concept:blackbox

A command for describing a concept as connected functional blocks, relationships, guiding principles, and simple text diagrams. It explains what the concept should do without specifying implementation details.

In plain words
What is it for?
Use it after the problem statement is complete to outline possible architectures, their responsibilities, how their parts interact, and the capabilities they could provide.
Why use it?
It provides a shared high-level view before technical design begins. Comparing distinct functional approaches can reveal trade-offs without prematurely choosing tools or platforms.

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.blackbox
Clone the repo
git clone --depth 1 https://github.com/ddunnock/claude-plugins
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,333 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 $0.00028 $0.01333
Opus 5 $0.00014 $0.00666
Sonnet 5 $0.00006 $0.00267
Haiku 4.5 $0.00003 $0.00133

Measured 2d ago against content hash 13af26ae7dbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

concept:blackbox 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.blackbox.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/concept:blackbox

Phase 3 of concept development: black-box architecture.

Prerequisites

Run the prerequisite gate check:

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

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: .concept-dev/PROBLEM-STATEMENT.md

Procedure

Step 1: Set Phase

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

Step 2: Context Loading

Read .concept-dev/PROBLEM-STATEMENT.md and present:

===================================================================
BLACK-BOX ARCHITECTURE
===================================================================

Problem: [1-2 sentence summary]
Scope: [IN scope summary]
Key Constraints: [List]

I'll propose 2-3 high-level approaches to solving this problem.
Each approach describes WHAT the concept does at a functional level
— not HOW it's implemented.

For each approach, I'll describe:
  - Functional blocks and their responsibilities
  - Relationships between blocks
  - Guiding principles
  - Capabilities this architecture enables
  - Trade-offs

===================================================================

Step 3: Propose Approaches

Use the concept-architect agent. Present 2-3 distinct architectural approaches:

===================================================================
APPROACH 1: [Name]
===================================================================

CONCEPT: [2-3 sentence description]

FUNCTIONAL BLOCKS:
  [Block A] — [What it does, not how]
  [Block B] — [What it does, not how]
  [Block C] — [What it does, not how]

RELATIONSHIPS:
  [Block A] → [Block B]: [What flows between them]
  [Block B] ↔ [Block C]: [Bidirectional relationship]

PRINCIPLES:
  1. [Guiding principle]
  2. [Guiding principle]

ENABLES:
  - [Capability this approach uniquely enables]
  - [Capability]

TRADE-OFFS:
  + [Advantage]
  + [Advantage]
  - [Disadvantage]
  - [Disadvantage]

===================================================================
APPROACH 2: [Name]
===================================================================
[Same structure]

===================================================================
APPROACH 3: [Name]
===================================================================
[Same structure]

Read the full file on GitHub · 204 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 · 204 lines · 28 tokens per session scan A 13af26ae7dbd

Subscribe to this mod's changes

concept:blackbox is a command published in the GitHub repository ddunnock/claude-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 1,333 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.