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 evolplus/talos --skill fe-framework-coding-standardgit clone --depth 1 https://github.com/evolplus/talosWrote 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/evolplus/talos/fe-framework-coding-standard)<a href="https://agentmods.dev/skills/evolplus/talos/fe-framework-coding-standard"><img src="https://agentmods.dev/badge/skills/evolplus/talos/fe-framework-coding-standard/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/evolplus/talos/fe-framework-coding-standard"><img src="https://agentmods.dev/badge/skills/evolplus/talos/fe-framework-coding-standard.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 | $0.00111 | $0.02424 |
| Opus 5.5 | $0.00044 | $0.00970 |
| Sonnet 5.5 | $0.00022 | $0.00485 |
| Haiku 4.5 | $0.00011 | $0.00242 |
Grade A, and why
fe-framework-coding-standard 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FE Framework Coding Standard
When to use
You are FE Dev implementing or reviewing UI code after the stack is declared in the signed-off SRS. This skill standardizes how to write framework-specific code without turning every task into a framework migration.
Inputs and outputs
- Inputs: task assignment,
docs/SRS.mdheaderFrontend-Framework:, SRS §3.4.2 UI Introspection Profile, SRS §3.4.5 Source Layout, SRS §3.4.6 Environment Configuration, SRS user story / FR / NFR IDs, design handoff, Reference Render, Visual Composition Contract, Asset Export Manifest, Design Element Manifest, visual spec assertions, instrumentation contract, architecture decisions, current frontend source tree, installed framework versions and libraries. - Outputs: framework-native UI code that follows the project's existing architecture, names stable test selectors, implements every required Figma field/item/copy/action, reproduces the contracted composition, uses every required exported asset, handles loading / error / empty states, satisfies design tokens where available, and includes the appropriate unit / component / E2E updates.
Framework selection
- Read
docs/SRS.mdbefore inspecting package files. The headerFrontend-Framework:is authoritative. - If the header is one supported value, select that framework reference.
- If the header is
multiple, select the framework from the row that owns the task:- use SRS §3.4.2 for a surface-driven task;
- use SRS §3.4.5 for a path/app-driven task;
- if the task maps to more than one framework or no row matches, halt with
NEEDS_CONTEXTand cite the candidate SRS rows.
- If the header is
N/A, do not perform FE framework implementation; report that no frontend framework applies. - If the header is missing,
TBD, unsupported, or inconsistent with §3.4.2 / §3.4.5, halt and return the work to BA:- greenfield/authored SRS: BA Phase 1.X step 10c must ask the user to choose;
- brownfield/extracted SRS: BA Mode E must detect from source evidence and write the SRS field.
- After selecting the reference, inspect package files/source only as a consistency check. If code evidence contradicts the SRS-selected framework, halt and raise an open issue; do not silently switch references.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 106 lines · 111 tokens per session scan A 73a4afc402fa
fe-framework-coding-standard is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 16d ago), licensed Apache-2.0. It adds 111 tokens to every session and 2,424 once invoked, about $0.0004 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 skills, from other repositories
engineering-frontend-developer
A frontend development guide for modern web interfaces built with React, Vue, or Angular. Frontend code is the part of a website or web app that users see and interact with.
frontend-review
Review React/Vue components for a11y, state, and re-render bugs.
pr-check-frontend
Frontend PR checklist for React, Next.js, Vue.js, Tailwind CSS, and React Query (F1–F16). Use when user says "frontend review", "review my React/Vue PR", "check my UI code", working in a frontend repo, or when the diff contains .tsx/.vue/.css files. For the full review workflow, use pr-review.
zoom-meeting-sdk-web-component-view
Zoom Meeting SDK Web - Component View. Embeddable Zoom meeting components with Promise-based API for flexible integration. Ideal for React/Vue/Angular apps and custom layouts. Uses ZoomMtgEmbedded with async/await patterns and embeddable UI containers.
add-localization
Adds or extends multilingual localization in a Power Pages code-site SPA. Use whenever the user asks to translate, localize, internationalize, support multiple languages, add a language selector, add locale routes, repair an i18n setup, or add languages to an existing React, Vue, Angular, or Astro Power Pages site.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.