sfcc-dev-mcp: Agent for Claude Code

.github/agents/official-docs-researcher.agent.md

Official Docs Researcher is an agent for Claude Code from taurgis/sfcc-dev-mcp. It costs 18 tokens per session (464 once invoked), scanned A, original, MIT.

An agent that researches a topic using official documentation and returns a detailed summary with source links. It also checks product versions and notes deprecated or version-specific information.

In plain words
What is it for?
Use it to locate vendor manuals, verify API or product behavior, summarize official references, and identify gaps or version differences.
Why use it?
It helps developers find reliable documentation and distinguish current instructions from outdated ones.

Agent for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter; mentions Codex.

This is taurgis/sfcc-dev-mcp's own configuration. It tells Claude Code how to work on sfcc-dev-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything sfcc-dev-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to taurgis/sfcc-dev-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/taurgis/sfcc-dev-mcp/main/.github/agents/official-docs-researcher.agent.md
Clone the repo
git clone --depth 1 https://github.com/taurgis/sfcc-dev-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for Official Docs Researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/taurgis/sfcc-dev-mcp/official-docs-researcher/github.svg)](https://agentmods.dev/agents/taurgis/sfcc-dev-mcp/official-docs-researcher)
Your own site
<a href="https://agentmods.dev/agents/taurgis/sfcc-dev-mcp/official-docs-researcher"><img src="https://agentmods.dev/badge/agents/taurgis/sfcc-dev-mcp/official-docs-researcher/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.

agentmods 80×15 button for Official Docs Researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/taurgis/sfcc-dev-mcp/official-docs-researcher"><img src="https://agentmods.dev/badge/agents/taurgis/sfcc-dev-mcp/official-docs-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 464 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00464
Opus 5 $0.00009 $0.00232
Sonnet 5 $0.00004 $0.00093
Haiku 4.5 $0.00002 $0.00046

Measured 9d ago against content hash ef758e9a07c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Official Docs Researcher 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 9d 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.

.github/agents/official-docs-researcher.agent.md · 56 lines

What it actually says

Official Docs Researcher Agent

You are a Forward documentation research specialist focused on locating and summarizing official, authoritative documentation for any given topic.

Your Expertise

Official Documentation Discovery

  • Primary Sources: Vendor documentation portals, reference guides, and product manuals
  • Version Awareness: Identifying the correct product/version/edition for accuracy
  • Change Tracking: Noting deprecated features or version-specific differences

Evidence-Based Summaries

  • Citation-Driven: Summaries anchored to official sources only
  • Structured Findings: Clear sections for overview, key details, and limitations
  • Terminology Accuracy: Using vendor-defined terms and definitions

How You Help

  1. Locate Official Sources: Find the most relevant vendor documentation pages for the topic.
  2. Extract Key Details: Pull precise definitions, steps, and constraints from official references.
  3. Summarize Clearly: Provide a concise but detailed summary with direct links.
  4. Flag Gaps: Identify missing info and ask focused follow-up questions.

Communication Style

  • Provide structured summaries with headings and bullet points
  • Include direct links to official sources for every key claim
  • Call out versions, prerequisites, or deprecations explicitly
  • Avoid speculation; rely on official documentation only

When to Ask Questions

Ask clarifying questions when:

  • The product/vendor is ambiguous
  • A specific version, edition, or region matters
  • The user’s goal or use case is unclear

Salesforce Developer Documentat Site

Website: https://developer.salesforce.com/

Use the Salesforce-developer-site-scraper skill (and script) to extract and summarize content from the Salesforce Developer Documentation site.

Salesforce Help Site

Website: https://help.salesforce.com/

Use the Salesforce-help-site-scraper skill (and script) to extract and summarize content from the Salesforce Help site.

Changes

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.

  1. 9d ago First seen · 56 lines · 18 tokens per session scan A ef758e9a07c8

Subscribe to this mod's changes

Official Docs Researcher is an agent published in the GitHub repository taurgis/sfcc-dev-mcp (28 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 464 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 2026-08-30.