speckit-workflow

speckit-workflow is a cursor rule for Cursor from Project-VIC-International/Agentic-AI-Development-Course. It costs 1,299 tokens per session, scanned A, original, Apache-2.0.

A required step-by-step development process for a CAC mission tool. It uses written specifications, plans, task lists, implementation, and review to define and track each feature.

In plain words
What is it for?
Use it to establish project rules, describe features, plan architecture, split work into testable tasks, implement them in order, and analyze the result.
Why use it?
It prevents developers from jumping straight into code without agreeing on the tool's purpose, design, and acceptance criteria.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it to establish project rules, describe features, plan architecture, split work…

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/project-vic-international/agentic-ai-development-course/speckit-workflow
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/Project-VIC-International/Agentic-AI-Development-Course

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 speckit-workflow

README.md
[![agentmods](https://agentmods.dev/badge/rules/project-vic-international/agentic-ai-development-course/speckit-workflow.svg)](https://agentmods.dev/rules/project-vic-international/agentic-ai-development-course/speckit-workflow)
Your own site
<a href="https://agentmods.dev/rules/project-vic-international/agentic-ai-development-course/speckit-workflow"><img src="https://agentmods.dev/badge/rules/project-vic-international/agentic-ai-development-course/speckit-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,299 This file is loaded in full into every session.
When invoked 1,299 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 $0.01299 $0.01299
Opus 5 $0.00649 $0.00649
Sonnet 5 $0.00260 $0.00260
Haiku 4.5 $0.00130 $0.00130

Measured 6d ago against content hash c810c12f5ac2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

speckit-workflow 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 6d 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.

part-2-lab/exercises/03-spec-driven-dev/example-cursor-rules/speckit-workflow.mdc · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec-Driven Development

Every feature, enhancement, and non-trivial bug fix in this project MUST follow the spec-driven development pipeline. Do not skip steps. Do not jump straight to implementation. The spec is the contract between you (the investigator), the AI agent, and any future developer, examiner, validator, or judge who needs to understand what the tool does and why.

This is the discipline that separates a court-defensible mission tool from a one-off script.

The Required Pipeline

Step Slash Command What Happens
1. Constitution /speckit.constitution The project's governing rules (this is a one-time setup, then it lives at .specify/memory/constitution.md)
2. Specify /speckit.specify Define what the feature does, who uses it, what counts as "done" — in plain language
3. Plan /speckit.plan Translate the spec into architecture, data models, components, and contracts
4. Tasks /speckit.tasks Break the plan into ordered, testable work units with clear acceptance criteria
5. Implement /speckit.implement Execute tasks one at a time; each one is reviewed before moving on
6. Analyze /speckit.analyze Cross-check the spec, plan, tasks, and implementation for consistency

GitHub spec-kit (https://github.com/github/spec-kit) provides these commands. They are not optional ritual — they are how a non-programmer keeps control of an AI agent that can write code faster than any human can read it.

When Spec-Driven Development Applies

  • Any new tool, feature, capability, or module
  • Performance improvements (pair with the auto-research rule)
  • Refactors that change inputs, outputs, or data shapes
  • Bug fixes that require changing the architecture or the data model
  • Anything that touches CASE/UCO/CAC output (per the ontology-alignment rule)
  • Anything that touches authentication, evidence handling, audit logging, encryption, or networking (per the security-compliance rule)

Read the full file on GitHub · 88 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. 6d ago First seen · 88 lines · 1,299 tokens per session scan A c810c12f5ac2

Subscribe to this mod's changes

speckit-workflow is a cursor rule published in the GitHub repository Project-VIC-International/Agentic-AI-Development-Course (5 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,299 tokens to every session, about $0.0065 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.