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 taurgis/sfcc-dev-mcp --skill sfcc-isml-developmentgit clone --depth 1 https://github.com/taurgis/sfcc-dev-mcpWrote 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/taurgis/sfcc-dev-mcp/sfcc-isml-development)<a href="https://agentmods.dev/skills/taurgis/sfcc-dev-mcp/sfcc-isml-development"><img src="https://agentmods.dev/badge/skills/taurgis/sfcc-dev-mcp/sfcc-isml-development/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/taurgis/sfcc-dev-mcp/sfcc-isml-development"><img src="https://agentmods.dev/badge/skills/taurgis/sfcc-dev-mcp/sfcc-isml-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Prompt Injection · line 51 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 198 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Prompt Injection · line 356 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
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 | $0.00051 | $0.02902 |
| Opus 5 | $0.00026 | $0.01451 |
| Sonnet 5 | $0.00010 | $0.00580 |
| Haiku 4.5 | $0.00005 | $0.00290 |
Grade A, and why
sfcc-isml-development 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 — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ISML Development (SFRA + Bootstrap 4)
This skill is SFRA-only. It intentionally avoids SiteGenesis patterns.
SFRA storefront markup is built around Bootstrap 4 (grid, forms, alerts, utilities). Keep your ISML consistent with existing SFRA markup and CSS conventions.
When to Use
- You’re editing
templates/default/**in an SFRA cartridge. - You need to apply/extend SFRA layout (
common/layout/page/common/layout/checkout). - You’re building reusable components via
<isinclude>and Bootstrap 4 markup. - You’re debugging output encoding, caching, or remote include behaviour.
When NOT to Use
- For business logic, data fetching, persistence, or complex transformations (belongs in controllers/models/scripts).
- For redesigning UI with a different framework (SFRA baseline expects Bootstrap 4).
Quick Checklist
[ ] No business logic in ISML (no data fetches, no persistence)
[ ] <isscript> used only for SFRA asset registration (CSS/JS)
[ ] Output encoding is NOT disabled unless justified and safe
[ ] <iscontent>/<isredirect>/<iscache> placement constraints respected
[ ] Remote includes used sparingly with security middleware
[ ] Template receives all data via pdict (controller owns data)
[ ] Markup uses Bootstrap 4 classes (grid, forms, alerts)
Where Templates Live (SFRA)
/my-cartridge/cartridge/templates/
/default # Default templates (SFRA)
/product/detail.isml
/util/modules.isml # Optional: <ismodule> tag definitions
/fr_FR # Locale overrides (use sparingly)
SFRA Golden Rule: Templates Are Presentation-Only
NEVER use <isscript> for business logic. The only exception is asset management:
<!-- ✅ Only acceptable use of isscript -->
<isscript>
var assets = require('*/cartridge/scripts/assets.js');
assets.addCss('/css/product.css');
assets.addJs('/js/product.js');
</isscript>
All data comes from controllers via pdict:
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.
- references/REMOTE-INCLUDES.md 3.9 KB
- references/sfra-base-templates-architecture.md 789 B
- references/SFRA-LAYOUTS.md 1.6 KB
- references/SFRA-PAGES-CART-ACCOUNT-AUTH.md 1.3 KB
- references/SFRA-PAGES-CATALOG.md 2.3 KB
- references/SFRA-STRUCTURE-COMPONENTS.md 1.5 KB
- references/UTILITIES-EXPRESSIONS.md 4.2 KB
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 · 371 lines · 51 tokens per session scan A efaa4a856b8d
sfcc-isml-development is a skill published in the GitHub repository taurgis/sfcc-dev-mcp (28 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 2,902 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
Frontend Performance Audit
Comprehensive audit of frontend performance — bundle size, code splitting, image optimization, font loading, service worker caching, Core Web Vitals, unused dependencies, and memory management. Use when asked to audit performance, bundle size, page speed, loading time, or Core Web Vitals.
Audit Chat AI Experience
Comprehensive audit of the SKAPARA generative AI chat interface — the store's core differentiator. Use when asked to audit the chatbot, AI experience, chat UI/UX, design generation pipeline, product recommendations via chat, or conversational commerce flows. Covers AI context awareness, tool usage, streaming…
Audit Admin
Comprehensive audit of the admin panel (Next.js on /panel). Use when asked to audit, review, or assess the admin — covering RBAC, permission guards, API auth, data isolation, audit logging, session management, and operational security.
Audit API
Comprehensive audit of ALL API routes across frontend, admin, and mcp-server. Use when asked to audit APIs, review endpoints, or assess API security — covering auth middleware, input validation, rate limiting, error handling, CORS, and data exposure.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
nebula-logger-install
Use this skill when the user wants to install and configure Nebula Logger in a Salesforce org for the first time. Covers package selection, installation paths, permissions, LoggerSettingsc hierarchy, and first-run troubleshooting.