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.
npx skills add IgorGanapolsky/ThumbGate --skill thumbgate-blockedgit 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/skills/igorganapolsky/thumbgate/thumbgate-blocked)<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/thumbgate-blocked"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/thumbgate-blocked/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.
<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/thumbgate-blocked"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/thumbgate-blocked.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 3 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 18 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 43 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 48 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00162 | $0.00740 |
| Opus 5 | $0.00081 | $0.00370 |
| Sonnet 5 | $0.00032 | $0.00148 |
| Haiku 4.5 | $0.00016 | $0.00074 |
Grade A, and why
thumbgate-blocked 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ThumbGate Blocked
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.
Workflow
- Headline numbers with the
gate_statsMCP tool: blocked count, warned count, and the top gates by hits. (CLI fallback:npx thumbgate gate-stats.) - Full picture with the
enforcement_matrixMCP tool: feedback-pipeline stats, active pre-action checks, and the rejection ledger with revival conditions. - Summarize for the user: total blocks, most-triggered gates, and anything in the rejection ledger close to revival.
- If counts are all zero, say enforcement is wired but hasn't fired yet and point to the thumbgate-guard skill to promote a rule.
Field-by-field meanings (blocked vs warned, the rejection ledger, revival conditions) are in references/enforcement-fields.md.
Example
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.
Troubleshooting
- All zeros but rules exist: enforcement is wired but no gated action has been attempted yet — this is normal early on.
- All zeros and rules also empty: nothing has been promoted — use the thumbgate-guard skill.
gate_stats/enforcement_matrixunreachable: fall back tonpx thumbgate gate-stats, then run the thumbgate-doctor skill to confirm the MCP server and hooks are live.
Quality checklist (self-verify before delivering)
- I pulled real counters via
gate_stats(or thenpx thumbgate gate-statsfallback), not estimates. - I included the full pipeline via
enforcement_matrix, not just the headline block count. - I framed each block as a prevented repeat mistake (tokens/damage avoided), with real numbers.
- On all-zero, I explained why (wired-but-unfired vs nothing-promoted) instead of implying failure.
- I added no new logic — only read existing enforcement counters.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 53 lines · 162 tokens per session scan A 0ee7050a13c2
thumbgate-blocked is a skill published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed today), licensed MIT. It adds 162 tokens to every session and 740 once invoked, about $0.0008 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.
Other skills, from other repositories
agentguard
Runtime guardrails for AI coding agents. Stop loops, budget overruns, retry storms, and timeouts before they burn money. Zero dependencies, local-first, MIT licensed.
crm-pipeline-playbook
How to answer pipeline, renewal, and account-health questions using the CRM tools.
closing-stale-packets
Brings an abandoned or half-filled change packet to an honest terminal state by completing it, closing it with a recorded rationale, or deleting it. Use when ng status flags a scaffold or invalid packet, a long session left a draft behind, or work was abandoned mid-packet. Do not use for an actively in-progress…
deciding-who-decides
Decides who holds authority for a change — the agent at the edge or a human gate — by matching decision rights to reversibility, evidence, and consequence, and names the escalation trigger. Use when an agent could act on something irreversible, trust-bearing, or thinly evidenced. Do not use for trivial reversible…
staying-on-mission
Tests the current work against a written, lasting mission anchor and forces one choice, re-anchor, escalate, or stop. Use when an agent keeps finishing tasks but the work drifts from the goal, scope creeps, the same action repeats in a loop, or standards slip one small step at a time. Do not use for a tiny edit with…
verifying-final-artifacts
Verifies the delivered artifact a consumer actually receives (a figure, chart, PDF, SVG, screenshot, compiled build, or deployed response) by regenerating it fresh and directly observing the output, not the source that produces it, and ends in one honest verdict. Use when the deliverable is a produced artifact and…