A skill for running the MDT Markdown Ticket workflows and creating their ticket or architecture decision record files. An architecture decision record is a written record of an important technical choice.

Use it when creating or updating MDT change requests or decision records, or when running workflows for requirements, behavior scenarios, architecture, tests, tasks, implementation, audits, or technical debt.

It tells the coding agent which workflow instructions and output formats to follow, so generated project artifacts stay consistent.

mdt — Skill for Claude Code by andkirby/markdown-ticket

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 andkirby/markdown-ticket --skill mdt

Clone the repo

git clone --depth 1 https://github.com/andkirby/markdown-ticket

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andkirby/markdown-ticket/mdt/github.svg)](https://agentmods.dev/skills/andkirby/markdown-ticket/mdt)

Your own site

<a href="https://agentmods.dev/skills/andkirby/markdown-ticket/mdt"><img src="https://agentmods.dev/badge/skills/andkirby/markdown-ticket/mdt/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andkirby/markdown-ticket/mdt"><img src="https://agentmods.dev/badge/skills/andkirby/markdown-ticket/mdt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 655 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.

Model	Per session	Once invoked
Fable 5.1	$0.00096	$0.00655
Opus 5.5	$0.00038	$0.00262
Sonnet 5.5	$0.00019	$0.00131
Haiku 4.5	$0.00010	$0.00065

Measured 1mo ago against content hash 782847f12a1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mdt 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 1mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/enforce-tasks.sh, scripts/gen-tasks-status.sh, scripts/update-task-status.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mdt

Overview

Execute the MDT workflow system and generate CR artifacts exactly as specified by the MDT prompt set. Use the references in this skill for authoritative formats, steps, and file locations.

Quick Start

Identify the requested command (e.g., /mdt:requirements, /mdt:architecture, /mdt:tasks).
Load the matching command file from commands/.
Use references/README.md only when you need extra implementation guidance.
Respect {TICKETS_PATH} from .mdt-config.toml if not provided by context.

Core Rules

Always follow the exact output locations and formats from the command file.
If a command supports --prep or --part, detect from user arguments; if unclear, ask.
Do not invent new sections or formats; mirror the referenced templates.

Runtime Compatibility

Use built-in Codex agents via spawn_agent (default, worker, explorer) when a command requires subagents.
Treat files in agents/*.md as prompt contracts/templates for those spawned agents.
Do not assume a skill-local .mcp.json is auto-loaded by the host session. Use MCP tools available in the active runtime.

Reference Map

commands/*.md: Authoritative prompt for each /mdt:* command.
references/README.md: Supplemental reference docs and templates.
agents/*.md: Subagent role contracts for orchestrated implementation flows.

Command Files

Load only the file you need:

/mdt:ticket-creation → commands/ticket-creation.md
/mdt:requirements → commands/requirements.md
/mdt:bdd → commands/bdd.md
/mdt:assess → commands/assess.md
/mdt:poc → commands/poc.md
/mdt:domain-lens → commands/domain-lens.md
/mdt:domain-audit → commands/domain-audit.md
/mdt:architecture → commands/architecture.md
/mdt:tests → commands/tests.md
/mdt:clarification → commands/clarification.md
/mdt:tasks → commands/tasks.md
/mdt:implement → commands/implement.md
/mdt:implement-agentic → commands/implement-agentic.md
/mdt:tech-debt → commands/tech-debt.md
/mdt:reflection → commands/reflection.md

Read the full file on GitHub · 56 lines

Files

What ships with it

34 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.

1mo ago First seen · 56 lines · 96 tokens per session scan A 782847f12a1c

Subscribe to this mod's changes

mdt is a skill published in the GitHub repository andkirby/markdown-ticket (7 stars, last pushed 3d ago), licensed MIT. It adds 96 tokens to every session and 655 once invoked, about $0.0004 per session on Opus 5.5. 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.

Planning Project management

story-readiness

Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.

Donchitos/Claude-Code-Game-Studios · 48 tokens

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

handle-linkedin-connection-request-signal

Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…

swan-gtm/gtm-skills · 160 tokens

remove

Remove a deployed framework or addon from the current workspace.

jmagly/aiwg · 12 tokens