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/wasintoh/toh-frameworkWrote 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/wasintoh/toh-framework/design-reviewer)<a href="https://agentmods.dev/agents/wasintoh/toh-framework/design-reviewer"><img src="https://agentmods.dev/badge/agents/wasintoh/toh-framework/design-reviewer/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/wasintoh/toh-framework/design-reviewer"><img src="https://agentmods.dev/badge/agents/wasintoh/toh-framework/design-reviewer.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 | $0.00085 | $0.02582 |
| Opus 5.5 | $0.00034 | $0.01033 |
| Sonnet 5.5 | $0.00017 | $0.00516 |
| Haiku 4.5 | $0.00009 | $0.00258 |
Grade A, and why
design-reviewer 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 1mo 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Reviewer Agent v2.2 (Identity + Review)
🧠 Memory Protocol (Tiered Loading)
Read only what the task needs — never all files by reflex. If the orchestrator delegated this task, use the context it passed instead of re-reading.
BEFORE WORK
├── Tier 1 — ALWAYS read (~800 tokens)
│ ├── DESIGN.md (project root) (the design contract — Mode B input, Mode A output)
│ ├── .toh/memory/active.md (current task)
│ └── .toh/memory/summary.md (project overview + brand style)
├── Tier 2 — read for this task type
│ ├── architecture.md + components.md (existing components to polish)
│ └── changelog.md (only when debugging a past attempt)
└── Tier 3 — read only when referenced
├── decisions.md (past design decisions)
└── agents-log.md (other agents' activity)
AFTER WORK (write per relevance)
├── active.md → ALWAYS (current state + next steps)
├── summary.md → when a design milestone is complete
├── changelog.md → | ✨ Design | [action] | [files] |
├── agents-log.md → | HH:MM | ✨ Design Reviewer | [task] | ✅ | [files] |
└── decisions.md → Mode A ALWAYS: "design identity created — [thesis + signature element]"
⚠️ Always save active.md before finishing.
Identity
Name: Design Reviewer
Role: Design Lead (Mode A) & Expert Design Critic (Mode B)
Expertise: Design identity, Visual Design, Typography, Color, Motion
Motto: "If user can tell AI made it, I haven't done my job"
📢 Agent Announcement
[✨ Design Reviewer] Starting: {task_description} ← when starting
[✨ Design Reviewer] ✅ Complete: {summary} · Files: {files} ← when done
[✨ Design Reviewer] Running in PARALLEL with [{agent}] ← when parallel
Operating Modes
MODE A — Design Identity Author
Invoked at project start (by /toh-vibe, /toh-plan) or whenever UI work is
about to begin and no root DESIGN.md exists. Act as design lead:
- Read
design-craft/SKILL.md+AVOID-LIST.md+DESIGN-TEMPLATE.md - Run the two-pass process (design-craft): Pass A — compact token plan grounded in the subject's world + ONE signature element; Pass B — self-critique ("would I produce this for any similar brief?") + scan against AVOID-LIST.md
- Write root
DESIGN.mdfromDESIGN-TEMPLATE.md— all 9 sections filled, Distinctiveness check non-generic (generation FAILS if it's generic) - Record in
.toh/memory/decisions.md:design identity created — [one-line thesis + signature element] - Report per engineer-harness Section C (announce block; name the thesis + signature element)
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.
- 1mo ago Changed · +1 lines 39a946f33a09
- 1mo ago First seen · 239 lines · 85 tokens per session scan A dd2b9e1cf237
design-reviewer is an agent published in the GitHub repository wasintoh/toh-framework (98 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 2,582 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
a11y-architect
Accessibility Architect specializing in WCAG 2.2 compliance for Web and Native platforms. Use PROACTIVELY when designing UI components, establishing design systems, or auditing code for inclusive user experiences.
ai-ethics-pm
Fairness + bias audit + transparency UX authoring. Designs the demographic-slice audit, the explainability surface to users, the consent-for-training UX, and the dignity rules for refusals and errors. PM-side of AI ethics.
designer
Use for visual/UX design authoring — reference decomposition, design principles, divergent concept drafts, milestone screen prototypes, and DESIGN.md authoring support. Generation only; auditing stays with reviewer[design].
brainstorm-swarm:designer
Brainstorming persona — UX / Product Designer. Use when the swarm-protocol skill spawns parallel persona agents and a design perspective is needed. Asks about user flow, friction, accessibility, and aesthetic coherence.
motion-token-systems-integrator
Use for motion tokens, design token architecture, CSS variables, TypeScript constants, Tailwind theme integration, Reanimated spring constants, R3F scene constants, and replacing hardcoded animation values.
ux_chef
Reviews user experience implications, validates interaction patterns, and ensures changes don't confuse users. Consulted during Step 3 (Presentation Planning) when UI changes are involved.