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 skills add verivus-oss/llm-cli-gateway --skill design-review-cyclegit clone --depth 1 https://github.com/verivus-oss/llm-cli-gatewayWrote 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/skills/verivus-oss/llm-cli-gateway/design-review-cycle)<a href="https://agentmods.dev/skills/verivus-oss/llm-cli-gateway/design-review-cycle"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/design-review-cycle/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/skills/verivus-oss/llm-cli-gateway/design-review-cycle"><img src="https://agentmods.dev/badge/skills/verivus-oss/llm-cli-gateway/design-review-cycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 44 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 47 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 48 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00062 | $0.02546 |
| Opus 5 | $0.00031 | $0.01273 |
| Sonnet 5 | $0.00012 | $0.00509 |
| Haiku 4.5 | $0.00006 | $0.00255 |
Grade A, and why
design-review-cycle 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 11d 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Review Cycle
Review a design, specification, or implementation plan before code changes make the decision expensive to reverse. Dispatch every review through the local gtwy stdio MCP server, not by launching provider CLIs directly.
The gateway has seven CLI request surfaces: Claude, Codex, Gemini, Grok, Mistral, Devin, and Cursor. Each has a sync request tool and an async request tool when async jobs are enabled. Grok, Mistral, Devin, and Cursor also expose native ACP transports, but review requests still go through the gateway request tools.
Configured API providers can add generic request tools. Discover them with
list_models and their reported capabilities. They do not supply a local CLI
checkout/worktree or native ACP boundary, so they are not an automatic
replacement for a source-inspecting required CLI reviewer.
Start With Scope, Capability, and Target Checks
- Call provider_tool_capabilities through gtwy to discover the usable request surface, native transport capability, and local provider state.
- Define the review roster. A full cross-LLM review requires every provider that the user or process names. Do not silently reduce that roster because a provider is slow or unavailable.
- Verify that every reviewer will inspect the same repository and revision. A review of a default or unrelated workspace is invalid.
- If Personal Agent Config Kit mode is enabled, it supports Claude, Codex, and
Mistral only. route_request and normal cross-provider validation surfaces are
unavailable. A requested seven-provider review is therefore blocked until
Kit is disabled for that workflow or the user explicitly changes scope.
Claude and Mistral Kit requests also reject caller-supplied
workingDirbefore context compilation.explain_effective_config({workingDir:"<repo>"})can inspect a candidate scope, but execute that Kit work with an already configured registeredworkspacealias or the configured default workspace. It never inherits the gateway process cwd.
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.
- 11d ago First seen · 235 lines · 62 tokens per session scan A ff72fc6902a8
design-review-cycle is a skill published in the GitHub repository verivus-oss/llm-cli-gateway (15 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 2,546 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
web-artifacts-builder
Suite of tools for creating elaborate, multi-component agent-platform.local HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
prototype
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine…
motion-patterns
Production-ready animation patterns for React / Next.js — button, modal, toast, stagger, page transitions, exit animations, scroll, and layout — built on motion-foundations tokens and springs.
brand-guidelines
Applies Google's official brand colors and typography to any sort of artifact that may benefit from having Google's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
spatial-canvas-layout
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.