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.
npx agentmods add commands/murphytrueman/design-system-ops/drift-checkgit clone --depth 1 https://github.com/murphytrueman/design-system-opsWrote 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.
[](https://agentmods.dev/commands/murphytrueman/design-system-ops/drift-check)<a href="https://agentmods.dev/commands/murphytrueman/design-system-ops/drift-check"><img src="https://agentmods.dev/badge/commands/murphytrueman/design-system-ops/drift-check.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00009 | $0.00262 |
| Opus 5 | $0.00005 | $0.00131 |
| Sonnet 5 | $0.00002 | $0.00052 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
drift-check 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 4d 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.
What it actually says
Run the drift-detection skill to identify where consuming teams are diverging from the design system.
Load the drift-detection skill from ${CLAUDE_PLUGIN_ROOT}/skills/drift-detection/SKILL.md and follow its complete workflow.
Before starting, read the knowledge notes declared in the skill's frontmatter references: field, located in ${CLAUDE_PLUGIN_ROOT}/knowledge-notes/.
Classify every drift instance into one of five categories: A (intentional divergence), B (version lag), C (accidental drift), D (misunderstanding), E (system gap). Apply severity weighting based on component criticality (Step 4a).
For each classification, provide the recommendation path routing to the appropriate next skill: A→decision-record, B→deprecation-process, C→design-to-code-check, D→change-communication, E→contribution-workflow.
If the user provides specific files or teams to check as an argument, focus on those: $ARGUMENTS
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.
- 4d ago First seen · 17 lines · 9 tokens per session scan A 48b81e7ab2dc
drift-check is a command published in the GitHub repository murphytrueman/design-system-ops (174 stars, last pushed 12d ago), licensed MIT. It adds 9 tokens to every session and 262 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.
Other commands, from other repositories
brand
Generate a full editorial brand-guidelines book for any URL. 14 chapters covering brand essence/archetype, colour, typography, spacing, shape, iconography, motion, components, voice, accessibility, tokens, and how-to-use guidance. Print-ready, dark-mode toggle, hand-off-ready single HTML.
pair
Fuse two extracted designs into a single hybrid identity. Pick which axis (colour, typography, spacing, shape, motion, voice, components) comes from which site. Defaults to "visual A × voice B" — same colours/spacing as the first URL, type/voice/components from the second.
theme-swap
Recolour an extracted site's design around a new brand primary. OKLCH hue rotation preserves perceptual lightness — neutrals, type, spacing, and motion stay untouched. Side-by-side HTML preview + recoloured tokens (DTCG, Tailwind, shadcn, Figma).
dna
Place a design in the measured design space — nearest systems, per-axis percentiles, outliers.
extract
Extract the complete design language from a URL — DTCG tokens, Tailwind, Figma vars, motion, voice, components.
fidelity
Measure how faithfully a clone reproduces a site — pixel-diff plus motion-fidelity into one 0-100 score, a letter grade, a ranked correction plan, and a shareable card.