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/pre-action-gates)<a href="https://agentmods.dev/rules/igorganapolsky/thumbgate/pre-action-gates"><img src="https://agentmods.dev/badge/rules/igorganapolsky/thumbgate/pre-action-gates.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 | $0.00236 | $0.00236 |
| Opus 5 | $0.00118 | $0.00118 |
| Sonnet 5 | $0.00047 | $0.00047 |
| Haiku 4.5 | $0.00024 | $0.00024 |
Grade C, and why
pre-action-gates scanned grade C with 1 finding 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
description: Before risky tool calls (git push, rm -rf, npm publish, deploy), check prevention rules via the thumbgate MCP server. If a rule matches, STOP and explain why. What it actually says
Pre-Action Gates
Before executing any of these risky actions, query the prevention_rules MCP tool to check for matching prevention rules:
git push(especially force push)rm -rfor recursive file deletionnpm publishdeploycommands (any deployment target)- Database migration commands
- Secret or credential changes
Enforcement flow
- Extract the command or action about to be executed.
- Call
prevention_ruleswith the action description to check for matching rules. - If a rule matches:
- STOP the action immediately.
- Display the matched rule's description and corrective action.
- Ask the user to confirm before proceeding.
- If no rules match, proceed normally.
After a blocked action
- Suggest the corrective action from the matched prevention rule.
- Offer to capture feedback if the block was incorrect (false positive).
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.
- 8d ago First seen · 31 lines · 236 tokens per session scan C 08b4db2509f8
pre-action-gates is a cursor rule published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed today), licensed MIT. It adds 236 tokens to every session, about $0.0012 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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
agentguard
AgentGuard local-first safety.
agent-guardrails
A set of repository rules that guide an AI coding agent before, during, and after code changes.
agent-guardrails-enforce
Before telling the user a task is done, you MUST.
selectools-agent-core
Rules for working with the agent core loop in selectools.
selectools-providers
Rules for working with LLM provider adapters in selectools.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.