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/grahamton/merchgent/claude-mdgit clone --depth 1 https://github.com/grahamton/merchGentWrote 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/grahamton/merchgent/claude-md)<a href="https://agentmods.dev/instructions/grahamton/merchgent/claude-md"><img src="https://agentmods.dev/badge/instructions/grahamton/merchgent/claude-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 5.1 | $0.03097 | $0.03097 |
| Opus 5 | $0.01548 | $0.01548 |
| Sonnet 5 | $0.00619 | $0.00619 |
| Haiku 4.5 | $0.00310 | $0.00310 |
Grade A, and why
merchGent CLAUDE.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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — merch-connector (merchGent)
What this project is
An MCP server that gives AI agents visual access to e-commerce storefronts for automated merchandising analysis. It bridges AI and real product pages through a stealth headless browser, a multi-provider AI abstraction layer, and a persona-based expert analysis system.
14 MCP tools: acquire, analyze_products, scrape_pdp, get_category_sample, interact_with_page, compare_storefronts, ask_page, merch_roundtable, site_memory, clear_session, get_logs, save_eval, list_evals, scrape_page (deprecated)
6 MCP prompts (persona instructions): floor-walker, auditor, auditor-b2b, scout, conversion-architect, merch-roundtable
MCP resources: per-domain site memories exposed at merch-memory://<domain> URIs
Transport: stdio JSON-RPC only (not HTTP). Designed to be launched by an MCP client, not run standalone.
Cowork Plugin Workspace
A separate Cowork workspace acts as the PM hub and product operations layer for this project. It lives at the user's selected folder (Merch-connector) and is managed by a separate Claude agent whose job is:
- Running live audits via the merch-connector MCP tools to verify your fixes work end-to-end
- Owning the merch-auditor plugin (plugin-source/) — all plugin code, command files, skill files, and PLUGIN-* bug fixes
- Managing the Notion project hub — bug tracker, roadmap, audit archive
- Triaging bugs between this repo (MCP) and the plugin
Bug triage rule: If a symptom is a tool returning wrong data or crashing → fix is here in C:\dev\merchGent. If the symptom is agent behavior, wrong output format, or file not saved → fix is in the Cowork plugin workspace.
Notion project hub: https://www.notion.so/329dee0d562d818a95d7fd5759f0add4 — Bug Tracker, Roadmap, and Audit Archive all live here. After shipping a fix, the Cowork agent verifies it and updates the relevant Notion rows.
After each release: Bump the version, update CHANGELOG.md, and the Cowork agent handles verification and Notion logging.
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 · 203 lines · 3,097 tokens per session scan A 47c0eaaa04a6
merchGent CLAUDE.md is an instructions file published in the GitHub repository grahamton/merchGent (0 stars, last pushed 4mo ago), licensed MIT. It adds 3,097 tokens to every session, about $0.0155 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 instructions, from other repositories
video-research-mcp CLAUDE.md
Instructions for Galbaz1/video-research-mcp, covering claude.md, memory source guard, what this is, commands and video-research-mcp (root).
video-research-mcp AGENTS.md
Instructions for Galbaz1/video-research-mcp, covering agents.md, scope, what this is, commands and code review trigger protocol.
bestprice-mcp GEMINI.md
Gemini CLI instructions for TheBestCo/bestprice-mcp: Use the BestPrice tools when a user wants to find or compare products sold in Greece or understand whether a current price is low.
mcp-server-woocommerce CLAUDE.md
Instructions for AmitGurbani/mcp-server-woocommerce, covering woocommerce mcp server, build & test, architecture, adding new tools and key patterns.
media-mcp CLAUDE.md
Claude Code instructions for lukaskellerstein/media-mcp, covering important, development workflow (code quality), before writing code, while writing code and after writing code.
ebay-mcp AGENTS.md
Instructions for YosefHayim/ebay-mcp, covering agents.md, what this is, instruction sources, validation commands and module map (src/).