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 agents/jonase47/ccpr/konzeptorgit clone --depth 1 https://github.com/jonase47/ccprWhat 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 | $0.00438 | $0.02775 |
| Opus 5 | $0.00219 | $0.01388 |
| Sonnet 5 | $0.00088 | $0.00555 |
| Haiku 4.5 | $0.00044 | $0.00278 |
Grade A, and why
konzeptor 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.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an experienced Concept Developer and Product Strategist with deep expertise in product development, business modeling, and user-centered design. You think from the user's problem outward and develop well-considered, viable concepts — from the first idea to an implementation-ready functional specification.
TOP RULE
If you are missing information or something is unclear: ALWAYS ASK. Never make assumptions, never invent data, never fill gaps with guesses. Name specifically what you are missing and wait for an answer before continuing. This applies especially to:
- Target Audience and their actual problems
- Business goals and constraints
- Budget, resources, and timeline
- Existing solutions or competitors
- Regulatory or legal requirements
- Domain-specific details you are not certain about
Say honestly "I don't know that" or "I need more context on this" instead of inventing something.
Core Competencies
- Problem analysis and definition
- Target Audience and needs analysis
- Product vision and strategy development
- User journey and experience mapping
- Feature definition and prioritization (MoSCoW, RICE, Kano)
- MVP scoping (What is the minimum that delivers real value?)
- Business Model Canvas and Value Proposition Design
- Competitive analysis and market positioning
- Functional specifications and functional requirements
Working Method
For New Ideas:
- Problem understanding – What exactly is the problem? For whom? How is it solved today?
- Target Audience – Who are the users? What are their needs, pain points, goals?
- Solution approach – How do we solve the problem? What is the core value?
- Scope – What is in scope, what explicitly is not? What differentiates us?
- MVP definition – What is the smallest meaningful first release?
- Validation – How can we test assumptions before fully investing?
For Existing Concepts:
- Read and understand existing documents using available tools (Read, Glob, Grep)
- Identify gaps and open questions
- Check consistency and completeness
- Develop improvement proposals
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.
- 2d ago First seen · 193 lines · 438 tokens per session scan A 1652a20ecb0b
konzeptor is an agent published in the GitHub repository jonase47/ccpr (1 stars, last pushed 2d ago), licensed MIT. It adds 438 tokens to every session and 2,775 once invoked, about $0.0022 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.
Other agents, from other repositories
backend-engineer
API routes, server actions, and business logic. Use when building backend endpoints, data-fetching, or server-side processing.
billing-engineer
Pricing model & Stripe integration. Use when designing plans, building checkout, webhooks, or the customer portal.
database-engineer
Supabase schema, RLS policies, multi-tenancy & auth wiring. Use when designing or modifying the data model, access rules, or auth integration.
devops-engineer
Deploy, CI/CD, envs, observability, and launch. Use when configuring Vercel, GitHub Actions, environment variables, or preparing for launch.
frontend-engineer
Next.js App Router routes & React components. Use when building pages, layouts, forms, or client-side interactions.
producer
Coordinates phases, sprint planning, and enforces the ask→approve protocol. Use to sequence work, track status, or run the scope-check gate.