concept:problem

A command for refining selected ideas into a bounded problem statement through structured questioning. Its 5W2H pattern covers who, what, when, where, why, how, and how much, while keeping proposed solutions for later.

In plain words
What is it for?
Use it in the problem-definition phase to clarify the current state, stakeholders, effects, desired state, constraints, scope, and measures of success.
Why use it?
It turns promising but broad ideas into a defined problem that can be researched and evaluated. It also prevents solution details from narrowing the problem too 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/ddunnock/claude-plugins/concept.problem
Clone the repo
git clone --depth 1 https://github.com/ddunnock/claude-plugins
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,450 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 $0.00027 $0.01450
Opus 5 $0.00014 $0.00725
Sonnet 5 $0.00005 $0.00290
Haiku 4.5 $0.00003 $0.00145

Measured 2d ago against content hash 71402a5a9257, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

concept:problem 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.

skills/concept-dev/commands/concept.problem.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/concept:problem

Phase 2 of concept development: problem definition.

Prerequisites

Run the prerequisite gate check:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/update_state.py --state .concept-dev/state.json check-gate problem

If this exits non-zero, stop and tell the user to complete the previous phase first.

Then load context:

  • python3 ${CLAUDE_PLUGIN_ROOT}/scripts/update_state.py --state .concept-dev/state.json show
  • Read IDEAS.md: .concept-dev/IDEAS.md

Procedure

Step 1: Set Phase

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/update_state.py --state .concept-dev/state.json set-phase problem

Step 2: Context Loading

Read .concept-dev/IDEAS.md and present a summary:

===================================================================
PROBLEM DEFINITION
===================================================================

Starting from your selected themes:

  1. [Theme A] — [brief summary]
  2. [Theme B] — [brief summary]

I'll ask questions to refine these into a clear problem statement.
We'll work in batches of 3-4 questions with checkpoints between.

IMPORTANT: If you think of specific solutions or technologies,
I'll note them for Phase 4 (Drill-Down) and keep us focused on
the problem itself.
===================================================================

Step 3: Metered Questioning

Use the problem-analyst agent pattern. Follow the metered questioning approach from references/questioning-heuristics.md.

Questioning Framework (adapted from 5W2H for concept development):

Batch 1: Current State

  1. What is the current situation? How do things work today?
  2. Who is affected by this situation? (stakeholders, users, operators)
  3. What are the consequences of the current state? What's the cost of inaction?
  4. How long has this been the case?

Checkpoint — Summarize understanding, confirm.

Read the full file on GitHub · 213 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 · 213 lines · 27 tokens per session scan A 71402a5a9257

Subscribe to this mod's changes

concept:problem is a command published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 1,450 once invoked, about $0.0001 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 2026-08-30.