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 doordash-oss/agentic-orchestrator --skill review-implementation-designgit clone --depth 1 https://github.com/doordash-oss/agentic-orchestratorWrote 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/doordash-oss/agentic-orchestrator/review-implementation-design)<a href="https://agentmods.dev/skills/doordash-oss/agentic-orchestrator/review-implementation-design"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/review-implementation-design/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/doordash-oss/agentic-orchestrator/review-implementation-design"><img src="https://agentmods.dev/badge/skills/doordash-oss/agentic-orchestrator/review-implementation-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Agent Snooping · line 57 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00013 | $0.02216 |
| Opus 5 | $0.00006 | $0.01108 |
| Sonnet 5 | $0.00003 | $0.00443 |
| Haiku 4.5 | $0.00001 | $0.00222 |
Grade A, and why
review-implementation-design 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 10d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Design axis for a multi-axis implementation review. The harness may run you at either the per-phase implementation gate for a frontend phase or the feature-level Final Review gate for a feature with any frontend phase.
You run with a live-run posture. Build, launch, render, screenshot, record, and drive the app as needed to judge visible UI quality. Treat the source tree as read-only. Write screenshots, recordings, command output, notes, and other live-run evidence only under the live-run evidence root named in your prompt, plus the required review-feedback.md. The harness owns phase_complete.
Output Files
| Artifact | Path | Requirement | Purpose |
|---|---|---|---|
review-feedback.md |
{helper_dir}/review-feedback.md |
required | structured review feedback markdown with findings, suggestions, and verdict |
Axis Scope
Own visible UI quality against the approved design, attached baseline images, and captured ### Visual Evidence screenshots:
- fidelity to the approved baseline, design artifact, feature intent, and phase or final-review scope
- layout correctness, spacing, visual hierarchy, responsive behavior, and non-overlapping text or controls
- accessibility basics: contrast, focus visibility, semantic structure, target size, reduced motion, and multimodal feedback
- interaction and state coverage visible in the UI: hover, focus, active, disabled, loading, empty, and error states
- subjective distinctiveness and originality when a distinctive direction was approved or visible in the baseline
At the per-phase gate, judge only the current frontend phase's committed UI work. At the Final gate, judge the assembled frontend experience across the completed feature.
Design Smells
Each smell reads what it is → how to fix; match it against the rendered UI and screenshots, and name the smell in each finding. Smells describe symptoms, not a house style — a brutalist page, a dense enterprise dashboard, and an expressive editorial layout can all pass.
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.
- 10d ago First seen · 100 lines · 13 tokens per session scan A 16506fbf8402
review-implementation-design is a skill published in the GitHub repository doordash-oss/agentic-orchestrator (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 13 tokens to every session and 2,216 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 2026-08-30.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.