poc

poc is a command for coding agents from andkirby/markdown-ticket. It costs 0 tokens per session (3,453 once invoked), scanned A, original, MIT.

A proof-of-concept workflow for testing an uncertain technical idea with a small, temporary experiment before finalizing the software design. A proof of concept checks whether an approach works in practice.

In plain words
What is it for?
Use it to try out library features, service behavior, API responses, performance assumptions, or other technical choices that are not yet proven.
Why use it?
Documentation and research cannot always answer whether a library, service, or design will work in a specific project. Early experimentation helps avoid costly changes and incorrect assumptions during implementation.

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/poc
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 poc

README.md
[![agentmods](https://agentmods.dev/badge/commands/andkirby/markdown-ticket/poc.svg)](https://agentmods.dev/commands/andkirby/markdown-ticket/poc)
Your own site
<a href="https://agentmods.dev/commands/andkirby/markdown-ticket/poc"><img src="https://agentmods.dev/badge/commands/andkirby/markdown-ticket/poc.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 3,453 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 $0.03453
Opus 5 $0.00000 $0.01726
Sonnet 5 $0.00000 $0.00691
Haiku 4.5 $0.00000 $0.00345

Measured 3d ago against content hash 3a1c34424f92, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

poc 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/poc.md · 569 lines

How it starts

The opening of the file, as written. The whole thing — 569 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MDT Proof of Concept Workflow (v1)

Validate uncertain technical decisions through hands-on experimentation before committing to architecture.

Core Principle: When documentation and research can't answer "will this work?", build a throwaway spike to find out.

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).

Problem This Solves

Some technical decisions can't be validated through documentation alone:

  • "Does library X support feature Y in our context?"
  • "Can we achieve acceptable performance with approach Z?"
  • "How does service A behave when B happens?"
  • "What's the actual API shape returned by C?"

Without hands-on validation, architecture commits to unproven approaches, leading to:

  • Mid-implementation pivots (waste)
  • Workarounds for discovered limitations (debt)
  • Incorrect assumptions baked into tests (fragile)

PoC resolves uncertainty before architecture locks in decisions.

When to Use

Explicit Trigger (User Request)

User says:

  • "I need to verify X works"
  • "Not sure if library supports Y"
  • "Build a proof of concept for Z"
  • "Let's spike on this before architecture"

Detected Trigger (From /mdt:architecture)

Architecture workflow detects uncertainty and suggests PoC:

⚠️ **Technical Uncertainty Detected**

| Question | Why It Matters | Suggestion |
|----------|----------------|------------|
| {uncertainty} | {impact on design} | `/mdt:poc {CR-KEY} --question "{question}"` |

Recommend: Run PoC before finalizing architecture.

Open Questions in CR

CR contains unresolved technical questions:

## Open Questions
- [ ] Does Express support dynamic port binding with graceful shutdown?
- [ ] Can pdf-lib handle encrypted PDFs without external dependencies?

Do NOT Use When

  • Question can be answered by reading documentation
  • Decision is about code organization (that's architecture)
  • Feature is well-understood, just needs implementation
  • Time pressure doesn't allow thorough investigation

Read the full file on GitHub · 569 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 · 569 lines · 0 tokens per session scan A 3a1c34424f92

Subscribe to this mod's changes

poc 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 3,453 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.