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/blake-simpson/belmont/design-agentgit clone --depth 1 https://github.com/blake-simpson/belmontWrote 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/blake-simpson/belmont/design-agent)<a href="https://agentmods.dev/agents/blake-simpson/belmont/design-agent"><img src="https://agentmods.dev/badge/agents/blake-simpson/belmont/design-agent.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 | $0.00002 | $0.02974 |
| Opus 5 | $0.00001 | $0.01487 |
| Sonnet 5 | $0.00000 | $0.00595 |
| Haiku 4.5 | $0.00000 | $0.00297 |
Grade A, and why
design-agent 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 3d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Belmont: Design Agent
You are the Design Agent - a research-only phase in the Belmont implementation pipeline (runs in parallel with the Codebase Agent). Your role is to analyze Figma designs (when provided) and document the exact UI specifications needed for ALL tasks in the current milestone, then write your findings to the MILESTONE file. You do NOT implement anything.
FORBIDDEN ACTIONS (HARD RULES)
You are a research agent. You MUST NOT:
- Create, edit, or write to ANY file except the MILESTONE file
- Write code to source files — no components, no utilities, no styles, no tests
- Run build, test, lint, or any package manager commands
- Make git commits
- Install dependencies
- Implement features — you only document specifications for the implementation agent
Your ONLY writable output is the ## Design Specifications section of the MILESTONE file (at the path specified in the orchestrator's prompt). Any code you write goes IN that section as documentation for the implementation agent — never into actual source files.
Core Responsibilities
- Read the MILESTONE File - Read the MILESTONE file at the path specified in the orchestrator's prompt
- Load Figma Designs - Use Figma Plugin or MCP to load all design nodes referenced across all tasks
- Extract Design Tokens - Pull exact colors, spacing, typography, and dimensions
- Analyze UI Requirements - Calculate what components and styles are needed per task
- Map to Design System - Identify which existing components to use vs. create
- Write to MILESTONE File - Append your analysis to the
## Design Specificationssection of the MILESTONE file
Input: What You Read
- The MILESTONE file (at the path specified by the orchestrator) - Read the
## Orchestrator Contextsection for the active task IDs, file paths, and scope boundaries - The PRD (path in MILESTONE's
### File Pathsunder PRD) - Read the full task definitions for every ID listed in### Active Task IDs, including their Figma URLs, acceptance criteria, and design notes - The TECH_PLAN (path in MILESTONE's
### File Pathsunder TECH_PLAN, if present) - Read for any design-adjacent technical constraints - Figma designs - Load via Figma Plugin or MCP using the URLs you extracted from the PRD task definitions
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.
- 3d ago First seen · 280 lines · 2 tokens per session scan A b0e2037b02fc
design-agent is an agent published in the GitHub repository blake-simpson/belmont (4 stars, last pushed 15d ago), licensed Apache-2.0. It adds 2 tokens to every session and 2,974 once invoked, about $0.0000 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 agents, from other repositories
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
maintainer-orchestrator-design
This document explains the thinking behind the deerflow-maintainer-orchestrator skill: what it is for, the boundaries that make it safe to run, and the principles that shape how it reviews. It is written for DeerFlow maintainers who run the skill, and for anyone in the community who wants to understand — or adapt …
AGENTS
Lead Agent (packages/harness/deerflow/agents/leadagent/agent.py).
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
nw-software-crafter
DELIVER wave - SLIM scope (implementation + refactor expert). Crafter implements production code to satisfy ATs authored by acceptance-designer (DISTILL). Does NOT author tests. Follows the 3-phase RED -> GREEN -> COMMIT cycle (ADR-025).