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 Ichliebedich1/mimo-bridge-mcp --skill use-mimo-bridge-mcpgit clone --depth 1 https://github.com/Ichliebedich1/mimo-bridge-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/ichliebedich1/mimo-bridge-mcp/use-mimo-bridge-mcp)<a href="https://agentmods.dev/skills/ichliebedich1/mimo-bridge-mcp/use-mimo-bridge-mcp"><img src="https://agentmods.dev/badge/skills/ichliebedich1/mimo-bridge-mcp/use-mimo-bridge-mcp/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/ichliebedich1/mimo-bridge-mcp/use-mimo-bridge-mcp"><img src="https://agentmods.dev/badge/skills/ichliebedich1/mimo-bridge-mcp/use-mimo-bridge-mcp.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 | $0.00073 | $0.01808 |
| Opus 5 | $0.00036 | $0.00904 |
| Sonnet 5 | $0.00015 | $0.00362 |
| Haiku 4.5 | $0.00007 | $0.00181 |
Grade A, and why
use-mimo-bridge-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
使用 MiMo Bridge MCP
核心规则
把 MiMo Bridge 当作有边界的委派系统:Codex 负责规划和审查,MiMo 或 Reasonix 只在配置的安全边界内执行,最终合并、丢弃或继续任务的决定由 Codex 或用户作出。
默认从有界的 Review Package 开始,只有风险证据不足时,才读取相关 diff、文件或日志尾部。不要为了方便读取整个仓库、完整日志或完整 diff。
先选择正确的客户端
优先使用不依赖源码 node_modules 的发行客户端:
& "$env:LOCALAPPDATA\MiMoBridgeApp\MiMo Bridge Client.cmd" health
便携包中使用当前目录的 MiMo Bridge Client.cmd。只有明确在源码仓库开发时,才使用:
node .\scripts\mimo-bridge-client.mjs health
下文的 $Client 表示已经确认存在的发行客户端路径:
$Client = "$env:LOCALAPPDATA\MiMoBridgeApp\MiMo Bridge Client.cmd"
不要因为源码目录缺少 node_modules 或 @modelcontextprotocol/sdk 就判定客户端不可用;发行客户端只使用内置 Node 模块和 REST。
首次检查
- 运行
& $Client health。 - 确认
daemon.status="ok"、daemon.identity="mimo-bridge-local-daemon/v1"和mcp.status="ready"。 - 检查
config.reload_required;为true时不要直接开始新任务。 - 如果 Codex 中缺少 MCP 工具,确认 MCP 地址为
http://127.0.0.1:3210/mcp。配置传输变化通常需要重启 Codex或新开会话。
委派流程
- 对含中文路径、空格、引号或多行目标的请求,创建 UTF-8 JSON 文件;不要用内联 PowerShell/Node 拼接 JSON。
- 为每次逻辑任务生成唯一且稳定的
idempotency_key,超时或断线重试时复用同一个键和完全相同的参数;不同逻辑任务不得共用该键。 - MiMo 使用
start;Reasonix 使用agent-start --agent-id reasonix-tui。 - 新任务应在 5 秒内返回
task_id、request_id、status="preparing_worktree"、queue_state和idempotent_replay。这只是成功持久化占位任务,不代表 Agent 已运行。 - 启动阶段正常顺序是
preparing_worktree -> starting_agent -> running;路径冲突或容量限制可能让任务保持排队状态。 - 启动后只做一次有界等待,不要高频轮询
get_task。 - 从
detail_level="review"的 Review Package 开始审查,再按风险最小化升级读取范围。 - 只有 Codex 或用户验收后才执行 finish/merge/discard/delete。
同一幂等键和同一请求会返回原任务,并设置 idempotent_replay=true;同一键配不同参数会返回 IDEMPOTENCY_CONFLICT。遇到超时不得换新键创建“替代任务”。
max_rounds 的有效范围是 1-10,MCP Schema 上限固定为 10。
命令选择
MiMo 任务:
& $Client start --json .\task.json --idempotency-key "replace-with-one-stable-uuid"
& $Client wait --task-id task_xxx --timeout-seconds 1800
& $Client review --task-id task_xxx --detail-level review --max-chars 8000
& $Client recover --limit 5 --max-chars 8000
Reasonix 或通用 Agent 任务:
What ships with it
2 files 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 · 122 lines · 73 tokens per session scan A 4e7523b58550
use-mimo-bridge-mcp is a skill published in the GitHub repository Ichliebedich1/mimo-bridge-mcp (3 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,808 once invoked, about $0.0004 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 2026-08-31.
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…