cloakbox-guardrails.example

cloakbox-guardrails.example is a cursor rule for Cursor from mbufkin/cloakbox. It costs 354 tokens per session, scanned A, original, MIT.

A set of mandatory workspace rules for handling sensitive Cloakbox data, including restrictions on real records and identity mappings.

In plain words
What is it for?
Guiding agents that analyze Cloakbox data while keeping real identities, vault files, and decoding materials off-limits.
Why use it?
It prevents an agent from opening protected files, reversing anonymous tokens, or using anything except the approved read-only sanitized data source.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Install

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.

agentmods
npx agentmods add rules/mbufkin/cloakbox/cloakbox-guardrails.example
Clone the repo
git clone --depth 1 https://github.com/mbufkin/cloakbox

Made for: Cursor.

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 cloakbox-guardrails.example

README.md
[![agentmods](https://agentmods.dev/badge/rules/mbufkin/cloakbox/cloakbox-guardrails.example.svg)](https://agentmods.dev/rules/mbufkin/cloakbox/cloakbox-guardrails.example)
Your own site
<a href="https://agentmods.dev/rules/mbufkin/cloakbox/cloakbox-guardrails.example"><img src="https://agentmods.dev/badge/rules/mbufkin/cloakbox/cloakbox-guardrails.example.svg" alt="Measured on agentmods" height="20"></a>
Per session 354 This file is loaded in full into every session.
When invoked 354 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00354 $0.00354
Opus 5 $0.00177 $0.00177
Sonnet 5 $0.00071 $0.00071
Haiku 4.5 $0.00035 $0.00035

Measured 5d ago against content hash eecb5de5766b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cloakbox-guardrails.example 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.

gateway/cloakbox-guardrails.example.mdc · 31 lines

What it actually says

Cloakbox guardrails (sensitive data)

Copy this into .cursor/rules/ in any workspace where an agent can reach this project. These rules are non-negotiable.

Never touch the vault or the decode side

  • NEVER open, read, ATTACH, query, copy, or print the vault (vault.duckdb or your real warehouse) or any file containing real data.
  • NEVER read the mapping (mapping.duckdb), the salt (salt.txt), or anything under ~/.cloakbox_vault/ (the decode side).
  • NEVER attempt re-identification. Turning tokens back into people is a manual, human-only step via decode/decode.py; an agent must never run it or read its inputs/outputs.

Only the sanitized Cloakbox is allowed

  • The ONLY data source you may query is the cloakbox MCP server (read-only), which points at data/cloakbox.duckdb. It contains tokens (e.g. SUB_…, TCH_…), never real names.
  • Do not write to it, and do not open the .duckdb files directly as files.

When asked to analyze data

  • Use the cloakbox MCP tools. Report results using the tokens as-is — never speculate about who a token "really is."
  • If a task seems to require real identities, STOP and tell the user it must be done manually with the decoder; do not work around this.
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. 5d ago First seen · 31 lines · 354 tokens per session scan A eecb5de5766b

Subscribe to this mod's changes

cloakbox-guardrails.example is a cursor rule published in the GitHub repository mbufkin/cloakbox (0 stars, last pushed 1mo ago), licensed MIT. It adds 354 tokens to every session, about $0.0018 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.