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-protectgit 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-protect)<a href="https://agentmods.dev/skills/igorganapolsky/thumbgate/thumbgate-protect"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/thumbgate-protect/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-protect"><img src="https://agentmods.dev/badge/skills/igorganapolsky/thumbgate/thumbgate-protect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 19 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00165 | $0.00807 |
| Opus 5 | $0.00082 | $0.00404 |
| Sonnet 5 | $0.00033 | $0.00161 |
| Haiku 4.5 | $0.00016 | $0.00081 |
Grade A, and why
thumbgate-protect 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ThumbGate Protect
Inspect the protected-action posture for this project and, when the user explicitly approves, grant a scoped, expiring exception so a protected-file edit or publish can proceed under audit.
This skill wraps existing ThumbGate capability and adds no new logic — it reads governance state and records a time-boxed approval.
Workflow
- Read the posture with the
get_branch_governanceMCP tool: protected branches, release rules, and the protected-file globs in effect. - Report it plainly: what is protected, and what the agent is currently blocked from touching without approval.
- Only if the user explicitly asks to proceed, grant a scoped approval with the
approve_protected_actionMCP tool — keeppathGlobsto the smallest set the action needs andttlMsas short as the task requires (default ~1 hour). - Confirm the approval id, covered globs, and expiry. Approvals are temporary and audited; re-run for the next task.
The full approve_protected_action field contract (pathGlobs, reason, evidence, ttlMs) and
the audit model are in
references/governance-and-approvals.md.
Example
Input: "main is protected but I need to hotfix the changelog — approve it for this one edit"
Action:
get_branch_governance→ confirmmainis protected andCHANGELOG.mdis in a protected glob.approve_protected_action→pathGlobs: ["CHANGELOG.md"],reason: "hotfix changelog entry",evidence: "owner OK in thread",ttlMs: 900000(15 min).- Report: approval id + "CHANGELOG.md is editable for 15 minutes, then protection resumes."
Troubleshooting
get_branch_governancereturns nothing: no governance configured — say so; don't invent protected branches.- User wants a broad/standing exception: decline. Grant the smallest glob + shortest TTL, or suggest changing governance config deliberately instead.
- Approval granted but edit still blocked: the glob may not cover the file, or the TTL expired —
re-check
pathGlobs/expiry; if the MCP path is unreachable, run the thumbgate-doctor skill.
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.
- 7d ago First seen · 56 lines · 165 tokens per session scan A 42befdf70677
thumbgate-protect is a skill published in the GitHub repository IgorGanapolsky/ThumbGate (26 stars, last pushed today), licensed MIT. It adds 165 tokens to every session and 807 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 2026-09-03.
Other skills, from other repositories
checking-release-readiness
Records a ship, block, defer, or ship-with-risk decision that ties baseline, evidence status, residual risk, rollback, monitoring, and handoff together. Use when a packet, PR, release, dependency change, or agent-authority change approaches merge. Do not use early in development before evidence exists.
release-notes
Generate release notes from git history and CHANGELOG. Formats for GitHub Release, Slack, or email. Use before tagging a release.
github-release-briefing-skill
Create a source-linked briefing for the latest published GitHub release of a public repository. Use for engineering teams tracking a dependency release; do not use it to publish releases or change repositories.
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.
changelog-gen
A changelog generator that turns Git history into a version-by-version record of project changes. A changelog is a readable summary of new features, fixes, breaking changes, documentation, and other updates.
changelog-rules
Shared changelog conventions and formatting rules referenced by /create-changelog and /update-changelog. Not typically invoked directly.