design

design is a command for Claude Code from ethanaubuchon/dossier-tradecraft. It costs 29 tokens per session (2,192 once invoked), scanned A, original, MIT.

An interactive design-planning command for deciding how a feature, recipe, or system should work before implementation is scoped. It keeps the reasoning in a reusable design note and revisits that note when the command is run again.

In plain words
What is it for?
Use it to explore options, settle an approach, refine an existing design, and record connected decisions about architecture, components, and data flow.
Why use it?
It reduces the risk of starting implementation before the main structure and decisions are clear. It also keeps the reasons behind those decisions available across later sessions.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Use it to explore options, settle an approach, refine an existing design, and record connected decisions about architecture, components, and data flow.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/ethanaubuchon/dossier-tradecraft/design
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.

Clone the repo
git clone --depth 1 https://github.com/ethanaubuchon/dossier-tradecraft

Made for: Claude Code.

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 design

README.md
[![agentmods](https://agentmods.dev/badge/commands/ethanaubuchon/dossier-tradecraft/design/github.svg)](https://agentmods.dev/commands/ethanaubuchon/dossier-tradecraft/design)
Your own site
<a href="https://agentmods.dev/commands/ethanaubuchon/dossier-tradecraft/design"><img src="https://agentmods.dev/badge/commands/ethanaubuchon/dossier-tradecraft/design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for design

Your own site · 80×15
<a href="https://agentmods.dev/commands/ethanaubuchon/dossier-tradecraft/design"><img src="https://agentmods.dev/badge/commands/ethanaubuchon/dossier-tradecraft/design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,192 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00029 $0.02192
Opus 5 $0.00015 $0.01096
Sonnet 5 $0.00006 $0.00438
Haiku 4.5 $0.00003 $0.00219

Measured 11d ago against content hash ff160452686f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design 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 11d 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.

commands/design.md · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are starting a /design session. The topic (if provided): $ARGUMENTS

This is the /design recipe of the dossier-tradecraft framework — early-stage design exploration for settling the shape of a feature/recipe/system before its implementation gets scoped.

Principles

  • Vault is the home. The design note lives in the vault as long-lived rationale across many sessions. If we're in a repo, that's additive context — not a different destination.
  • Re-entry is typical. Most invocations refine an existing design note rather than creating a new one. Search by tag (design) + topic, not by path.
  • Required structural element: an ## Approach section. Forces synthesis posture; prevents option-collection-without-decision. Other sections are agent-driven per topic.
  • Holistic refinement, not Unknowns walk. Design iteration touches intertwined elements (architecture, components, data flow). EXISTING-DESIGN mode presents a summary and invites refinement — no checklist to walk.
  • Agent-judged writes. Decide slug, structure, and edits directly; surface what was done so the user can redirect post-hoc. No propose-then-approve gates.
  • Inline integration. Findings during the session land in the design note itself, including those from inline research methodology (see Step 4.c). Research is methodology used inside this recipe, not a separate destination — there's no standalone research-note kickback.
  • Loop exits on natural signal. No 3-option decision matrix at every cycle.

Workflow

  1. Load context. Invoke the load-context skill (vault grounding: profile, inbox check, project area pre-warm). If the working directory is inside a git repo, also note the cwd, current branch, and whether a project agent-instruction file (CLAUDE.md, AGENTS.md, etc.) is present.

  2. Resolve design doc. Search the vault for an existing design note on this topic.

    • Use mcp__dossier-mcp__search_notes with the topic terms; filter for tag:design if the search supports it, otherwise check the tags field on each candidate.
    • 1 match → call mcp__dossier-mcp__get_note to load it, enter EXISTING-DESIGN MODE.
    • >1 match → list candidates briefly (slug + title) and ask the user which to continue with.
    • 0 matches → before writing, surface "no existing design note found for this topic, creating a new one" so the user can redirect if they expected a match. Then enter NEW-DESIGN MODE.

Read the full file on GitHub · 106 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. 11d ago First seen · 106 lines · 29 tokens per session scan A ff160452686f

Subscribe to this mod's changes

design is a command published in the GitHub repository ethanaubuchon/dossier-tradecraft (3 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 2,192 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 2026-08-31.