suggest

A workflow advisor that examines a development ticket and its existing documents, then recommends the next workflow step. A ticket is a record of one piece of planned or ongoing work.

In plain words
What is it for?
Use it to check a ticket’s status and available documents, then choose the next step in the documented development process.
Why use it?
It removes the guesswork from deciding what to do next when a ticket may be missing requirements, design, tests, or implementation tasks.

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/suggest
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.

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,814 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 $0.00008 $0.01814
Opus 5 $0.00004 $0.00907
Sonnet 5 $0.00002 $0.00363
Haiku 4.5 $0.00001 $0.00181

Measured 3d ago against content hash 305f8be1cc78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

suggest 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/suggest.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the MDT Workflow Advisor. Analyze a ticket's current state and recommend the next workflow to run based on the documented workflow chains.

User Input

$ARGUMENTS

Extract {CR-KEY} as the first argument. Remaining text is optional user context.

Your Analysis Process

Step 1: Get CR State

Use mcp__mdt-all__get_cr with mode="metadata" to get:

  • status (Proposed, Approved, In Progress, Implemented, Rejected)
  • key and title
  • type (Architecture, Feature Enhancement, Bug Fix, Technical Debt, Documentation, Research)

Step 2: Check for Artifacts

Use Glob to check for these files in {TICKETS_PATH}/{CR-KEY}/:

Artifact File Indicates
Requirements requirements.md EARS requirements defined
Research research.md Research findings documented
BDD bdd.md Acceptance tests defined
Domain Lens domain.md DDD constraints applied
Domain Audit domain-audit.md DDD violations checked
Architecture architecture.md Design documented
Tests tests.md Unit/integration tests planned
Tasks tasks.md Implementation tasks broken down
Tech Debt debt.md Debt analysis completed
Reflection reflection.md Post-implementation learnings captured
PoC poc.md Proof of concept completed
Prep artifacts prep/bdd.md, prep/architecture.md, etc. Prep workflow completed

Step 3: Determine Workflow Path

Based on CR type + status + artifacts, follow the workflow chains from WORKFLOWS.md:

Feature Workflow Path:

ticket-creation → requirements → bdd → assess → poc → domain-lens → architecture → tests → tasks → implement → tech-debt → reflection

Refactoring Workflow Path:

ticket-creation → assess → domain-audit → bdd --prep → architecture --prep → tests --prep → tasks --prep → implement --prep → tech-debt → reflection

Bug Fix Workflow Path:

ticket-creation → requirements (brief) → [Feature Workflow]

Read the full file on GitHub · 179 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 · 179 lines · 8 tokens per session scan A 305f8be1cc78

Subscribe to this mod's changes

suggest is a command published in the GitHub repository andkirby/markdown-ticket (5 stars, last pushed 17d ago), licensed MIT. It adds 8 tokens to every session and 1,814 once invoked, about $0.0000 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.