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 kings0527/agent-skills --skill re-metastrategy-cognitivegit clone --depth 1 https://github.com/kings0527/agent-skillsWrote 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/kings0527/agent-skills/re-metastrategy-cognitive)<a href="https://agentmods.dev/skills/kings0527/agent-skills/re-metastrategy-cognitive"><img src="https://agentmods.dev/badge/skills/kings0527/agent-skills/re-metastrategy-cognitive/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/kings0527/agent-skills/re-metastrategy-cognitive"><img src="https://agentmods.dev/badge/skills/kings0527/agent-skills/re-metastrategy-cognitive.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 | $0.00136 | $0.05606 |
| Opus 5 | $0.00068 | $0.02803 |
| Sonnet 5 | $0.00027 | $0.01121 |
| Haiku 4.5 | $0.00014 | $0.00561 |
Grade A, and why
re-metastrategy-cognitive 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 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.
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 — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RE-MetaStrategy-Cognitive
逆向工程元认知激活引擎。只负责怎么想，不负责用什么工具。
目标不是替代 IDA / Ghidra / Frida / Unicorn / angr，而是避免 Agent 在逆向过程中掉进以下陷阱：
- 沉迷低层细节，却无法复述语义
- 被控制流叙事、伪复杂度、符号命名误导
- 连续使用同一分析范式，注意力长期停滞
- 过早单押某个解释，失去候选分支管理能力
- 不区分任务类型，拿同一套收敛标准处理所有逆向问题
- 无法识别哪些信息是信号，哪些只是噪声
First Principle
程序执行 = CPU 指令集 + OS ABI + 内存模型 + 外部 I/O 约束下的确定性或近确定性状态机。
混淆 / 保护 / 对抗 = 状态冗余、观察障碍、成本转移，不改变底层不变量。
逆向 = 从可观测状态变化、数据依赖、边界穿越与副作用反推出目标的机制语义与业务语义。
注意力 = 稀缺资源。高质量逆向不是“看到更多”，而是过滤更多无效信息后，看清真正关键变化。
Role
本 Skill 是逆向分析的元认知调度器。它管理：
- 注意力预算（attention budget）
- 噪声抑制（noise suppression）
- 任务模式（task mode）
- 分析对象分型（object typing）
- 假设池与区分证据（hypothesis pool + discriminators）
- 心智模型轮换（mental model rotation）
- 抽象层级跃迁（abstraction ascent）
- 前瞻观察（outlook / forward attention）
- 收敛与暂停条件（termination / parking）
本 Skill 不规定任何具体命令、脚本、工具调用。
1. Task Mode Router
开始分析前，先判断当前任务属于哪一类。不同任务使用不同收敛标准。
Task Modes
| Mode | 目标 | 典型问题 |
|---|---|---|
classify |
判断样本/模块是什么 | 这段代码在干嘛？ |
localize |
找关键入口/关键路径 | 核心校验逻辑在哪？ |
explain |
解释机制如何工作 | 这个 VM / 壳 / 反调试怎么运作？ |
recover |
还原协议/结构/算法/数据模型 | 这个格式、加密、状态机怎么恢复？ |
bypass |
找最脆弱假设与最小破坏面 | 最容易绕过的点在哪？ |
compare |
对比两个样本/版本差异 | 新旧版本差了什么？ |
validate |
验证某个具体假设是否成立 | 这真的是 license 校验吗？ |
attribute |
归因现象到组件/路径 | 崩溃/上报/检测是谁触发的？ |
Router Rule
先输出一个明确的 task_mode。如果无法判断，先在 classify 与 validate 中二选一，禁止无模式漂移。
2. Dual Abstraction Ladder
不要把抽象层级压成一条线。逆向至少存在两条抽象轴：
- Mechanism Abstraction，机制语义
- Business Abstraction，业务语义
Mechanism Ladder
| Level | 表示形态 | 示例 |
|---|---|---|
| M0 | 字节/原始内存 | 48 89 5C 24 08 |
| M1 | 指令/基本块 | mov [rsp+8], rbx |
| M2 | 函数/地址壳名 | sub_401000 |
| M3 | 类型/结构恢复 | func(char* buf, int len) |
| M4 | 机制语义 | vm_dispatcher, xor_decoder, anti_debug_gate |
Business Ladder
| Level | 表示形态 | 示例 |
|---|---|---|
| B0 | 无业务语义 | unknown |
| B1 | 粗粒度领域语义 | auth, telemetry, config, persistence |
| B2 | 业务动作语义 | verify_license, parse_packet, sync_profile |
| B3 | 属性-值-实体语义 | verify_license(key: String, hwid: HWID) -> ValidationResult |
What ships with it
1 file 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.
- 12d ago First seen · 594 lines · 136 tokens per session scan A cd6f10f32929
re-metastrategy-cognitive is a skill published in the GitHub repository kings0527/agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 136 tokens to every session and 5,606 once invoked, about $0.0007 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.