profile

profile is a command for Claude Code from cathrynlavery/diagram-design. It costs 16 tokens per session (458 once invoked), scanned A, original, MIT.

A command for managing saved client profiles used by the Diagram Design tools. Profiles store the design settings needed for a project.

In plain words
What is it for?
Use it to list, inspect, save, load, update, reset, or delete diagram-design profiles.
Why use it?
It avoids repeatedly entering or manually managing project design settings. It also checks profile names and project markers according to the documented rules.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the diagram-design plugin — 1 skill, 5 commands shipped together

Good fit Use it to list, inspect, save, load, update, reset, or delete diagram-design profiles.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/cathrynlavery/diagram-design/profile
About the project

Diagram Design is a tool for creating editorial-style diagrams as self-contained HTML and SVG files, covering layouts such as flows, system architectures, Sankey diagrams, maps, and schemas. Designers and coding-agent users can use it to produce branded static diagrams or redraw Mermaid and draw.io sources. The catalogue commands, plugin, and skill provide the agent workflow for generating these diagrams.

cathrynlavery/diagram-design · 35,796 stars · on GitHub · cathrynlavery.github.io

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/cathrynlavery/diagram-design

Made for: Claude Code.

Or install diagram-design, the plugin that ships this one along with the rest of its 1 skill, 5 commands.

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 profile

README.md
[![agentmods](https://agentmods.dev/badge/commands/cathrynlavery/diagram-design/profile/github.svg)](https://agentmods.dev/commands/cathrynlavery/diagram-design/profile)
Your own site
<a href="https://agentmods.dev/commands/cathrynlavery/diagram-design/profile"><img src="https://agentmods.dev/badge/commands/cathrynlavery/diagram-design/profile/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 profile

Your own site · 80×15
<a href="https://agentmods.dev/commands/cathrynlavery/diagram-design/profile"><img src="https://agentmods.dev/badge/commands/cathrynlavery/diagram-design/profile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 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 $0.00016 $0.00458
Opus 5 $0.00008 $0.00229
Sonnet 5 $0.00003 $0.00092
Haiku 4.5 $0.00002 $0.00046

Measured 10d ago against content hash c4a510ded471, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

profile 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 10d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • profile — 100% identical, 0 lines differ
commands/profile.md · 35 lines

What it actually says

Manage Diagram Design client profiles by following skills/diagram-design/references/profiles.md. Treat that reference as the source of truth for storage, strict slug validation, metadata, marker-first resolution, schema checks, and failure handling. Do not reimplement or relax its rules here.

Full argument string: $ARGUMENTS

Routing

  • No arguments → list, with the active project-marker or working-copy profile marked.
  • Bare <name> with no verb → load <name>.
  • switch <name> → synonym for load <name> even though switch is omitted from the short argument hint.
  • save [name], load [name], list, show, update [name], reset, and delete [name] → run that exact procedure from the reference.
  • Missing required name → list when useful, then ask. Never invent a slug.
  • Unknown verb or extra argument → show the accepted forms and stop without writing.

Required behavior

  1. Resolve the current installed skill directory before reading its working style-guide.md; do not assume the repository checkout is the active install.
  2. Treat .diagram-design as untrusted data. Accept only the exact marker grammar and canonical home profile path described in the reference.
  3. Confirm before overwriting an existing profile, changing a project marker, or deleting a profile. Never skip a confirmation because the command was invoked from a script.
  4. For marker-selected projects, read the profile directly and leave the installed working copy unchanged.
  5. For copy-over load, verify the destination after writing. If it is unwritable, offer the marker-based flow.
  6. After save/update, verify exactly one profile metadata header and an unchanged body.

Report the active profile and the canonical file or marker affected. Never claim a write succeeded without re-reading it.

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. 10d ago First seen · 35 lines · 16 tokens per session scan A c4a510ded471

Subscribe to this mod's changes

profile is a command published in the GitHub repository cathrynlavery/diagram-design (35,796 stars, last pushed yesterday), licensed MIT. It adds 16 tokens to every session and 458 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.