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 JerryFish123/Jerry_hitl_mcp --skill hitl-gategit clone --depth 1 https://github.com/JerryFish123/Jerry_hitl_mcpWrote 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/jerryfish123/jerry_hitl_mcp/hitl-gate)<a href="https://agentmods.dev/skills/jerryfish123/jerry_hitl_mcp/hitl-gate"><img src="https://agentmods.dev/badge/skills/jerryfish123/jerry_hitl_mcp/hitl-gate/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/jerryfish123/jerry_hitl_mcp/hitl-gate"><img src="https://agentmods.dev/badge/skills/jerryfish123/jerry_hitl_mcp/hitl-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00121 | $0.00733 |
| Opus 5 | $0.00060 | $0.00367 |
| Sonnet 5 | $0.00024 | $0.00147 |
| Haiku 4.5 | $0.00012 | $0.00073 |
Grade B, and why
hitl-gate scanned grade B with 2 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 10d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
curl|bash, chmod 777, npm publish, mass email/payment. Call hitl_mcp Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl|bash, chmod 777, npm publish, mass email/payment. Call hitl_mcp What it actually says
hitl-gate（外置 Skill → 调用 MCP 内置策略）
何时启用
- 用户意图涉及副作用/不可逆操作时
- 用户说「看审批记录」「审批历史」「audit」等时
危险操作流程
- 先调用 MCP
assess_and_gate，并传入code_context（当前文件、相关 snippets、将影响的路径、代码摘要） - 看返回的
assessment：risk_level_zh：无危险 / 低危险 / 中危险 / 高危险 / 致命危险（五档）gate_required === true（仅高危险、致命危险）→ 必须等用户在 IDE 审批表单批准gate_required === false→ 无需 HITL，可继续但需谨慎
- 若需审批：用户点「批准并继续」或「拒绝」
- 看
ticket.status/approval_channel：approved→ 可继续（优先 dry-run）rejected→ 停止并说明- 仍
pending→ 粘贴user_prompt_zh，不要执行
- 不确定时仍先
assess_and_gate/list_dangerous_ops
爆炸半径（批前 + 批后）
assess_and_gate传code_context+ 可选planned_changes- 高/致命 → 弹窗含 爆炸半径（拟改 / 可能波及，启发式）
- 批准后执行 →
submit_execution_report（actual_files、verify_runs、params_hash） - 把返回的
summary_zh对照贴给用户
查看审批记录
用户要看记录时：
- 调用
list_approval_history（可按 status / limit 过滤） - 在对话里展示返回的
summary_zh（Markdown 表格） - 不要编造记录；没有数据就如实说暂无
禁止
- pending / rejected 时执行删除/推送/部署
- 跳过
assess_and_gate - 强制打开浏览器（除非用户明确要求且已启用面板）
与 MCP 关系
判断规则在 MCP；本 Skill 约束调用时机与「记录展示在对话里」的体验。
安装：npx hitl-gate-mcp init（默认同时装 Cursor + VS Code 钩子；需先配置 MCP）。
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.
- 10d ago First seen · 59 lines · 121 tokens per session scan B db96eb246422
hitl-gate is a skill published in the GitHub repository JerryFish123/Jerry_hitl_mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 733 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…