concept:document

A guided command for turning earlier concept work into a formal concept document and comparison of possible solutions. It requires reviewing assumptions and approving each section as it is written.

In plain words
What is it for?
Use it after the ideas, problem statement, functional overview, and detailed research are complete. It helps create the final concept document and solution landscape from those files.
Why use it?
It keeps important assumptions and earlier research from being overlooked. It also gives you checkpoints before the final documents are produced.

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.document
Clone the repo
git clone --depth 1 https://github.com/ddunnock/claude-plugins
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,625 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 $0.00023 $0.01625
Opus 5 $0.00012 $0.00813
Sonnet 5 $0.00005 $0.00325
Haiku 4.5 $0.00002 $0.00162

Measured 2d ago against content hash 1f34dcebc58d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

concept:document 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.document.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/concept:document

Phase 5 of concept development: document generation.

Prerequisites

Run the prerequisite gate check:

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

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 all artifacts:
    • .concept-dev/IDEAS.md
    • .concept-dev/PROBLEM-STATEMENT.md
    • .concept-dev/BLACKBOX.md
    • .concept-dev/DRILLDOWN.md

Procedure

Step 1: Set Phase

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

Step 2: Pre-Generation Review

Present a summary of all inputs:

===================================================================
DOCUMENT GENERATION
===================================================================

Inputs:
  IDEAS.md          — [N] themes, [N] ideas
  PROBLEM-STATEMENT — [1-sentence summary]
  BLACKBOX.md       — [N] functional blocks, [Approach name]
  DRILLDOWN.md      — [N] sub-functions, [N] sources, [N] gaps

I will generate two documents:

  1. CONCEPT DOCUMENT
     Modeled on engineering concept papers:
     Exec Summary → Problem → Concept → Capabilities →
     ConOps → Maturation Path → Glossary

  2. SOLUTION LANDSCAPE
     Per-domain approaches with pros/cons, citations,
     confidence ratings, and unresolved gaps

Each section will be presented for your approval before
being included in the final document.

Ready to begin?
===================================================================

Step 3: Mandatory Assumption Review

Before generating any document content, run the assumption review gate:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/assumption_tracker.py --registry .concept-dev/assumption_registry.json review

Read the full file on GitHub · 265 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 · 265 lines · 23 tokens per session scan A 1f34dcebc58d

Subscribe to this mod's changes

concept:document is a command published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 23 tokens to every session and 1,625 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.