Borrowing it
Nothing to install: this file belongs to Surferdude-AF/CatalogMCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Surferdude-AF/CatalogMCP/master/CLAUDE.mdgit clone --depth 1 https://github.com/Surferdude-AF/CatalogMCPWrote 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/surferdude-af/catalogmcp/claude-md)<a href="https://agentmods.dev/instructions/surferdude-af/catalogmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/surferdude-af/catalogmcp/claude-md/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/instructions/surferdude-af/catalogmcp/claude-md"><img src="https://agentmods.dev/badge/instructions/surferdude-af/catalogmcp/claude-md.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 | $0.01742 | $0.01742 |
| Opus 5.5 | $0.00697 | $0.00697 |
| Sonnet 5.5 | $0.00348 | $0.00348 |
| Haiku 4.5 | $0.00174 | $0.00174 |
Grade A, and why
CatalogMCP 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 2mo 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CatalogMCP
What this is
A spike demonstrating that MCP (Model Context Protocol) is a good fit for maintaining a product catalog — an MCP server that lets an agent safely mutate a configuration surface (attributes, rules, product data), not just read one.
What we're trying to prove
Setting up a digital product catalog today is either slow (click through a UI for every attribute and rule) or expensive (script it against an API, which turns labor cost into engineering cost for every future change). The claim: an agent talking to a governed MCP tool surface can replace both — "describe what you want in plain language, agent executes it" — without sacrificing safety, because the governance layer (preview, audit, confirm) is what makes ungoverned write access tolerable in the first place.
The guardrails are not a bolt-on feature; they're the precondition for the pitch. A demo that shows mutation without also showing preview/audit/confirm hasn't proven anything.
Status
Implementation complete: domain model, full tool surface (schema + content +
governance), and the 6-step demo script are all built and tested (npm test), and
the demo has been run live against the real Anthropic API — see
demo/transcript.txt and the recorded video linked from the
README. What follows below is retained as the design record (decisions, scope, and
the explicit non-goals) rather than a live TODO list.
Decisions made during discovery:
- Terminal-only, no product UI. The "no UI" scope cut stands. But browsing the catalog is a first-class use case in its own right, not just a demo verification step — the belief is that agents are becoming a primary consumer of catalog data, so an agent reading the catalog back (not a human refreshing a browser) is itself part of the pitch.
- Schema AND content, not schema alone. Schema-only (defining attributes/rules) makes for a poor demo — the compelling story is content setup (loading actual products and their attribute values) validated against schema (required attributes, rules), which is what produces real dry-run previews and real back-and-forth.
- Destructive demo step: after initial setup, delete one product attribute — this is where the two-phase confirm / blast-radius disclosure gets shown (an attribute with live product data behind it is a much more meaningful "are you sure" than deleting an unused one).
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.
- 2mo ago First seen · 128 lines · 1,742 tokens per session scan A 463c93fe1bd8
CatalogMCP CLAUDE.md is an instructions file published in the GitHub repository Surferdude-AF/CatalogMCP (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,742 tokens to every session, about $0.0070 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.
CatalogMCP CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| CatalogMCP CLAUDE.mdSurferdude-AF/CatalogMCP | Instructions file | 0 | 3mo ago | MIT | A | 1,742 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |