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.
npx agentmods add commands/andkirby/markdown-ticket/architecturegit clone --depth 1 https://github.com/andkirby/markdown-ticketWrote 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.
[](https://agentmods.dev/commands/andkirby/markdown-ticket/architecture)<a href="https://agentmods.dev/commands/andkirby/markdown-ticket/architecture"><img src="https://agentmods.dev/badge/commands/andkirby/markdown-ticket/architecture.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.02707 |
| Opus 5 | $0.00000 | $0.01354 |
| Sonnet 5 | $0.00000 | $0.00541 |
| Haiku 4.5 | $0.00000 | $0.00271 |
Grade A, and why
architecture 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MDT Architecture Design Workflow (v11)
Surface architectural decisions before implementation. Output is minimal but complete.
Core Principle: Capture decisions that matter. Skip ceremony that duplicates code.
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} in all file path templates below (if it's not defined read ticketsPath key from .mdt-config.toml).
Output Location
| Mode | Output | Criteria |
|---|---|---|
Prep (--prep flag) |
{TICKETS_PATH}/{CR-KEY}/prep/architecture.md |
Preparatory refactoring design |
| Simple | ## Architecture Design in CR |
Single component or tightly scoped change; fits cleanly as a CR section |
| Complex | {TICKETS_PATH}/{CR-KEY}/architecture.md |
Multiple components, cross-module coordination, or needs a standalone artifact |
Don't pre-calculate complexity scores. Write the architecture, then decide where it goes based on scope.
What Good Architecture Output Looks Like
Must have:
- Overview (2-3 sentences)
- Pattern name + why
- One canonical runtime flow per critical behavior
- One owner module per critical behavior (no duplicates)
- Structure (file tree)
- Scope boundaries per module
- Runtime vs test scaffolding separation
- Architecture invariants
- Extension rule
Include only if needed:
- Build vs Use decisions (if evaluated)
- Component diagram (if >3 components with non-obvious relationships)
- Runtime prerequisites (if external deps exist)
- Error philosophy (if non-trivial failure modes)
Never include:
- Requirement-to-component mapping tables (code is the mapping)
- Implementation code snippets (they drift from reality)
- Bug fix history (git tracks this)
- Exhaustive domain alignment tables (2-3 key concepts max)
Execution Steps
Step 0: Detect Mode
Check for --prep flag in $ARGUMENTS. If present, mode is prep.
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.
- 4d ago First seen · 323 lines · 0 tokens per session scan A 25a0add6642f
architecture is a command published in the GitHub repository andkirby/markdown-ticket (5 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,707 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.