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 FirenzeClaw/kimi-session-orchestrator --skill xmindgit clone --depth 1 https://github.com/FirenzeClaw/kimi-session-orchestratorWrote 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/firenzeclaw/kimi-session-orchestrator/xmind)<a href="https://agentmods.dev/skills/firenzeclaw/kimi-session-orchestrator/xmind"><img src="https://agentmods.dev/badge/skills/firenzeclaw/kimi-session-orchestrator/xmind/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/firenzeclaw/kimi-session-orchestrator/xmind"><img src="https://agentmods.dev/badge/skills/firenzeclaw/kimi-session-orchestrator/xmind.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 | $0.00053 | $0.02399 |
| Opus 5 | $0.00026 | $0.01200 |
| Sonnet 5 | $0.00011 | $0.00480 |
| Haiku 4.5 | $0.00005 | $0.00240 |
Grade A, and why
xmind 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 8d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XMIND — 困境梳理 + 新视角方案生成
概述
遇到困境时自动收集当前问题点与项目必读文档,打包交给独立子 Agent,该 Agent 从头理解项目全局后使用 zoom-out 退后一步,以宏观视角给出全新方案。方案被拒绝时,将拒绝原因注入交接包进入下一轮迭代,最多 3 轮。
核心原则: 困境中的 Agent 有思维惯性——它熟悉自己的解决方案,难以自我推翻。独立的新 Agent 不受此惯性约束。
何时使用
| 症状 | 示例 |
|---|---|
| 同一 bug 修了 2 次仍未解决 | "又错了,再查一次……" |
| 发现架构级矛盾但不知如何取舍 | "这样改会破坏A,那样改会破坏B" |
| 陷入细节无法判断优先级 | "现在该先做哪个?" |
| 需要全新视角审视方案 | "有没有完全不同的思路?" |
不适用: 单步操作(改一行配置)、已明确方案只需执行。
交接包 Schema(CRITICAL —— 单一事实来源)
子 Agent 工作流和交接包格式均以此 Schema 为准。必填字段缺失时拒绝传递,提示补全。
HandoffPackage {
// 必填段
project: {
name: string // required
stack: string // required, 语言/框架/工具链
cwd: string // required, 工作目录
}
docs: [{
path: string // required
summary: string // required, 一句话摘要
}] // required, min 1
problems: [{
title: string // required
symptom: string // required, 可观测现象
attempts: [{
solution: string // required, 已尝试的方案
why_failed: string // required, 失败原因
}]
files: string[] // 涉及的文件/模块列表
}] // required, min 1
constraints: {
no_modify: string[] // 不能修改的模块
perf_floor: string // 性能底线阈值
compat: string // 兼容性要求
} // required
// 迭代段(由反馈闭环自动填充)
iteration: number // 当前迭代轮次, 0=首次
rejections: [{
round: number
proposal_title: string
reason: string // 用户拒绝原因
}]
// 子Agent工作流指令(从 SUBAGENT-WORKFLOW 注入)
subagent_workflow: string // required
}
// 验证规则
必填字段缺失 → 拒绝传递 → 提示 "HandoffPackage 验证失败: 缺少 [字段名]"
docs 长度 < 1 → 拒绝传递 → 提示 "至少提供 1 个必读文档"
problems 长度 < 1 → 拒绝传递 → 提示 "至少描述 1 个问题"
子 Agent 工作流指令(subagent_workflow 字段内容,从 SUBAGENT-WORKFLOW.md 注入):
请按以下步骤工作:
1. 通读 docs 中列出的所有必读文档,理解项目架构、约束和规范
2. 逐个分析 problems,理解为何已尝试的方案失败
3. 调用 zoom-out:绘制模块关系图,用项目术语描述全局架构
- 若 zoom-out skill 不可用:手动绘制模块依赖图 + 用 constraints 中的术语描述全局
4. 基于宏观理解,提出 1-3 个新方案
5. 每个方案标注:
- 可行性(高/中/低) + 理由
- 风险
- 与已尝试方案的本质区别(不能只是旧方案的微小变体)
6. 考虑 rejections 中的拒绝原因(如有),避免重复被拒绝的路径
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.
- 8d ago First seen · 190 lines · 53 tokens per session scan A 11e8d062d422
xmind is a skill published in the GitHub repository FirenzeClaw/kimi-session-orchestrator (0 stars, last pushed 13d ago), licensed MIT. It adds 53 tokens to every session and 2,399 once invoked, about $0.0003 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
output-dev-skill-file
Create .md skill files for Output framework's lazy-loaded instruction system. Use when adding skills to prompts, configuring skill loading, or debugging skill resolution.
output-debug-workflow
Debug Output SDK workflow issues. Use when user reports a workflow failing, erroring, hanging, producing wrong results, or asks to debug, troubleshoot, or investigate a workflow execution.
output-workflow-trace
Analyze Output SDK workflow execution traces. Use when debugging a specific workflow, examining step failures, analyzing input/output data, understanding execution flow, or when you have a workflow ID to investigate.
output-services-check
Verify Output SDK development services are running. Use when debugging workflows, starting development, encountering connection errors, services may be down, or when you see "ECONNREFUSED" or timeout errors.
scientific-debugging
A method for debugging software by observing the problem, forming possible explanations, running small experiments, and then fixing and checking the result.
diagnose-from-context
Diagnose a problem from the explicitly materialized context view.