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 rules/sayanarijit/cottage/deny-ctggit clone --depth 1 https://github.com/sayanarijit/cottageWrote 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/sayanarijit/cottage/deny-ctg)<a href="https://agentmods.dev/rules/sayanarijit/cottage/deny-ctg"><img src="https://agentmods.dev/badge/rules/sayanarijit/cottage/deny-ctg.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 | $0.00207 | $0.00207 |
| Opus 5 | $0.00103 | $0.00103 |
| Sonnet 5 | $0.00041 | $0.00041 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
deny-ctg 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 6d 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
Deny ctg Command Execution and Secret File Access
The ctg and ctgx CLI commands are strictly forbidden from being executed by Cursor's AI agent in this workspace.
- Never propose or run any
ctgorctgxcommands (e.g.,ctg clean,ctg decrypt,ctg run,ctg env, etc.). - Never invoke lifecycle hooks or background tasks that execute
ctgorctgx.
Cursor's AI agent must also never view, read, edit, create, or otherwise access secret files:
- Anything inside a
.cottage/directory. - Any file matching
*.cott.*(encrypted*.cott.ageblobs and redacted*.cott.tomlpreviews). - Any decrypted file
{file}that has a corresponding{file}.cott.ageencrypted counterpart on disk.
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.
- 6d ago First seen · 18 lines · 207 tokens per session scan A 88ef7dfb2543
deny-ctg is a cursor rule published in the GitHub repository sayanarijit/cottage (47 stars, last pushed 8d ago), licensed Apache-2.0. It adds 207 tokens to every session, about $0.0010 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.
Other cursor rules, from other repositories
n8n-workflow-format
Use n8n-as-code TypeScript workflow files and explicit sync discipline for n8n workflow work.
index
This repository manages a Kubernetes homelab using GitOps principles with Flux, Talos, and Taskfile-driven workflows.
home-assistant
Home Assistant integration conventions (entities, config, async, GitManager contract).
security
Security-critical rules — secrets.yaml, SSH keys, knownhosts, sanitized logging.
code-style
Python code style, practices, lint/format rules, and common snippets.
hacs
HACS integration requirements — manifest, hacs.json, validation, releases.