期是新增、修改或刪除現有系統行為，但不在本 skill 寫入 truth。

Phase 4 -- 產出 plan artifacts 並自檢

  1. WRITE 將 spec 寫入 specs/plans/NNN-<slug>/spec.md，將 checklist 寫入 specs/plans/NNN-<slug>/checklists/requirements.md。
  2. READ 讀取 rules/spec完整性與一致性自檢判準.md，檢查使用者故事、FR / NFR、驗收情境、邊界情況、成功標準、假設與剩餘 clarify 缺口是否一致；若不符合，立即修正。

Phase 5 -- 交付後續 handoff

  1. WRITE 向使用者回報 plan package、spec、checklist、truth-delta 路徑、本次是否進入 /clarify、仍保留的 NEEDS CLARIFICATION 或假設，以及此 plan 是否可進入 /spec-by-example 或 /technical-research。

Read the full file on GitHub · 48 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today Changed · -1 lines 0033e806ceac
  2. yesterday First seen · 49 lines · 81 tokens per session scan A 4605d98e3dea

Subscribe to this mod's changes

specify is a skill published in the GitHub repository YuDefine/nuxt-supabase-starter (45 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 1,121 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 2026-09-10.

Claude CodePlanningProject managementTDDai-assistednuxtsupabasetemplate
Related

Other skills, from other repositories

gh-issue

Size-audit, write, and split BanyanDB issues that somebody else or an automated TDD workflow can implement. Use whenever the user asks to file or revise an issue, decide whether an issue is too large, make an issue TDD-ready, turn a design into tickets, or split an umbrella into executable leaves. Do not draft or file…

apache/skywalking-banyandb · 91 tokens

nw-finalize

Archives a completed feature to docs/evolution/, migrates lasting artifacts to permanent directories, and cleans up the temporary workspace. Use after all implementation steps pass and mutation testing completes.

nWave-ai/nWave · 39 tokens

linear-maintenance

Bi-weekly housekeeping pass over the evlog team's Linear backlog — labels, projects, priorities, stale triage, work that is done but still open, and anything misfiled next to its siblings. Applies the mechanically verifiable fixes and surfaces the rest as decisions. Load this when the linear-maintenance schedule…

HugoRCD/evlog · 89 tokens

nw-new

Guided wizard to start a new feature. Asks what you want to build, recommends the right starting wave, and launches it.

nWave-ai/nWave · 30 tokens

nw-deliver-orchestration

DELIVER wave orchestration workflow -- 9 phases from baseline to finalization. Load when user invokes deliver command. Covers state tracking, smart skip logic, retry, resume, and quality gate enforcement.

nWave-ai/nWave · 48 tokens

prd-v07-test-planning

Define test cases BEFORE implementation, ensuring every API, business rule, and user journey has verifiable acceptance criteria during PRD v0.7 Build Execution. Triggers on requests to define tests, plan test coverage, create test cases, or when user asks "define tests", "test planning", "what to test?", "test cases"…

mattgierhart/PRD-driven-context-engineering · 125 tokens