p2-poc

A command that builds a small technical proof of concept for the riskiest part of a project. A proof of concept is a limited experiment that checks whether a planned technical approach works, rather than a finished feature.

In plain words
What is it for?
Use it for risks such as real-time synchronisation, an AI integration, or a payment API. It can choose the riskiest technical area from the project's assumptions and planning documents.
Why use it?
It tests the hardest technical assumption before time is spent on the full architecture and implementation. This can expose feasibility problems early.

Command

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/jonase47/ccpr/p2-poc
Clone the repo
git clone --depth 1 https://github.com/jonase47/ccpr
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 1,190 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 $0.01190
Opus 5 $0.00000 $0.00595
Sonnet 5 $0.00000 $0.00238
Haiku 4.5 $0.00000 $0.00119

Measured 2d ago against content hash f68d22940ade, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

p2-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 2d 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.

commands/p2-poc.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/p2-poc – Technical Proof of Concept

Builds a minimal technical Proof of Concept for the riskiest technical area of the project. The goal is not a finished feature but proof that the planned approach fundamentally works – before investing in architecture and implementation.

Argument: $ARGUMENTS = [Technical risk area, e.g. "real-time synchronisation", "AI integration", "payment API"]

If provided: Build the PoC specifically for the named risk area. If not provided: Read ASSUMPTIONS.md and identify the most technically risky area yourself. If ASSUMPTIONS.md is missing, ask for the biggest technical risk of the project.

Execution

1. Read Context

Read the following files (if available):

  • ASSUMPTIONS.md (technical Assumptions with highest priority)
  • CONCEPT.md / FEATURES.md (What should the system do?)
  • DISCOVERY.md (Feasibility assessment from Phase 0)

2. Delegate to system-architekt Agent (Lead)

Delegate PoC planning and technical evaluation to the system-architekt agent:

Plan and evaluate a Proof of Concept for the following risk area: $ARGUMENTS Context: [Insert relevant technical Assumptions from ASSUMPTIONS.md and requirements from CONCEPT.md]

Work out:

A. Define PoC Scope

  • What exactly should the PoC prove? (1 clear question that must be answered)
  • What is deliberately NOT part of the PoC? (Scope Boundary)
  • Success criterion: How do we know the PoC is successful?

B. Choose Technical Approach

  • Which technology/library/API should be tested?
  • What alternatives exist and why is this approach preferred?
  • Which dependencies (external APIs, SDKs, services) are needed?

C. Assessment after PoC Execution

  • ✅ Feasible: Approach works, recommendation for architecture
  • ⚠️ Feasible with limitations: What needs to be adjusted?
  • ❌ Not feasible: Which alternative approach is recommended?

3. Delegate to senior-developer Agent (Support)

Delegate PoC implementation to the senior-developer agent:

Read the full file on GitHub · 103 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. 2d ago First seen · 103 lines · 0 tokens per session scan A f68d22940ade

Subscribe to this mod's changes

p2-poc is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,190 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.