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/the-sid-dani/second-brain-os/use-designgit clone --depth 1 https://github.com/the-sid-dani/second-brain-osWrote 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/the-sid-dani/second-brain-os/use-design)<a href="https://agentmods.dev/commands/the-sid-dani/second-brain-os/use-design"><img src="https://agentmods.dev/badge/commands/the-sid-dani/second-brain-os/use-design.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 | $0.00043 | $0.01098 |
| Opus 5 | $0.00022 | $0.00549 |
| Sonnet 5 | $0.00009 | $0.00220 |
| Haiku 4.5 | $0.00004 | $0.00110 |
Grade A, and why
use-design 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/use-design — swap the active design system
The user wants to swap the workspace's active design system to: $ARGUMENTS
Library: workspace/4-Resources/design-systems/
Active selection: ./DESIGN.md (workspace root)
Per-project override: workspace/1-Projects/<slug>/DESIGN.md takes precedence over root for that project
Workflow — execute these steps in order
Step 1 — Validate the argument
Check $ARGUMENTS:
- If empty: the user invoked
/use-designwith no brand. Skip to Step 2's "list and ask" branch. - If contains anything other than letters, digits, hyphens, underscores: REFUSE. The argument must match
^[a-zA-Z0-9_-]+$. Anything else (slashes, spaces, shell metacharacters) is rejected — print "Invalid brand name. Brand names must be alphanumeric with hyphens or underscores only." and stop. - If valid: continue to Step 2.
Step 2 — Resolve the brand
Run: test -f "workspace/4-Resources/design-systems/$ARGUMENTS/DESIGN.md" && echo FOUND || echo MISSING
- If FOUND: continue to Step 3.
- If MISSING (or
$ARGUMENTSwas empty): list available brands and ask the user to pick.
Show the list (72 brands). Tell the user: "BrandRun: ls workspace/4-Resources/design-systems/ | grep -v '^README' | sort$ARGUMENTSnot found. Pick one from the list above and re-run/use-design <brand>." Then stop. Do NOT proceed to copy.
Step 3 — Backup current DESIGN.md (so this swap is reversible)
Run: test -f DESIGN.md && cp DESIGN.md .DESIGN.md.previous && echo BACKED_UP || echo NO_PREVIOUS
- This preserves the previously-active brand at
.DESIGN.md.previousso a fat-fingered swap can be undone withcp .DESIGN.md.previous DESIGN.md. - If no DESIGN.md existed (first-time swap), skip the backup silently.
Step 4 — Detect what's currently active (for the diff summary)
Read the first 3 lines of the current DESIGN.md (if it exists) to extract the brand title (e.g., the # Title heading on line 1). Save this as PREVIOUS_BRAND. If no DESIGN.md, set to (none).
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.
- 3d ago First seen · 81 lines · 43 tokens per session scan A daade5e25c19
use-design is a command published in the GitHub repository the-sid-dani/second-brain-os (2 stars, last pushed 28d ago), licensed MIT. It adds 43 tokens to every session and 1,098 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
design-brief-builder
Generate Design-Brief.md through structured design interview.
design-maker
Generate complete design mockups via design tool MCP.
para-review
Walk through your PARA system to update statuses, archive completed items, and capture new ones.
para-status
Show an overview of your PARA system — item counts, statuses, and attention-needed flags.
para-add
Add a new item to any PARA category with the appropriate template.
para-capture
Quick-capture a note from the current conversation into a PARA item's log.