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/jrpease/throughline/design-system-statusgit clone --depth 1 https://github.com/jrpease/throughlineWrote 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/jrpease/throughline/design-system-status)<a href="https://agentmods.dev/commands/jrpease/throughline/design-system-status"><img src="https://agentmods.dev/badge/commands/jrpease/throughline/design-system-status.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 5.1 | $0.00000 | $0.00575 |
| Opus 5 | $0.00000 | $0.00287 |
| Sonnet 5 | $0.00000 | $0.00115 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
design-system-status 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 6d 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
Read design-system.json and present a clear, plain-language summary of where
the user's design system stands. This is the "where am I?" command — especially
valuable for users who don't want to read raw JSON.
Report, in friendly prose (not a JSON dump), scaled to user.codingLevel:
- Figma: connected? which mechanism? which file?
- Tokens: primitives / semantic / styles built? how many collections? intake mode? two- or three-tier?
- Foundations page, Icons: built? icon library + version + whether the code package is installed?
- Components: which have been built in Figma?
- Repo: what stage (folder / local-git / github)? remote?
- Sync: which platforms/adapters? any custom adapters? when last run?
- Storybook: initialized? Chromatic? Code Connect?
- Coding level + UI framework on record.
- Retrofit (brownfield only — skip the whole block if
tokens.intakeModeisn't"retrofit"andaudit.ranAtis null):- Audit: has it run (
audit.ranAt)? If so, the code-surface counts (audit.codeSurface), the Figma inventory (audit.figmaInventory— variables, bindings, text/effect styles, modes), and how semantic the system is (audit.percentSemantic). - Crosswalk: is it built (
tokenCrosswalk.path)? The status counts (tokenCrosswalk.statusCounts) and whether the validator is passing (tokenCrosswalk.validatorPassing). - Retrofit progress: which phase (
retrofit.phase), and whether the decision journal was scaffolded (retrofit.journalScaffolded).
- Audit: has it run (
Then suggest sensible next steps based on what's missing — e.g. "You've got
tokens and a repo but haven't synced yet — want to run /sync-figma-tokens?" or
"No components yet — want to build your foundational set?" Offer, don't force.
For a brownfield system, suggest the next retrofit step from the state: no audit yet
→ "want to run design-system-audit to size the retrofit?"; audited but no crosswalk
→ "want to build the crosswalk with token-crosswalk-builder?"; mid-retrofit
(retrofit.phase set, not "done") → "want to resume the retrofit at the <phase>
phase with retrofit-planner?".
If design-system.json doesn't exist, explain that no design system has been
set up in this folder yet and offer to run figma-environment-setup to start.
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.
- 6d ago First seen · 42 lines · 0 tokens per session scan A 6e1c4ca275a1
design-system-status is a command published in the GitHub repository jrpease/throughline (76 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 575 tokens. 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
profile
Save, load, inspect, update, reset, or delete diagram-design client profiles.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
team-ui
Orchestrate UI/UX design team.
p3-ux-wireframes
Creates wireframes (ASCII art) for the most important screens with interaction descriptions.