spec-driven-skill

spec-driven-skill is a cursor rule for Cursor from hbarbosa02/alaz-mcp-nestjs. It costs 718 tokens per session, scanned A, original, MIT.

A rule for using a specification-driven workflow in a project. It organizes work into defining requirements, designing a solution when needed, breaking it into tasks, implementing it, and verifying the result.

In plain words
What is it for?
Use it for project setup, feature planning, architecture and task breakdown, implementation, validation, quick fixes, and session continuity. It also covers project memory stored in the project’s specification files.
Why use it?
It gives larger or unclear changes a documented path from idea to tested outcome and keeps project decisions, blockers, and follow-up work recorded.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it for project setup, feature planning, architecture and task breakdown, implementation, validation, quick fixes, and session continuity. It also covers project memory stored in the project’s specification files.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/hbarbosa02/alaz-mcp-nestjs/spec-driven-skill
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.

Clone the repo
git clone --depth 1 https://github.com/hbarbosa02/alaz-mcp-nestjs

Made for: Cursor.

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 spec-driven-skill

README.md
[![agentmods](https://agentmods.dev/badge/rules/hbarbosa02/alaz-mcp-nestjs/spec-driven-skill/github.svg)](https://agentmods.dev/rules/hbarbosa02/alaz-mcp-nestjs/spec-driven-skill)
Your own site
<a href="https://agentmods.dev/rules/hbarbosa02/alaz-mcp-nestjs/spec-driven-skill"><img src="https://agentmods.dev/badge/rules/hbarbosa02/alaz-mcp-nestjs/spec-driven-skill/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 spec-driven-skill

Your own site · 80×15
<a href="https://agentmods.dev/rules/hbarbosa02/alaz-mcp-nestjs/spec-driven-skill"><img src="https://agentmods.dev/badge/rules/hbarbosa02/alaz-mcp-nestjs/spec-driven-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 718 This file is loaded in full into every session.
When invoked 718 The same file — it is already loaded in full.
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 $0.00718 $0.00718
Opus 5 $0.00359 $0.00359
Sonnet 5 $0.00144 $0.00144
Haiku 4.5 $0.00072 $0.00072

Measured 8d ago against content hash c0703cbf021a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

spec-driven-skill 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.

.cursor/rules/spec-driven-skill.mdc · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec-Driven skill — invocation

When to read and follow it

Load .cursor/skills/spec-driven/SKILL.md (and on-demand files under that folder) when the user’s goal matches planning, documenting, or executing work in the adaptive Specify → (Design) → (Tasks) → Execute pipeline, or session / project memory (.specs/). Use natural language; exact phrases are hints, not strict commands.

Situation Typical user intent (examples)
New / brownfield project “Initialize project”, “setup project”, “create roadmap”, “map codebase”, “analyze existing code”
Feature work “Specify feature …”, “define requirements”, “design”, “architecture”, “break into tasks”, “implement”, “build”, “validate”, “UAT”, “verify work”
Small / ad-hoc “Quick fix”, “quick task”, “bug fix”, small tweak (use Quick mode when scope is tiny — see below)
Continuity “Pause work”, “end session”, “resume work”, “continue”
Project memory “Record decision”, “log blocker”, “add todo”, “document concerns”, “tech debt”

Do not treat the spec-driven skill as the right tool for: generic architecture-decomposition analysis (use a dedicated architecture workflow/skill if present), or standalone technical design doc authoring when the user asked for a different doc process (create-technical-design-doc and similar). For everything else in the table, prefer spec-driven.

How to apply it (summary)

  1. Auto-size depth — Small: Quick mode (describe → implement → verify → commit; guardrails: ~≤3 files, no big design, no new deps). Medium: brief specify + execute with design/tasks inline. Large/complex: full spec IDs, design.md, tasks.md as needed.
  2. PhasesSpecify and Execute are always in play at the right depth; Design and Tasks are skipped when the change is obvious and small; if inline steps explode (>5 or messy deps), stop and add formal tasks.md (safety valve).
  3. Artifacts — Put outputs under .specs/ (see README.md in the skill folder for layout: project/, codebase/, features/, quick/).
  4. Context — Prefer base load: PROJECT.md, ROADMAP.md, STATE.md when they exist; load one feature’s spec/design/tasks at a time, not several specs in parallel.
  5. Research — Follow the skill’s Knowledge Verification Chain (codebase → project docs → MCP/web → flag uncertainty); do not fabricate APIs or behavior.
  6. Commits — One logical task or step per commit; commit messages must match this repo’s Conventional Commits rule in commit-pattern.mdc and npm run precommit when you commit.

Read the full file on GitHub · 32 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 · 32 lines · 718 tokens per session scan A c0703cbf021a

Subscribe to this mod's changes

spec-driven-skill is a cursor rule published in the GitHub repository hbarbosa02/alaz-mcp-nestjs (2 stars, last pushed 4mo ago), licensed MIT. It adds 718 tokens to every session, about $0.0036 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.