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 skills add KbWen/agent-virtual-office --skill custom-brand-designgit clone --depth 1 https://github.com/KbWen/agent-virtual-officeWrote 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/skills/kbwen/agent-virtual-office/custom-brand-design)<a href="https://agentmods.dev/skills/kbwen/agent-virtual-office/custom-brand-design"><img src="https://agentmods.dev/badge/skills/kbwen/agent-virtual-office/custom-brand-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kbwen/agent-virtual-office/custom-brand-design"><img src="https://agentmods.dev/badge/skills/kbwen/agent-virtual-office/custom-brand-design.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.00416 |
| Opus 5.5 | $0.00009 | $0.00166 |
| Sonnet 5.5 | $0.00005 | $0.00083 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
custom-brand-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 2d 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.
This is a copy
100% identical to custom-brand-design — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Custom brand design
This is a project-specific example. Copy it to .agents/skills/custom-brand-design/SKILL.md and create the matching one-line framework metadata file .agent/skills/custom-brand-design if the project chooses to use it. It is not active merely because this template exists.
Project references
- Read approved brand guidance from
docs/design/brand.mdwhen that file exists and is relevant. - Read the selected task reference from
docs/design/<screen>.md. - Treat those files as project-owned design input. State which revision or export you could actually inspect; if unavailable, request a readable local export and identify the gap.
- Do not treat a URL as proof of access, inspection, or approval. Do not invent brand values or mark pending decisions approved.
Plan
Map each UI-affecting plan step to a named screen or component in the selected design reference. Record the required Tool, Link, Approved, and Coverage fields in the active Work Log's ## Design Reference block. The link must point to the actual artifact or readable export.
Implement
Use only approved, implementation-ready detail from the selected reference: component structure, layout, spacing, typography, colors, assets, interactive states, and responsive behavior where specified. Surface missing detail or conflicting guidance for resolution through the existing workflow. This skill supplements frontend-patterns; it does not replace it.
Review
Compare the implementation with the source material that was actually inspected. Record concrete evidence, deviations, and any owner decision in the review and Work Log. Never claim a visual comparison for inaccessible material or a state/viewport that was not checked.
Boundaries
Follow the canonical Agentic OS workflows and rules. This example cannot approve a design, bypass a gate, or replace framework skill registration. Use it only in its declared phases: plan, implement, and review.
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.
- 2d ago First seen · 32 lines · 23 tokens per session scan A cf7e2940df72
custom-brand-design is a skill published in the GitHub repository KbWen/agent-virtual-office (73 stars, last pushed 3d ago), licensed MIT. It adds 23 tokens to every session and 416 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to custom-brand-design, differing in 0 lines, and is treated as a copy.
custom-brand-design compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| custom-brand-designKbWen/agent-virtual-office | Skill | 73 | 3d ago | MIT | A | 23 | Claude Code, Codex |
| glassmorphismfengshao1227/ccg-workflow | Skill | 6.0k | 16d ago | MIT | A | 30 | Claude Code |
| liquid-glassfengshao1227/ccg-workflow | Skill | 6.0k | 16d ago | MIT | A | 43 | Claude Code |
| frontend-designfengshao1227/ccg-workflow | Skill | 6.0k | 16d ago | MIT | A | 75 | Claude Code, Codex |
| adaptfengshao1227/ccg-workflow | Skill | 6.0k | 16d ago | MIT | A | 51 | Claude Code |
| extractfengshao1227/ccg-workflow | Skill | 6.0k | 16d ago | MIT | A | 55 | Claude Code |
| normalizefengshao1227/ccg-workflow | Skill | 6.0k | 16d ago | MIT | A | 50 | Claude Code |