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 builtingit 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/builtin)<a href="https://agentmods.dev/skills/jerryfish123/jerry_hitl_mcp/builtin"><img src="https://agentmods.dev/badge/skills/jerryfish123/jerry_hitl_mcp/builtin/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/builtin"><img src="https://agentmods.dev/badge/skills/jerryfish123/jerry_hitl_mcp/builtin.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 | $0.00000 | $0.00608 |
| Opus 5 | $0.00000 | $0.00304 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade D, and why
builtin scanned grade D with 3 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 9d 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.
| chmod_dangerous | high | chmod 777 | Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| shell_pipe_curl | critical | curl \| bash | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| shell_pipe_curl | critical | curl \| bash | What it actually says
hitl_mcp 内置策略（Built-in Skill / Policy）
本文件随 MCP 仓库分发，不是 Cursor 外置 Skill。
运行时由assess_and_gate/list_dangerous_ops执行同等规则。
目标
在调用真正有副作用的操作前：
- 用内置危险操作表 +
code_context评估意图（五档风险） - 若 高危险 / 致命危险 → 自动开审批单（含爆炸半径案卷）
- 优先通过 IDE MCP elicitation 批准/拒绝；可选网页面板（
HITL_ENABLE_PANEL=1） - 批准后执行 → 调用
submit_execution_report产出计划 vs 实际对照 - 拒绝/过期必须停止
危险操作枚举（摘要）
| id | 风险 | 典型意图 |
|---|---|---|
| delete_files | high | 删文件、rm、动 .env |
| git_force_push | critical | force push、reset --hard |
| git_destructive | high | clean -fd、删分支 |
| db_destructive | critical | DROP/TRUNCATE |
| prod_deploy | critical | 生产发布、kubectl apply |
| secrets_exfil | critical | 泄露密钥、提交 .env |
| shell_pipe_curl | critical | curl | bash |
| chmod_dangerous | high | chmod 777 |
| package_publish | high | npm publish |
| mass_side_effect | high | 群发、批量支付 |
完整匹配规则见源码 src/policy.ts。
Agent 应如何用 MCP
- 副作用操作前调
assess_and_gate（intent+code_context+ 可选planned_changes） - 看
gate_required：仅 高/致命 弹审批；案卷在blast_radius/ 弹窗【爆炸半径】分区 - 仅
ticket.status === "approved"可执行 - 执行后调
submit_execution_report（actual_files、verify_runs、params_hash） - 用户要看记录 →
list_approval_history，展示summary_zh表格（含案卷/对照列） - 可用
list_dangerous_ops查看内置表
外置钩子（hitl-gate-mcp init）负责提醒 Agent 必须走上述流程：
Cursor → Rule/Skill；VS Code / Copilot → .github/instructions/。
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.
- 9d ago First seen · 44 lines · 0 tokens per session scan D 75e2033fcfc3
builtin is a skill published in the GitHub repository JerryFish123/Jerry_hitl_mcp (0 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 608 tokens. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, 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…