concept:init

A command that starts a structured concept-development session, creates its workspace, and checks which research tools are available.

In plain words
What is it for?
Use it to begin exploring a new idea, prepare concept files, and check whether tools such as web search or Crawl4AI are available.
Why use it?
It removes the setup work and records the session state and assumptions in one place before research begins.

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.init
Clone the repo
git clone --depth 1 https://github.com/ddunnock/claude-plugins
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,018 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 $0.00017 $0.01018
Opus 5 $0.00009 $0.00509
Sonnet 5 $0.00003 $0.00204
Haiku 4.5 $0.00002 $0.00102

Measured 2d ago against content hash f8801531a6e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

concept:init 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.init.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/concept:init

Initialize a new concept development session.

Procedure

Step 1: Create Workspace

Run the init script to create the .concept-dev/ workspace:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/init_session.py "$(pwd)"

Then initialize the assumption registry:

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

If a session already exists, report the existing session details and ask:

  • [A] Resume existing session (use /concept:resume)
  • [B] Start fresh (archive existing .concept-dev/ to .concept-dev.bak.TIMESTAMP/)

Step 2: Detect Research Tools

Detect available research tools using two methods:

2a: Detect Python packages (via shell import check)

Run check_tools.py to detect Python packages like crawl4ai. This uses python3 -c "import <pkg>" to check if the package is importable, and updates state.json with the results:

python3 ${CLAUDE_PLUGIN_ROOT}/scripts/check_tools.py --state .concept-dev/state.json --json

Python Packages (detected by check_tools.py):

  • crawl4ai — Deep web crawling (used via web_researcher.py, not MCP)

Always Available:

  • WebSearch (built-in)
  • WebFetch (built-in)
2b: Detect MCP tools (via ToolSearch)

Probe for available MCP research tools by attempting ToolSearch for each tier:

Tier 1 (Free MCP — probe each):

  • mcp__jina — Document parsing
  • mcp__fetch — MCP fetch
  • mcp__paper_search — Academic papers

Tier 2 (Configurable — probe each):

  • mcp__tavily — AI search
  • mcp__semantic_scholar — Academic API
  • mcp__context7 — Documentation search

Tier 3 (Premium — probe each):

  • mcp__exa — Neural search
  • mcp__perplexity — Perplexity Sonar

For each MCP tool, attempt a ToolSearch with select:<tool_name>. If found, mark as available. Merge MCP results with the Python package results already in state.json:

Read the full file on GitHub · 142 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 · 142 lines · 17 tokens per session scan A f8801531a6e6

Subscribe to this mod's changes

concept:init is a command published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 1,018 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.