konzept-update

konzept-update is a command for coding agents from jonase47/ccpr. It costs 0 tokens per session (1,398 once invoked), scanned A, original, MIT.

A command for revising an existing rough concept when new findings, answers, or requirements change it. Each revision receives a version and timestamp so the concept’s history remains traceable.

In plain words
What is it for?
Use it to update a concept document after new research, clarified questions, changed requirements, or a technology decision, while keeping versioned records of the changes.
Why use it?
It prevents updates from becoming an untracked rewrite and preserves how the idea developed over time. It can also ask which concept to update when no file is named.

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/konzept-update
Clone the repo
git clone --depth 1 https://github.com/jonase47/ccpr

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 konzept-update

README.md
[![agentmods](https://agentmods.dev/badge/commands/jonase47/ccpr/konzept-update.svg)](https://agentmods.dev/commands/jonase47/ccpr/konzept-update)
Your own site
<a href="https://agentmods.dev/commands/jonase47/ccpr/konzept-update"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/konzept-update.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 1,398 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 $0.01398
Opus 5 $0.00000 $0.00699
Sonnet 5 $0.00000 $0.00280
Haiku 4.5 $0.00000 $0.00140

Measured today against content hash 8c866749999f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

konzept-update 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 today.

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/konzept-update.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/konzept-update – Revise an existing rough concept

Purpose

This command updates an existing rough concept based on new findings, clarified open questions, or changed requirements. Each revision is versioned and timestamped so that the evolution of the concept remains traceable.


Execution

Step 1 – Load the concept file

Check whether the user named a file:

  • If yes: read it completely.
  • If no: search the docs/concepts/ directory for concept files and display a compact selection list:

    "Which concept should be updated? [List of found files with title and current version]"

Wait for the selection before continuing.


Step 2 – Clarify reason for change & context

Check whether the user has already described in the initial prompt what has changed or what should be updated.

If not sufficiently described, ask once briefly:

"What has changed or should be re-evaluated? (e.g. clarified tech stack decision, new scope, changed requirement)"

If the user also named an input file with new notes or decisions: read it as well and process it as context.


Step 3 – Parallel analysis by sub-agents

Start three sub-agents in parallel using the Task tool. Each agent receives both the existing concept and the change context. Ambiguities are marked as [UNCLEAR: ...] – do not make assumptions.

Sub-Agent A – What changes in content?
  • Which sections of the concept are affected by the change?
  • What specifically needs to be reformulated or added?
  • Are there contradictions with the existing concept that need to be resolved?
Sub-Agent B – Impact on scope & open questions
  • Does the change affect the scope (In Scope / Out of Scope)?
  • Which previously open questions from Chapter 5 are now answered?
  • Do the changes create new open questions or dependencies?
Sub-Agent C – Impact on risks & next steps
  • Does the change alter the risk assessment?
  • Do risks fall away, do new ones arise?
  • What are the updated next steps?

Read the full file on GitHub · 166 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. today Changed · +3 lines 8c866749999f
  2. 3d ago First seen · 163 lines · 0 tokens per session scan A 89171df1e09d

Subscribe to this mod's changes

konzept-update is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,398 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.