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/localplugins/plugins/brand-newgit clone --depth 1 https://github.com/localplugins/pluginsWhat 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 | $0.00034 | $0.00525 |
| Opus 5 | $0.00017 | $0.00262 |
| Sonnet 5 | $0.00007 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
brand-new 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 yesterday.
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
/brand-new
Create a versioned visual brand profile in the user's repo. Zero-permission unless the user asks to import from a URL (that one step is opt-in network use).
Steps
-
Pick a location. Single brand →
brand/. Multiple brands →brands/<slug>/. Ask for the slug if not given. -
Seed from the starter. Copy
templates/brand/(color-system.json,typography.json,visual-identity.md) into the target directory. -
Optional import. If the user supplied a source, propose a starter palette and fonts, then present them for the user to confirm or edit — never adopt them silently:
- Local SVG / PDF / CSS / HTML →
import { extractFromFile } from '../../lib/extract-brand.mjs'(no network). - Website URL →
import { extractFromUrl } from '../../lib/extract-brand-url.mjs'— the one opt-in network call; http(s) only, private/loopback addresses refused, body size- and time-capped.
Raster images (PNG/JPEG) aren't parsed locally — ask for an SVG, a PDF, or a URL. If a source is unreachable, yields nothing, or a PDF has no embedded fonts, fall back to Q&A for the missing fields.
- Local SVG / PDF / CSS / HTML →
-
Guided Q&A to fill the rest: brand name, three personality adjectives, tone, imagery style, colors (if not imported), heading/body fonts, do/don't rules.
-
Validate with
lib/brand.mjs→validateProfile; fix any flagged field (e.g. non-hex color, missing font family). -
Set active. Write the slug to
brand/.active. -
Confirm by running
/brand-statusso the user sees the loaded kit.
Font policy
If the user has a licensed font file, place it in the brand folder. If a font isn't
available locally, record a free/Google-font fallback in typography.json and tell
the user it's a substitution — never silently mismatch.
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.
- yesterday First seen · 37 lines · 0 tokens per session scan A 11196cc03f0a
brand-new is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 525 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
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.
sprint
Sprint lifecycle — plan a sprint, run a retrospective, or generate release notes.
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
analyze-test
Analyze A/B test results — statistical significance, sample size validation, and ship/extend/stop recommendations.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.