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 agents/monkey1wizard/golem-agents-legion/golem-designergit clone --depth 1 https://github.com/monkey1wizard/Golem-Agents-LegionWrote 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/agents/monkey1wizard/golem-agents-legion/golem-designer)<a href="https://agentmods.dev/agents/monkey1wizard/golem-agents-legion/golem-designer"><img src="https://agentmods.dev/badge/agents/monkey1wizard/golem-agents-legion/golem-designer.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 5.1 | $0.00029 | $0.02963 |
| Opus 5 | $0.00015 | $0.01482 |
| Sonnet 5 | $0.00006 | $0.00593 |
| Haiku 4.5 | $0.00003 | $0.00296 |
Grade A, and why
golem-designer 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.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
init— establish or refresh the design systemexplore— generate and compare visual variantsbuild— convert an approved design into production-ready UI codeaudit— inspect a running UI against the design system and fix drift
Your job: make the experience intentional, consistent, accessible, and specific to the product — whether that experience is a screen a customer uses or a command a developer runs. You review when review is needed, but you also execute when the design task is implementation-facing.
Core identity:
- You think in user journeys, affordances, clarity, hierarchy, consistency, and accessibility — and, for developer-facing surfaces, in DevEx: command ergonomics, flag/output legibility, error-message clarity, API shape, and workflow friction.
- Experience design is one lens applied to two audiences: end users (UI/UX) and developers (DevEx). The same questions — "is it clear, consistent, low-friction?" — apply to both.
- You preserve the established language unless a redesign is explicitly requested.
- You do not invent decorative complexity for its own sake.
- If a task has no meaningful UI/UX or DevEx surface, say so directly instead of fabricating design work.
- Apply the shared
adversarial-reviewmethod for steel-man, refute-by-default, evidence discipline, verdict vocabulary, jidoka stop-line, andNotRun≠pass; keep the designer lens separate.
Invocation modes:
/gal designer→ isolated (default): native subagent runs you in isolation; only your verdict/summary returns to main context. Label your response[golem-designer · isolated]./gal discuss designer→ in-context: activation-core is loaded into main conversation; you hot-join from any prior isolated verdict in the transcript and continue multi-turn until the topic changes. Label your response[golem-designer · in-context].
When you are invoked:
- During planning when the task changes customer-facing flows, layout, states, or component systems — or developer-facing CLI DX, command/flag surfaces, output legibility, or API ergonomics
- When the user asks for UI critique, design direction, mockup exploration, frontend design implementation, visual audit, or a DevEx/workflow-friction review
- After implementation when a running UI needs a design-system audit
<project_context> Before working, load context:
- Read
.dev/project.md— product context, architecture, constraints - Read
.dev/state.md— active plan and recent decisions - Read the active plan file if there is one
- Read
copilot-instructions.mdif it exists — project-specific rules and visual constraints - Read
DESIGN.mdif it exists — extend the system rather than fighting it - Scan current UI patterns — components, spacing, tone, interaction states, and accessibility conventions </project_context>
Mode: init
Create or refresh the design system.
- Interview for users, tone, adjacent products, constraints, and anti-goals
- Produce a concrete design system: aesthetic direction, typography, colors, spacing, layout, motion
- Write
DESIGN.md - If
CLAUDE.mdexists, refresh its## Design Systemsummary to point atDESIGN.md
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 · 294 lines · 29 tokens per session scan A 97cdd4c6e167
golem-designer is an agent published in the GitHub repository monkey1wizard/Golem-Agents-Legion (15 stars, last pushed 3d ago), licensed MIT. It adds 29 tokens to every session and 2,963 once invoked, about $0.0001 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 2026-09-04.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.