thumbgate-guard

thumbgate-guard is a skill for Claude Code from IgorGanapolsky/ThumbGate. It costs 201 tokens per session (930 once invoked), scanned A, original, MIT.

A tool that turns a recent agent mistake into a rule that blocks the same risky tool action before it runs. The rule applies across supported coding-agent environments and future sessions.

In plain words
What is it for?
It is for capturing an agent failure, creating a prevention rule from it, and confirming that the rule is active as a pre-action block.
Why use it?
It prevents a known mistake from happening again instead of merely recording that it happened. This is useful for actions such as force-pushing protected branches or changing data destructively.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: mentions Claude Code; mentions Codex; built for cline.

Part of the thumbgate plugin — 37 skills, 7 commands, 1 agent, 5 hooks, 2 MCP servers, 2 plugins shipped together

Good fit It is for capturing an agent failure, creating a prevention rule from it, and confirming that the rule is active as a pre-action block.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/igorganapolsky/thumbgate/thumbgate-guard
Install

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.

Any agent
npx skills add IgorGanapolsky/ThumbGate --skill thumbgate-guard
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 37 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.

agentmods badge for thumbgate-guard

README.md
[![agentmods](https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/thumbgate-guard/github.svg)](https://agentmods.dev/skills/igorganapolsky/thumbgate/thumbgate-guard)
Your own site
<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/thumbgate-guard"><img src="https://agentmods.dev/badge/skills/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.

agentmods 80×15 button for thumbgate-guard

Your own site · 80×15
<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/thumbgate-guard"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/thumbgate-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 201 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 930 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to high

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 →

  • high Tool Misuse · line 18
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • 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 24
    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 31
    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 40
    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 55
    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]
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00201 $0.00930
Opus 5 $0.00101 $0.00465
Sonnet 5 $0.00040 $0.00186
Haiku 4.5 $0.00020 $0.00093

Measured 7d ago against content hash a1f835f59450, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 7d 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.

skills/thumbgate-guard/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ThumbGate Guard

Escalate the agent's most recent mistake into an enforced ThumbGate prevention rule — a PreToolUse block gate that intercepts the same bad tool-call shape before it runs again, in this session and every future one (Claude Code, Cursor, Codex, Gemini, Amp, Cline).

This skill wraps existing ThumbGate capability and adds no new logic — it routes to the real capture_feedback + force-promote path.

Workflow

  1. Name the mistake. From the recent conversation, state the specific bad action in one sentence (e.g. git push --force origin main, DROP TABLE users, deploy without tests).
  2. Capture it with the capture_feedback MCP tool: signal: "down", context, whatWentWrong, whatToChange, tags. If the user only gave a vague signal, pass the recent turns as conversationWindow / chatHistory for history-aware distillation instead of refusing.
  3. Promote it to an enforced gate:
    npx thumbgate force-gate "<one-sentence context of the mistake>"
    
    This prints the new gateId and the active gate count.
  4. Confirm enforcement. Show the user the promoted rule and state that it is now a PreToolUse block — not just a logged note.

Full capture_feedback field contract, force-gate flags, and the guided first-rule walkthrough (npx thumbgate quickstart) are in references/capture-and-promote.md.

Example

Input: "the agent force-pushed to main and overwrote a teammate's commit — never again"

Action:

  1. capture_feedbacksignal: down, context: "agent force-pushed to main, overwrote a teammate's commit", whatWentWrong: "destructive force-push to a shared branch", whatToChange: "block force-push to main", tags: "git,force-push".
  2. npx thumbgate force-gate "force-push to main overwrote a teammate's commit".
  3. Report: the real gateId + "force-push to main is now blocked as a PreToolUse check."

Troubleshooting

  • "Vague feedback rejected": add whatWentWrong + whatToChange, or pass conversationWindow so it can distill from history.
  • force-gate prints nothing or errors: ThumbGate may not be wired — run the thumbgate-doctor skill.
  • Rule didn't fire next time: confirm it is active with the thumbgate-rules skill and that hooks are installed (thumbgate-doctor).

Read the full file on GitHub · 58 lines

Files

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.

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.

  1. 7d ago First seen · 58 lines · 201 tokens per session scan A a1f835f59450

Subscribe to this mod's changes

thumbgate-guard is a skill published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed yesterday), licensed MIT. It adds 201 tokens to every session and 930 once invoked, about $0.0010 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 2026-09-03.

Related

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.

bmdhodl/agent47 · 38 tokens

crm-pipeline-playbook

How to answer pipeline, renewal, and account-health questions using the CRM tools.

schmitech/orbit · 22 tokens

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…

FlyFission/nuclear-grade-context-engineering · 80 tokens

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…

FlyFission/nuclear-grade-context-engineering · 98 tokens

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…

FlyFission/nuclear-grade-context-engineering · 84 tokens

vetting-outside-code-and-models

Checks dependencies, models, APIs, SaaS tools, generated files, and vendor claims against how you will actually use them, the proof you have, the gaps, and the release impact. Use when any of these affect evidence, permissions, data, releases, or public trust. Do not use for an internal cleanup with no outside…

FlyFission/nuclear-grade-context-engineering · 85 tokens