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 yhy0/CHYing-agent --skill stagnation-recoverygit clone --depth 1 https://github.com/yhy0/CHYing-agentWrote 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/yhy0/chying-agent/stagnation-recovery)<a href="https://agentmods.dev/skills/yhy0/chying-agent/stagnation-recovery"><img src="https://agentmods.dev/badge/skills/yhy0/chying-agent/stagnation-recovery/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/yhy0/chying-agent/stagnation-recovery"><img src="https://agentmods.dev/badge/skills/yhy0/chying-agent/stagnation-recovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Tool Misuse · line 16 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00071 | $0.02266 |
| Opus 5 | $0.00036 | $0.01133 |
| Sonnet 5 | $0.00014 | $0.00453 |
| Haiku 4.5 | $0.00007 | $0.00227 |
Grade A, and why
stagnation-recovery scanned grade A with 1 finding 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 12d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **换方向不是换参数**：curl 加了 `-k` 还是 403？这不叫换方向。从 client_credentials 换到 device_code flow 才叫换方向。 How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stagnation Recovery - Security Operations
Core Principle
停下来比错误方向的加速更有价值。 当你连续尝试同类操作无果时，问题不是执行力不够，而是方向错了。
Iron Rules
- 穷尽验证再放弃：没有读过报错全文、没有搜索过文档、没有检查过前置条件的，不算尝试过。
- 先查后问：你有 wss_exec/docker_exec/WebSearch/Read 等工具，在判定"不可行"之前，必须用工具验证。
- 换方向不是换参数：curl 加了
-k还是 403？这不叫换方向。从 client_credentials 换到 device_code flow 才叫换方向。
Step 1: Diagnose - 识别你的卡壳模式
在采取任何行动之前，先判断你属于哪种模式：
| 模式 | 信号 | 根因 |
|---|---|---|
| A: 原地打转 | 反复执行同一工具、只改参数/flag | 方向错误，需要换攻击面 |
| B: 环境约束 | Permission denied, 工具缺失, 网络不通 | 硬限制，需要绕道或换工具链 |
| C: 信息不足 | 盲目尝试、猜测 API 端点/参数 | 缺少侦察，需要回退到信息收集 |
| D: 攻击链断裂 | 有多个发现但无法串联 | 需要停下来组合攻击链 |
| E: 工具使用错误 | 命令语法错、参数编码错、curl 格式错 | 需要读文档或用脚本替代手工命令 |
Step 2: Recover - 按模式执行恢复
Mode A: 原地打转 -> 换攻击面
强制动作：
- 列出你已尝试的所有方向（不是参数变体，是方向）
- 从下面的攻击树中选择一个未尝试过的方向
- 每个新方向最多尝试 3 次，无果则换下一个
Web 攻击树：
目标 Web 应用
├── 认证绕过: 默认凭据 / SQL注入 / JWT伪造 / OAuth滥用 / Session固定
├── 注入攻击: SQLi / XSS / SSTI / SSRF / XXE / Command Injection / LDAP Injection
├── 逻辑漏洞: IDOR / 竞态条件 / 业务逻辑绕过 / 价格篡改 / 权限越权
├── 文件操作: 上传绕过 / 路径遍历 / LFI/RFI / 反序列化
├── 前端攻击: DOM XSS / Prototype Pollution / WebSocket劫持 / PostMessage滥用
└── 信息泄露: .git泄露 / 备份文件 / 错误页面 / API文档 / 源码泄露
提权攻击树：
初始访问
├── Linux: SUID/SGID / sudo滥用 / cron/定时任务 / capabilities / 内核漏洞 / Docker逃逸
├── Windows: 服务权限 / 注册表 / AlwaysInstallElevated / Token模拟 / SeImpersonate
├── Cloud: IMDS/metadata / IAM提权 / 角色链 / SSRF到云凭据 / 存储桶误配置
└── K8s: ServiceAccount / RBAC滥用 / etcd / kubelet API / 挂载逃逸
云安全攻击树：
Cloud Target
├── Azure: OAuth App滥用 / Managed Identity / device_code flow / Admin Consent攻击
│ / Dynamic Group注入 / PRT滥用 / Conditional Access绕过
├── AWS: IMDS v1/v2 / IAM提权链 / Lambda环境变量 / S3 ACL / STS AssumeRole
└── GCP: SA密钥 / metadata server / Workload Identity / Org Policy绕过
Mode B: 环境约束 -> 绕道
强制动作：
- 明确列出约束（具体错误信息）
- 对每个约束检查：是真约束还是可绕过的？
- Permission denied -> 能否换用户/换路径/换工具？
- 工具缺失 -> 能否用替代工具？(例: 没有 nmap 用 /dev/tcp 探测)
- 网络不通 -> 能否通过已有代理/隧道？
- 确认是硬约束后，立即放弃这个方向，不要再尝试任何变体
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.
- 12d ago First seen · 177 lines · 71 tokens per session scan A 96b9bdf6d0fd
stagnation-recovery is a skill published in the GitHub repository yhy0/CHYing-agent (566 stars, last pushed 4mo ago), licensed MIT. It adds 71 tokens to every session and 2,266 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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…