design-engineer:document

A command for recording project decisions, lessons, current state, and messages for stakeholders. Stakeholders are people who need updates about or have an interest in the project.

In plain words
What is it for?
Use it to save session progress, record decisions, document project status, or prepare communication for stakeholders.
Why use it?
It preserves important context between coding sessions and during handoffs, so work does not depend on one conversation's history.

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/volomydyr/design-engineer-plugin/document
Clone the repo
git clone --depth 1 https://github.com/volomydyr/design-engineer-plugin
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 619 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 $0.00619
Opus 5 $0.00012 $0.00309
Sonnet 5 $0.00005 $0.00124
Haiku 4.5 $0.00002 $0.00062

Measured 2d ago against content hash 574a6fa5ed60, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

design-engineer: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.

commands/document.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Documentation

Plugin paths

Your conversation context contains a line DESIGN_ENGINEER_PLUGIN_ROOT: <absolute path> injected by the plugin's UserPromptSubmit hook. Whenever this command references ${DESIGN_ENGINEER_PLUGIN_ROOT}/..., substitute the absolute path from that context line. No shell commands are run from this command body.

Context

#$ARGUMENTS

Documents decisions, learnings, and project state. Ensures context survives across sessions and team handoffs.

Step 1: Read project context

  1. Read .design-engineer-plugin/config.yaml for mode and project state
  2. Scan existing deliverables in design/
  3. Check what has changed recently (git status if available)

Step 2: Determine what to document

If arguments contain "status", show current project status and recent changes directly.

If arguments contain "stakeholder", jump to stakeholder communication directly.

Otherwise, present what makes sense based on context:

question: "What would you like to document?"
header: "Document"
options:
  - label: "This session's progress"
    description: "Save this session's work – what changed, what was created, what's next"
  - label: "Record a decision"
    description: "Record a decision and why – so future you (or your team) understands the reasoning"
  - label: "Project status"
    description: "See the full project status – what's done, what's in progress, what's next"
  - label: "Stakeholder summary"
    description: "Frame decisions and trade-offs for non-design audiences"

Step 3: Execute

Read ${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/meta-document/SKILL.md and follow its instructions for the selected path. Do NOT use the Skill tool — plugin skills set disable-model-invocation: true.

In Guided mode: present a draft, ask for review, then save. In Autopilot: execute and save, show summary.

Step 3.5: Pre-finalize advisor checkpoint

Before writing the deliverable to disk (or after a draft is staged but before the user-facing confirmation), consult the advisor by Reading ${DESIGN_ENGINEER_PLUGIN_ROOT}/skills/advisor/SKILL.md and following its instructions (do NOT use the Skill tool — plugin skills disable model invocation) with: what's being documented, the framing chosen, anything that felt uncertain or contested, and "I'm about to finalize this as the documented record – any course correction?" Apply the advice. Skip on routine status-only updates (status argument) where the document is a flat snapshot of project state.

Read the full file on GitHub · 61 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 · 61 lines · 23 tokens per session scan A 574a6fa5ed60

Subscribe to this mod's changes

design-engineer:document is a command published in the GitHub repository volomydyr/design-engineer-plugin (19 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 619 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.