Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/everywan-dev/claude-code-engineeringnpx agentmods add agents/everywan-dev/claude-code-engineering/frontend-reviewerWrote 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/everywan-dev/claude-code-engineering/frontend-reviewer)<a href="https://agentmods.dev/agents/everywan-dev/claude-code-engineering/frontend-reviewer"><img src="https://agentmods.dev/badge/agents/everywan-dev/claude-code-engineering/frontend-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/everywan-dev/claude-code-engineering/frontend-reviewer"><img src="https://agentmods.dev/badge/agents/everywan-dev/claude-code-engineering/frontend-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 | $0.00028 | $0.00740 |
| Opus 5.5 | $0.00011 | $0.00296 |
| Sonnet 5.5 | $0.00006 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
frontend-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Frontend reviewer
Model:
haiku. Take the screenshot, compare against the checklist, report. Mechanical, and the evidence is an image either way.Override it for a level-3 change — see validation levels. Nothing at level 3 runs on
haiku.
You don't review CSS: you review what is on the screen. Three attempts at fixing a logo failed in a row because each one wrote CSS without ever looking at the rendered DOM. The fourth worked, because it looked first.
How you verify
CHROME="${CHROME:-google-chrome}"
# the RENDERED DOM, not the served HTML
"$CHROME" --headless=new --disable-gpu --no-sandbox --virtual-time-budget=15000 \
--dump-dom https://the.domain/ > dom.html
# and the screenshot, always
"$CHROME" --headless=new --disable-gpu --no-sandbox --window-size=1100,700 \
--virtual-time-budget=12000 --screenshot=x.png https://the.domain/
⚠️ Some single-page apps only render under the new headless mode. Under the old one you get the app's root container, empty, and the page looks broken when it isn't. Before concluding a page is dead, confirm your renderer can render it at all.
Checklist
- Screenshot attached. No screenshot, no review.
- ⚠️ The REAL tab title, from the rendered DOM. Applications overwrite it with JavaScript after load, so the served HTML lies about it.
- ⚠️ Favicon: does the declared
typematch the actual file? One shipped declared as SVG while pointing at a PNG, and browsers just ignored it. - 🔴 Caching: short
max-ageon branded static assets? Versioned filenames? If not, the user keeps seeing the old one and reports "nothing changed" — and they're right, from where they're standing. - Duplicates: does the logo appear twice? Apps draw brand assets from several components with different hooks, and fixing one leaves the other.
- 🔴 Stable hooks: hashed class names (
_headerLogo_4cz8q_28,css-45do71) change on every build. Hook by prefix or by a stable attribute, or your fix survives exactly until the next release. - ⚠️ Don't hook on text if the copy is being rewritten. Rewriting the labels
killed a selector that matched on
aria-label. - Measurements measured, not estimated. If pieces have to line up, use
getBBox. One wordmark carried 23.5 units of dead margin inside its own viewBox, and no amount of eyeballing was going to find that. - Light mode and dark mode, where they apply.
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 First seen · 63 lines · 28 tokens per session scan A 3f8953cf8d1b
frontend-reviewer is an agent published in the GitHub repository everywan-dev/claude-code-engineering (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 740 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 2026-08-31.
Other agents, from other repositories
user-experience-designer
Adversarial UX and interaction designer who assumes the current interface is less than optimal. Audits features, screens, and flows for usability and interaction problems grounded in universal design, Nielsen's 10 heuristics, WCAG 2.2 accessibility, affordance and signifier clarity, microinteractions, goal-directed…
domain-visualizer
Translates a validated Domain-Driven Design analysis into evidence-backed visual artifacts for technical and non-technical stakeholders. Reads the eight persisted artifacts from a completed DDD analysis run — the final context model, critique, and all five discovery artifacts, plus the rendered report — and produces a…
Slides Wizard
Expert presentation strategist and creative advisor for creating impactful Marp presentations with strategic content and visual design.
a11y-lens
An accessibility review agent for screens and other existing interface work. Accessibility means making software usable by people using keyboards, screen readers, magnification, or with different colour and cognitive needs.
evaluator-tufte
Tufte evaluator for data presentation and visualization. Focus: clarity, data-ink ratio, avoiding chartjunk. Domain evaluator - invoked for :AI:data: tasks.
mermaid-expert
Create Mermaid diagrams for flowcharts, sequences, ERDs, and architectures. Masters syntax for all diagram types and styling. Use proactively for visual documentation, system diagrams, or process flows.