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 agentmods add skills/yhy0/chying-agent/ctf-postmortemnpx skills add yhy0/CHYing-agent --skill ctf-postmortemgit 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/ctf-postmortem)<a href="https://agentmods.dev/skills/yhy0/chying-agent/ctf-postmortem"><img src="https://agentmods.dev/badge/skills/yhy0/chying-agent/ctf-postmortem.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.02121 |
| Opus 5 | $0.00027 | $0.01060 |
| Sonnet 5 | $0.00011 | $0.00424 |
| Haiku 4.5 | $0.00005 | $0.00212 |
Grade A, and why
ctf-postmortem 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 5d 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.
| `JS_BLIND` | JS 渲染内容不可见，curl 看不到真实页面 | Content-Length=0，browser 未启用 | How it starts
The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CTF 赛后复盘分析
对 CHYing Agent 在一次或多次 CTF 比赛中的表现进行系统性分析，找出失败规律，提出系统级（非题目级）优化建议。
数据来源
- challenge 工作目录：
agent-work/ctf/<Category>/<challenge_dir>/ - 关键文件：
文件 内容 progress.md主任务状态、攻击树、Dead Ends、当前阶段 findings.log所有 key findings，含 kind/status/evidence dumps/commands.log执行命令历史 dumps/checkpoints.logReflection 检查点与停滞诊断 result.json最终结果（若存在）
执行流程
第一步：收集所有 challenge 目录
agent-work/ctf/
├── Web/
│ └── <challenge_dir>/
├── PWN/
├── Crypto/
├── Misc/
├── Cloud/
├── reverse/
└── tencent_cloud/
用 Glob 工具扫描所有 */*/progress.md 文件，建立题目清单。
对每道题提取：
- 题目名：从目录名推断
- 类别：父目录名
- 是否解出：检查 progress.md 中是否出现
FLAG{或flag{字样，或 findings.log 中存在kind: flag条目 - 最终状态：从 progress.md 的 "Current Phase" 或最后的 Dead Ends 推断
第二步：统计解题率
输出如下统计表：
## 解题统计
总题数: N
已解出: M (M/N = XX%)
未解出: K
| 类别 | 总数 | 解出 | 解出率 |
|-------|------|------|--------|
| Web | X | X | XX% |
| PWN | X | X | XX% |
| Crypto| X | X | XX% |
| Misc | X | X | XX% |
| Cloud | X | X | XX% |
第三步：失败题目逐题诊断
对每道未解出的题目，读取其 progress.md 和 findings.log，提取：
- 停止原因（stop_reason）：timeout / consecutive_failures / blocked / max_turns
- 最后阶段（Current Phase）：到哪一步卡住了
- Dead Ends：列举所有已证实无效的方向
- 最后的 highest_anomaly：最有价值但未被充分利用的线索
- 工具使用模式：主要用了哪类工具（executor/browser/reverse/c2）
- 是否触发了 kb_search：findings.log 中是否有知识库搜索记录
- 是否使用了 browser：是否做过 JS 渲染验证
第四步：失败模式归类
将所有失败题目归入以下根因类别（一题可归多类）：
| 根因代码 | 含义 | 识别信号 |
|---|---|---|
TARGET_UNREACHABLE |
目标服务不可达 | 大量连接错误/超时，无任何有效响应 |
TOOL_GAP |
缺少合适工具或工具用法错误 | 反复 exec 失败，未尝试 browser/reverse |
KB_MISS |
未搜索知识库，错过已知漏洞/技术 | 存在版本号但无 kb_search，类型为 cloud/misc |
JS_BLIND |
JS 渲染内容不可见，curl 看不到真实页面 | Content-Length=0，browser 未启用 |
LOOP_SAME_VECTOR |
在同一攻击向量上反复尝试，未转换方向 | Dead Ends 全属同一类别，攻击树分支单一 |
PARTIAL_CHAIN |
有部分发现但未串联成完整攻击链 | findings.log 有多条 confirmed 但无 exploited |
TIMEOUT_TOO_EARLY |
时间到了但方向是对的，只是执行不够深入 | 最后阶段在正确方向上但 stop_reason=timeout |
RECON_SHALLOW |
侦察不足，缺少关键信息就开始攻击 | progress.md 缺少服务版本/路径/参数信息 |
REFLECT_MISSED |
Reflection 机制未触发或触发后未改变策略 | checkpoints.log 无记录，或记录后仍重复死路 |
SESSION_REPEAT |
多次 session 重复相同工具路径 | prior_knowledge 存在但策略未变 |
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.
- 5d ago First seen · 209 lines · 54 tokens per session scan A 338a50d760dc
ctf-postmortem is a skill published in the GitHub repository yhy0/CHYing-agent (554 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 2,121 once invoked, about $0.0003 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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…