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/ssheleg/super-ux/brandgit clone --depth 1 https://github.com/ssheleg/super-uxWrote 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/ssheleg/super-ux/brand)<a href="https://agentmods.dev/commands/ssheleg/super-ux/brand"><img src="https://agentmods.dev/badge/commands/ssheleg/super-ux/brand.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 | $0.00042 | $0.01045 |
| Opus 5 | $0.00021 | $0.00522 |
| Sonnet 5 | $0.00008 | $0.00209 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
brand 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.
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.
Single entry point for the brand layer. The user is NOT expected to know the
files, fields or codes inside docs/brand/ — routing is your job. Idempotent:
safe to run at any stage, any number of times.
0. Understand the task
If $ARGUMENTS states it, route and skip the question. Otherwise ask ONE
plain question — "What do you need the product's text to do?" — with examples
in everyday words (a new landing page, a post, the interface sounds
inconsistent, we need a tone of voice, check everything).
Never ask the user to choose between skills or files.
| User says (any language) | Route to |
|---|---|
| "we have no tone of voice", "define how we sound" / "нужен тон оф войс" | 1 (Init) |
| "write X", "post for X", "landing copy" / "напиши текст", "пост" | 5 (Write) |
| "the copy is inconsistent" / "текстовка везде разная" | 4 then 6 |
| "check everything" / "проверь всё" | 4 (lint) then 6 (audit) |
| "we changed pricing / renamed a tier" / "переименовали тариф" | 3 (Update) |
| "this sounds like AI" / "звучит как нейросеть" | 5, Humanize mode |
| "don't know" / "просто посмотри" | run 1–3 of Inspect, recommend from state |
1. Inspect state
docs/brand/present? Which of the seven files exist.voice.md: pack,Status,Last calibrated, declared locales, and theHumanizationstate. An absent field is not silence: it means the pack defaultonapplies and nobody chose it, whichB064warns about. When the state isoff, report theHumanization declined:reason beside it, because an opt-out nobody can see is one nobody can safely reverse.facts.md: rows, how many with no source or pastReview by.channels.md: how many surfaces recorded, which of the product's surfaces are missing.strings.md: rows by status, how manydriftedororphan.locales/: declared versus present, parity where computable.- Run the linter
python3 docs/brand/lint.pyand fold its errors and warnings into the status. - Also read
docs/ux/foundation.mdif present — the pack derives from it, and a foundation newer thanLast calibratedis worth saying out loud.
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 · 81 lines · 42 tokens per session scan A 03333e459520
brand is a command published in the GitHub repository ssheleg/super-ux (3 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,045 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
querying
Query documents from a search index using type-safe filters with support for pagination, sorting, field selection, scoring, and highlighting. Count matching documents efficiently without returning results.
agent-brain-index
Index documents for semantic search.
agent
Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.
ingest
Manually add knowledge to the Weaviate store.
web-ingest
Crawl the configured source and generate knowledge markdown files.
web-update
Re-ingest a URL or refresh a local knowledge file, then rebuild the search index.