full-diagnostic

full-diagnostic is a command for coding agents from murphytrueman/design-system-ops. It costs 6 tokens per session (368 once invoked), scanned A, original, MIT.

A command that runs a broad health review of a design system, the shared rules and components used to build interfaces. It combines audits of tokens, naming, components, divergence, documentation, and overall health, with optional theme and Figma checks.

In plain words
What is it for?
Use it for a comprehensive review of token structure, naming conventions, component coverage, team divergence, documentation gaps, themes, Figma variables, and system health.
Why use it?
It brings separate audit results into one diagnostic report, so teams can see related problems together instead of reviewing isolated checks. The final health assessment summarises the earlier findings.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the design-system-ops plugin — 40 skills, 14 commands shipped together

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/murphytrueman/design-system-ops/full-diagnostic
Clone the repo
git clone --depth 1 https://github.com/murphytrueman/design-system-ops

Or install design-system-ops, the plugin that ships this one along with the rest of its 40 skills, 14 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 full-diagnostic

README.md
[![agentmods](https://agentmods.dev/badge/commands/murphytrueman/design-system-ops/full-diagnostic.svg)](https://agentmods.dev/commands/murphytrueman/design-system-ops/full-diagnostic)
Your own site
<a href="https://agentmods.dev/commands/murphytrueman/design-system-ops/full-diagnostic"><img src="https://agentmods.dev/badge/commands/murphytrueman/design-system-ops/full-diagnostic.svg" alt="Measured on agentmods" height="20"></a>
Per session 6 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 368 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 $0.00006 $0.00368
Opus 5 $0.00003 $0.00184
Sonnet 5 $0.00001 $0.00074
Haiku 4.5 $0.00001 $0.00037

Measured 5d ago against content hash 58ee1ba27d5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

full-diagnostic 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 5d 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/full-diagnostic.md · 27 lines

What it actually says

Run the full system diagnostic — a comprehensive health sweep that chains six audit skills (plus conditional theme and Figma audits) into a unified diagnostic report.

Load the agent instructions from ${CLAUDE_PLUGIN_ROOT}/skills/full-system-diagnostic-agent.md and follow the complete workflow.

Before starting, read the reference material for each chained skill from the references: field of each skill's frontmatter, located in ${CLAUDE_PLUGIN_ROOT}/knowledge-notes/.

The diagnostic runs in this order:

  1. Token audit — token architecture, naming, structural debt
  2. Naming audit — convention consistency, ambiguity, intent clarity
  3. Component audit — inventory, usage, duplication, coverage gaps
  4. Drift detection — where teams diverge and why
  5. Docs coverage — documentation that has fallen behind the components (coverage gaps, staleness)
  6. System health — scored assessment across 7 dimensions, run last so it synthesises everything upstream

Conditional steps run before system-health when they apply: theme audit (if the system supports theming) and Figma variable audit (if Figma is configured).

After running the chain, use the synthesis decision tree (Phase 3) to identify cross-skill patterns: concentrated debt, documentation gaps, governance gaps, structural gaps, AI-readiness gaps, platform maturity gaps, or dependency cascades.

Produce a unified diagnostic report with: executive summary, per-skill findings table, cross-skill patterns, and a ranked action list ordered by impact.

If the user provides context about their system: $ARGUMENTS

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. 5d ago First seen · 27 lines · 6 tokens per session scan A 58ee1ba27d5a

Subscribe to this mod's changes

full-diagnostic is a command published in the GitHub repository murphytrueman/design-system-ops (175 stars, last pushed 13d ago), licensed MIT. It adds 6 tokens to every session and 368 once invoked, about $0.0000 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.