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/IgorGanapolsky/ThumbGateWrote 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/igorganapolsky/thumbgate/thumbgate-pretool-gate)<a href="https://agentmods.dev/rules/igorganapolsky/thumbgate/thumbgate-pretool-gate"><img src="https://agentmods.dev/badge/rules/igorganapolsky/thumbgate/thumbgate-pretool-gate/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/rules/igorganapolsky/thumbgate/thumbgate-pretool-gate"><img src="https://agentmods.dev/badge/rules/igorganapolsky/thumbgate/thumbgate-pretool-gate.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 | $0.00000 | $0.00167 |
| Opus 5.5 | $0.00000 | $0.00067 |
| Sonnet 5.5 | $0.00000 | $0.00033 |
| Haiku 4.5 | $0.00000 | $0.00017 |
Grade A, and why
thumbgate-pretool-gate 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 15d 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
ThumbGate pre-tool gate
Before a shell or network command runs:
- If the command would print, post, or copy a secret, do not run it.
- If this repository already recorded the same failure, do not repeat it.
- A warning is not permission to continue a secret leak.
For automated pre-action inspection:
npx thumbgate gate-check
Pass the tool name and tool input JSON on stdin. A deny result stops the action.
Product page: https://thumbgate.ai/pro
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.
- 15d ago First seen · 24 lines · 0 tokens per session scan A 42ec62b392f8
thumbgate-pretool-gate is a cursor rule published in the GitHub repository IgorGanapolsky/ThumbGate (29 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 167 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 2026-10-01.
Other cursor rules, from other repositories
selectools-testing
Testing conventions and patterns for selectools.
selectools-agent-core
Rules for working with the agent core loop in selectools.
selectools-development
Selectools development conventions, testing requirements, and release process.
selectools-docs
Documentation standards for selectools docs and MkDocs site.
selectools-providers
Rules for working with LLM provider adapters in selectools.
agentguard
AgentGuard local-first safety.