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 agentmods add instructions/taurgis/sfcc-dev-mcp/agents-mdgit 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/instructions/taurgis/sfcc-dev-mcp/agents-md)<a href="https://agentmods.dev/instructions/taurgis/sfcc-dev-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/taurgis/sfcc-dev-mcp/agents-md.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 | $0.10573 | $0.10573 |
| Opus 5 | $0.05287 | $0.05287 |
| Sonnet 5 | $0.02115 | $0.02115 |
| Haiku 4.5 | $0.01057 | $0.01057 |
Grade A, and why
sfcc-dev-mcp AGENTS.md 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 5d 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 — 691 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md – SFCC Development MCP Server (AI Coding Agent Instructions)
This file provides authoritative, agent-focused operational guidelines. It complements README.md by documenting build/test workflows, architectural conventions, and maintenance rules that would clutter a human-facing introduction.
Goals of AGENTS.md:
- Give any AI coding agent (Copilot, Cursor, Claude, Gemini, Aider, Factory, Ona, Devin, Zed, etc.) a predictable place to load project instructions
- Separate contributor onboarding (README) from deep operational detail (here)
- Encourage portable, open, plain-Markdown instructions (no proprietary schema)
Agent Operating Principles (Quick Commit Rules):
- Verify reality first (counts, structures) with commands—never guess
- Make surgical diffs—no drive‑by formatting or unrelated refactors
- Validate after every substantive change (build + lint + relevant tests)
- Prefer explicit, readable code & docs over clever abstractions
- Surface ambiguity or risky instructions with safer alternatives
- Keep
AGENTS.md↔README.mdin sync where they overlap (update both or neither) - Discover actual tool response formats with
npx aegis querybefore writing tests - Treat security (credentials, paths, network) as a first‑class concern—assume local but protect anyway
- Defer performance tuning unless a measurable issue exists; avoid premature micro‑optimizations
- Fail loud & clear: actionable error messages, user vs system error distinction
🤖 Unified Engineering Principles & Persona
Operate as a senior TypeScript / Node.js engineer with deep MCP + SFCC (OCAPI, SCAPI, WebDAV, logs, system objects, preferences) domain knowledge. Apply the following unified principles (consolidates former Persona, Professional Standards, Development Approach, and Development Guidelines):
Core Competencies
- MCP protocol compliance & tool schema rigor
- SFCC integration breadth: logs, job logs, OCAPI auth, system objects, site preferences
- Strong TypeScript typing, safe narrowing, interface-driven design
- OAuth + token lifecycle correctness
- Log & job execution analysis (parsing, summarization, health signals)
- Documentation ingestion (scan → parse → resolve → extract types)
- Multi-layer test strategy: Jest (unit) + Aegis YAML (declarative) + Node programmatic (stateful)
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.
- 5d ago First seen · 691 lines · 10,573 tokens per session scan A c254027de72c
sfcc-dev-mcp AGENTS.md is an instructions file published in the GitHub repository taurgis/sfcc-dev-mcp (27 stars, last pushed 5d ago), licensed MIT. It adds 10,573 tokens to every session, about $0.0529 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 instructions, from other repositories
salesforce-mcp-server CLAUDE.md
Instructions for advancedcommunities/salesforce-mcp-server, covering claude.md, build and development commands, build the typescript project, run development mode with mcp inspector for debugging and build mcp bundle (.mcpb) for distribution.
salesforce-mcp-lib CLAUDE.md
Instructions for Damecek/salesforce-mcp-lib, covering salesforce-mcp-lib development guidelines, active technologies, project structure, commands and code style.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).