Stats
Actions
Tags
From thumbgate
Shows ThumbGate's enforcement record: blocked vs warned actions, top gates, tokens saved, and the feedback-to-rejection pipeline. Use when asked about what ThumbGate blocked or enforcement stats.
How this skill is triggered — by the user, by Claude, or both
Slash command
/thumbgate:thumbgate-blockedThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Show the enforcement record: how many risky actions were blocked vs warned, which gates fire most,
Show the enforcement record: how many risky actions were blocked vs warned, which gates fire most, and the full feedback → check → rejection pipeline. Each block is a repeat mistake stopped before it spent tokens or did damage.
This skill wraps existing ThumbGate capability and adds no new logic — it reads the live enforcement counters.
gate_stats MCP tool: blocked count, warned count, and the top
gates by hits. (CLI fallback: npx thumbgate gate-stats.)enforcement_matrix MCP tool: feedback-pipeline stats, active
pre-action checks, and the rejection ledger with revival conditions.Field-by-field meanings (blocked vs warned, the rejection ledger, revival conditions) are in references/enforcement-fields.md.
Input: "is ThumbGate actually blocking anything? how many tokens did we save?"
Action: call gate_stats for the counters and enforcement_matrix for the pipeline, then:
14 blocks, 3 warns in the last 30 days. Top gate:
no-force-push-main(6 hits). Estimated ~9k tokens saved from re-runs avoided. 1 archived gate is one strike from revival.
gate_stats / enforcement_matrix unreachable: fall back to npx thumbgate gate-stats, then
run the thumbgate-doctor skill to confirm the MCP server and hooks are live.gate_stats (or the npx thumbgate gate-stats fallback), not estimates.enforcement_matrix, not just the headline block count.npx claudepluginhub igorganapolsky/thumbgateDisplays active ThumbGate prevention rules, reliability rules, and originating lessons. Shows what guardrails protect the project and why each exists. Uses MCP tools or CLI.
Explains ClawdStrike's 12 security guards, rulesets (permissive, default, strict), and policies for troubleshooting denials, understanding blocks, and configuring settings.
Assesses network security posture using Zscaler Analytics (Z-Insights). Analyzes Zero Trust Firewall action distribution, location-based activity, network service usage, and rule hit counts.