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.
git 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/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/agents/monkey1wizard/golem-agents-legion/golem-designer"><img src="https://agentmods.dev/badge/agents/monkey1wizard/golem-agents-legion/golem-designer.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 | $0.00029 | $0.02976 |
| Opus 5.5 | $0.00012 | $0.01190 |
| Sonnet 5.5 | $0.00006 | $0.00595 |
| Haiku 4.5 | $0.00003 | $0.00298 |
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 13d 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 — 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): thedesignercommand runs you throughgal dispatch-script golem-designerwith native isolation; only your verdict/summary returns to main context. Label your response[golem-designer · isolated]./designer discuss→ in-context: thedesignercommand runsgal consult-script golem-designerand loads activation-core into the current conversation. Continue multi-turn until the topic changes. Label responses [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
AGENTS.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 - Record the
DESIGN.mdpointer in.dev/project.mdso regeneratedAGENTS.mdcarries the design-system reference.
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.
- 13d ago Changed 7581993f95c4
- 14d ago Changed d28424f9aa2d
- 1mo ago Changed 86c9118abd0c
- 1mo ago 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 (14 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 2,976 once invoked, about $0.0001 per session on Opus 5.5. 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
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.
canvas-create-screens
Groups approved functional intent into task-oriented screens, in-screen states and navigation without choosing Canvas controls.
ijfw-accessibility-reviewer
Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.
design
Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.
mobile-ux-optimizer
Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…
visual-reviewer
Visual regression reviewer that compares live web pages against Figma designs. Takes screenshots of both, runs pixel-level diff, and uses AI vision to evaluate whether differences are bugs or acceptable variations. Use before merge or deployment to catch visual regressions.