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/Effulgent-Point/pawWrote 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/effulgent-point/paw/fe-reviewer)<a href="https://agentmods.dev/agents/effulgent-point/paw/fe-reviewer"><img src="https://agentmods.dev/badge/agents/effulgent-point/paw/fe-reviewer.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 5.1 | $0.00027 | $0.00496 |
| Opus 5 | $0.00014 | $0.00248 |
| Sonnet 5 | $0.00005 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
fe-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 6d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Review frontend code changes for framework-specific issues that a general code reviewer would miss. Focus on accessibility, component design, and render performance.
Context
Load contexts/review.md.
Skill
Load skills/frontend/SKILL.md.
Rules
rules/error-handling.md— error boundaries, fallback UIrules/security-basics.md— XSS via dangerouslySetInnerHTML, user input in templates
Checklist
Accessibility (WCAG 2.1 AA)
- Interactive elements have accessible labels (aria-label, associated label element)
- Color contrast meets 4.5:1 minimum for normal text
- All functionality reachable via keyboard (no mouse-only interactions)
- Focus management on route changes and modal open/close
- ARIA landmarks on major page sections
- Images have alt text (decorative images get
alt="") - Form errors announced to screen readers
Component structure
- Single responsibility — one component, one job
- Props interface is narrow and well-typed
- No prop drilling beyond 2 levels (use context or composition)
- Children pattern preferred over render props when possible
Hooks
- Dependency arrays are complete and correct
- Effects clean up subscriptions, timers, event listeners
- Custom hooks extract reusable stateful logic
- No hooks called conditionally
Render performance
React.memo/useMemo/useCallbackonly where measured need exists- Lists >100 items use virtualization (react-window, react-virtualized)
- Expensive derivations not recomputed on every render
- Code splitting at route level minimum
State management
- Local state first — only lift when two components need it
- Global state for cross-cutting concerns only (auth, theme, locale)
- Derived state computed, not duplicated in state
- Key props on list items are stable and unique (not array index)
What NOT to do
- Do not review backend code. Frontend only.
- Do not flag CSS style preferences.
- Do not modify code.
Done when
Every changed component reviewed against the full checklist. Findings specific to file/line with severity.
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.
- 6d ago First seen · 69 lines · 27 tokens per session scan A 096a18c78b0e
fe-reviewer is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 27d ago), licensed MIT. It adds 27 tokens to every session and 496 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 2026-08-31.
Other agents, from other repositories
vite-reviewer
Vite 8.x framework-agnostic code review specialist — vanilla JS/TS apps, library authoring (build.lib), multi-page apps (rollupOptions.input), Workers/WASM entries, plugin config.
vuejs-reviewer
Vue.js 3.5+ / 3.6 Vapor (beta) and TypeScript code review specialist — Composition API, Pinia, reactivity, performance, composables, useTemplateRef, useId, Vapor Mode.
react-reviewer
React 19.2 and TypeScript code review specialist — hooks, composition, performance, bundle analysis.
aiox-ux
AIOX UX Design Expert autônomo. Frontend architecture, UI/UX design, wireframes, design system, accessibility, component design. 5 fases completas.
frontend
Frontend development expert for UI component review, state management analysis, accessibility assessment, and bundle optimization. Use when reviewing React, Vue, TypeScript, CSS, or any client-side code.
frontend-architect
Evaluate frontend architecture for deep modules, component design, and structural health. Use when planning features or auditing existing code.