requirements

requirements is a command for coding agents from andkirby/markdown-ticket. It costs 0 tokens per session (2,676 once invoked), scanned A, original, MIT.

A workflow that turns a change request into behavioral requirements describing what the software should do. It stores those requirements in a Markdown file linked to the ticket.

In plain words
What is it for?
Use it for feature enhancements or complex bug fixes with several distinct behaviors. Skip it for simple fixes, refactoring, technical debt, or documentation-only work.
Why use it?
It separates expected behavior from implementation details, making it easier to agree on outcomes and carry edge cases through later design and task planning.

Command

Part of the mdt plugin — 1 skill, 16 commands, 5 agents, 1 hook shipped together

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.

agentmods
npx agentmods add commands/andkirby/markdown-ticket/requirements
Clone the repo
git clone --depth 1 https://github.com/andkirby/markdown-ticket

Or install mdt, the plugin that ships this one along with the rest of its 1 skill, 16 commands, 5 agents, 1 hook.

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 requirements

README.md
[![agentmods](https://agentmods.dev/badge/commands/andkirby/markdown-ticket/requirements.svg)](https://agentmods.dev/commands/andkirby/markdown-ticket/requirements)
Your own site
<a href="https://agentmods.dev/commands/andkirby/markdown-ticket/requirements"><img src="https://agentmods.dev/badge/commands/andkirby/markdown-ticket/requirements.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,676 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02676
Opus 5 $0.00000 $0.01338
Sonnet 5 $0.00000 $0.00535
Haiku 4.5 $0.00000 $0.00268

Measured 3d ago against content hash 56884ea3b5be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

requirements 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 3d 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.

prompts/mdt/commands/requirements.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MDT Requirements Specification Workflow (v5)

Generate behavioral requirements from CR. Output: {TICKETS_PATH}/{CR-KEY}/requirements.md

Core Principle: Requirements describe WHAT the system does. Architecture decides WHERE and HOW.

Skill Discovery

Check AGENTS.md for skills matching this workflow. If found, invoke via Skill tool before proceeding.

User Input

$ARGUMENTS

Session Context

Use {TICKETS_PATH} from .mdt-config.toml.

When to Use (and When to Skip)

CR Type Generate? Why
Feature Enhancement Yes New behaviors need specification
Complex Bug Fix Yes (brief) Multiple behaviors affected
Simple Bug Fix Skip CR acceptance criteria suffices
Refactoring Skip No new behavior → /mdt:architecture
Tech Debt Skip Structure change → /mdt:architecture
Documentation Skip No behavioral requirements

Quick test: If CR has <3 distinct behaviors, skip requirements.md unless the CR explicitly sets Requirements Scope.

Carryover rule: Any constraints or edge-case rules in requirements must be carried into architecture and tasks (by ID). Deviation rule: If architecture proposes a simpler alternative that changes a stated requirement, mark it as Decision Needed and do not change the requirement until explicitly approved. Security rule: If requirements involve executing external commands or substituting user content (e.g., {text} placeholders), include a security constraint for escaping/command injection prevention and carry it forward to tests. Traceability rule: /mdt:bdd must not introduce behaviors that are not in requirements. If a needed behavior is missing, add it here or flag for /mdt:clarification before writing BDD.

EARS Syntax (Quick Reference)

Type Template Example
Event WHEN <trigger>, the system shall <action> WHEN user clicks Save, the system shall persist within 200ms
State WHILE <state>, the system shall <action> WHILE offline, the system shall queue mutations
Error IF <condition>, THEN the system shall <action> IF validation fails, THEN the system shall show field errors
Always The system shall <action> The system shall hash passwords with bcrypt
Absence WHILE <dependency> is unavailable, the system shall <fallback> WHILE external detection is unavailable, the system shall proceed without applying a constraint

Read the full file on GitHub · 294 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. 3d ago First seen · 294 lines · 0 tokens per session scan A 56884ea3b5be

Subscribe to this mod's changes

requirements is a command published in the GitHub repository andkirby/markdown-ticket (5 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,676 tokens. 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.