ThumbgateSAFE
A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw
Overview
A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw
80a0afd96301OBSERVED · 2026-10-07Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
# ThumbGate — Pre-Action Gates for AI Coding Agents ## What it does ThumbGate adds deterministic pre-action gates to AI coding agents. Before any destructive operation executes, ThumbGate checks it against enforceable rules. ## Key features - **33 pre-action gates** — block destructive actions (force-push, mass delete, destructive SQL) before they execute - **Thumbs up/down feedback** — type "thumbs down" and the mistake becomes a prevention rule - **Budget enforcement** — action count + time limits prevent runaway sessions - **Self-protection** — agent cannot disable its own governance - **NIST/SOC2 compliance tags** — enterprise-ready gate rules ## Installation ``` npx thumbgate ``` ## Usage Start a Claude Code session with ThumbGate installed. When the agent does something wrong, type "thumbs down" — ThumbGate captures the mistake, distills a lesson, and creates a prevention rule that blocks the pattern from repeating.
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
Gates applied: no_behavioural_pass.
80a0afd96301full audit observations/trust-audit/skill/davepoon__thumbgate.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 80a0afd96301 | SAFE | B | 89 | first audit |
Questions
What does the Thumbgate skill do?
A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw
Is Thumbgate safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Thumbgate access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Thumbgate work with?
Its documentation mentions claude-code. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (80a0afd96301), read on 2026-10-07. The repository is watched, and a new audit runs when it changes — this is the first audit.