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 skills/ccevans/bobbycode/bobby-designnpx skills add ccevans/bobbycode --skill bobby-designgit clone --depth 1 https://github.com/ccevans/bobbycodeWhat 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 | $0.00179 | $0.12423 |
| Opus 5 | $0.00089 | $0.06212 |
| Sonnet 5 | $0.00036 | $0.02485 |
| Haiku 4.5 | $0.00018 | $0.01242 |
Grade A, and why
design-site scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **Then fetch the stylesheet with `curl`** — not with a markdown-converting fetch tool, which strips `<link>` tags and loses the CSS entirely: How it starts
The opening of the file, as written. The whole thing — 766 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bobby Design Skill
Design Lead — takes a subject from nothing to a designed, built page. Runs the process a real design studio runs, and enforces the craft rules that keep output from looking generated.
Scope
This skill CREATES design. It produces art direction, design tokens, and built pages.
It is not the design reviewer. Auditing an already-running app against its brand and filing tickets is review-design (bobby-ux). If the user wants a critique of something already built, use that skill instead. If they want something designed or redesigned, you are in the right place.
Before Starting
Read these in parallel:
.claude/skills/bobby-design/learnings.md+.claude/skills/bobby-design/learnings.local.mdand.claude/skills/bobby-shared/learnings.md+.claude/skills/bobby-shared/learnings.local.md— anti-patterns to avoid.claude/skills/bobby-design/references/craft_principles.md— the craft rules. Non-optional..claude/skills/bobby-design/references/design_process.md— the full process detail.claude/skills/bobby-design/references/reference_teardown.md— how to extract a design doc from a reference.claude/skills/bobby-design/references/slop_checklist.md— the full do-not list. Binding..claude/skills/bobby-design/references/style_directory.md— catalogue of studied systems, for when the user has none.claude/skills/bobby-design/references/style_tile_template.md— the style tile spec- Any existing design system in the project —
CLAUDE.md, a tokens/theme file, existing component styles. If one exists, it wins. This skill fills gaps; it never silently overrides an established system.
The Three Rules (read before anything else)
These exist because the person you are designing for is usually not a designer. They are a solo dev, an indie hacker, or someone who just wants their thing to look good. The process only works if it respects that.
Rule 1 — The human reacts. You design.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 766 lines · 179 tokens per session scan A eed2139d8a01
design-site is a skill published in the GitHub repository ccevans/bobbycode (6 stars, last pushed 8d ago), licensed MIT. It adds 179 tokens to every session and 12,423 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
haiku
When writing a haiku for this bot, follow these conventions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.