What is thumbgate-guard?

A command that turns a recent agent mistake into a rule checked before similar actions run. A block gate is a prevention check that can stop a risky action.

Use it after an incorrect or harmful action to record what went wrong and create a rule that applies across supported coding-agent tools.

It reduces the chance of repeating a bad tool call or other mistake, such as an unsafe Git or database command.

How IgorGanapolsky/ThumbGate configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to IgorGanapolsky/ThumbGate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/IgorGanapolsky/ThumbGate/main/.claude/commands/thumbgate-guard.md

Clone the repo

git clone --depth 1 https://github.com/IgorGanapolsky/ThumbGate

Made for: Claude Code.

Or install thumbgate, the plugin that ships this one along with the rest of its 35 skills, 7 commands, 1 agent, 5 hooks, 2 MCP servers, 2 plugins.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/igorganapolsky/thumbgate/thumbgate-guard/github.svg)](https://agentmods.dev/commands/igorganapolsky/thumbgate/thumbgate-guard)

Your own site

<a href="https://agentmods.dev/commands/igorganapolsky/thumbgate/thumbgate-guard"><img src="https://agentmods.dev/badge/commands/igorganapolsky/thumbgate/thumbgate-guard/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/igorganapolsky/thumbgate/thumbgate-guard"><img src="https://agentmods.dev/badge/commands/igorganapolsky/thumbgate/thumbgate-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 479 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.00479
Opus 5	$0.00031	$0.00239
Sonnet 5	$0.00012	$0.00096
Haiku 4.5	$0.00006	$0.00048

Measured 9d ago against content hash 9b7254f4c764, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

thumbgate-guard 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 9d 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.

.claude/commands/thumbgate-guard.md · 37 lines

What it actually says

ThumbGate Guard

Capture the mistake the agent just made and promote it into a Pre-Action Check (a block gate) so the same tool-call shape is intercepted before it runs again — in this and every future session, across Claude Code, Cursor, Codex, Gemini, Amp, and Cline.

This command wraps existing ThumbGate capability. It adds no new logic — it routes to the real capture + force-promote path.

Steps

Identify the specific bad action from the recent conversation (e.g. git push --force origin main, DROP TABLE users, deploy without tests). State it in one sentence.
Record the signal with the capture_feedback MCP tool:
- signal: "down"
- context: one sentence describing what went wrong
- whatWentWrong: the concrete failure
- whatToChange: the prevention action
- tags: the domain (e.g. git, database, deploy)
- If the user only gave a vague signal, pass the recent turns through conversationWindow / chatHistory for history-aware distillation instead of refusing.
Promote it to an enforced block gate using the existing force-promote path:
```
npx thumbgate force-gate "<one-sentence context of the mistake>"
```
This prints the new gateId and the total active gate count.
Show the user the promoted rule and confirm it is now enforced as a PreToolUse block.

First rule of the project and want the guided walkthrough (capture → promote → watch it block once)? Run npx thumbgate quickstart instead.

Example

/thumbgate-guard the agent force-pushed to main and overwrote a teammate's commit

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.

9d ago First seen · 37 lines · 62 tokens per session scan A 9b7254f4c764

Subscribe to this mod's changes

thumbgate-guard is a command published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 479 once invoked, about $0.0003 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.

AI Safety Building agents Guardrails agent-reliability ai-agents developer-tools thompson-sampling

ThumbGate: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

ThumbGate Guard

Steps

Example

What this file has done since we first saw it

Other commands, from other repositories

ng-decide-authority

ng-folders

ng-context-pack

ng-new

ng-learn

ng-ship-review