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.
git clone --depth 1 https://github.com/zackiles/deno-kitWrote 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/rules/zackiles/deno-kit/with-banned-directories)<a href="https://agentmods.dev/rules/zackiles/deno-kit/with-banned-directories"><img src="https://agentmods.dev/badge/rules/zackiles/deno-kit/with-banned-directories.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 | $0.00000 | $0.00503 |
| Opus 5 | $0.00000 | $0.00251 |
| Sonnet 5 | $0.00000 | $0.00101 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
with-banned-directories 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 7d 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.
What it actually says
Rules for Banned Directories Jsonc Config
- These
.jsoncfiles contain strings that represent either a) an absolute path to a directory, OR b) a glob pattern used to match using the methodcheckPatternMatchin the filebanned-direcories.ts. - Glob patters MUST adhere to the specification provided by the method
globToRegExpin the library@std/path. - Before editing, adding to, or analyzing these
.jsoncfiles you MUST review the documentation forglobToRegExpto ensure you use the right syntax, options, and patterns provided by the method. - Before editing, adding to, or analyzing these
.jsoncfiles you MUST review the methodcheckPatternMatchin the filebanned-direcories.ts. - The objective of these
jsoncfiles and thebanned-direcories.tsfile is to be able to check an absolute path of a directory (or multiple paths) to see if it matches a list banned folders or patterns.
Pattern and Path Rules
- If its a path and not a pattern it should NOT be the path of a file. These strings are ONLY for matching folders or directories (including folders that start with a dot like
.config). - MUST be inside a platform and be platform specific
- MUST match against folder paths only. This code is not for matching files.
- MUST assume all first-level folders on a system are banned paths. This doesn't always apply to subfolders of the first-level UNLESS its a known system path
- MUST be as speciifc as possible for any second-level or deeper paths.
- MUST ensure all paths and patterns for a specific platform are unique. Redudant or overlapping paths or patterns must be removed. No patterns should be added to
banned_directories_custom.jsoncthat already exist inbanned_directories_default.jsonc - Patterns in
banned_directories_default.jsoncSHOULD whenever possible comprehensively target ALL platform specific directories, but WITHOUT matching against folders that typically would contain user application code such as second-level or deeper folders in appdata, user document folders, caches, user desktops, temp directories, and program file directories.
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.
- 7d ago First seen · 23 lines · 0 tokens per session scan A 8709052f3330
with-banned-directories is a cursor rule published in the GitHub repository zackiles/deno-kit (3 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 503 tokens. 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 cursor rules, from other repositories
orchestrator
Use when coordinating AI agents through a pipeline — orchestrator role instructions.
workspace
Multi-agent workspace context — loaded on every session.
engineering-agent-prompt-engineer
Use when writing, reviewing, or improving prompts for AI agents — agent role design and prompt engineering.
deno-lint
Deno lint error guidance.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.