thumbgate-f444fc — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited thumbgate-f444fc (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Stop your AI from making the same mistake twice.
Repeated AI mistakes cost real money in tokens. Thumbs-down once — ThumbGate blocks that exact pattern on every future call, across every agent you use.
thumbgatenpx thumbgate initBootstraps .thumbgate/ and wires PreToolUse hooks into your agent. Works out-of-the-box with Claude Code, Cursor, Codex, Gemini CLI, Amp, OpenCode, and any MCP-compatible agent.
thumbgate capture "Never run --force push to main" # create a rule
thumbgate gates list # see active gates
thumbgate feedback down "agent ignored file paths" # capture a thumbs-down
thumbgate lessons search "DROP TABLE" # recall prior lessons
thumbgate dashboard # open the local dashboardPreToolUse hooks physically block matching tool calls before the model is invoked. Zero tokens spent on the repeat.DROP TABLE, git push --force, etc.) blocked at the tool-call layer, not the prompt layer.Dashboard + live tokens-saved counter: https://thumbgate-production.up.railway.app/dashboard
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.