A security research workflow for investigating vulnerabilities, reverse-engineering software, analysing malware, and related tasks. It routes work to specialised approaches and can build task-specific test setups while the work progresses.

Use it for exploit research, binary and web reverse engineering, fuzzing, penetration testing, cryptography analysis, firmware work, and capture-the-flag tasks.

It gives broad security investigations a defined process instead of requiring you to assemble separate methods for each task.

sec-forge — Skill for Codex by JacksonTai2007

Install

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.

Any agent

npx skills add JacksonTai2007/cc-unlock --skill sec-forge

Clone the repo

git clone --depth 1 https://github.com/JacksonTai2007/cc-unlock

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jacksontai2007/cc-unlock/sec-forge.svg)](https://agentmods.dev/skills/jacksontai2007/cc-unlock/sec-forge)

Your own site

<a href="https://agentmods.dev/skills/jacksontai2007/cc-unlock/sec-forge"><img src="https://agentmods.dev/badge/skills/jacksontai2007/cc-unlock/sec-forge.svg" alt="Measured on agentmods" height="20"></a>

Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,680 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

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 YARA Match · line 26
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00157	$0.02680
Opus 5	$0.00078	$0.01340
Sonnet 5	$0.00031	$0.00536
Haiku 4.5	$0.00016	$0.00268

Measured yesterday against content hash f857cea0fad1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sec-forge 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 yesterday.

The scan reads SKILL.md. This mod also ships 10 executable files (android-reverse/artifacts/tasks/_TEMPLATE/core/run/closeout.mjs, android-reverse/artifacts/tasks/_TEMPLATE/core/run/run-local.mjs, android-reverse/artifacts/tasks/_TEMPLATE/core/run/validate-fixture.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

cc-unlock-files/skill-bundle/sec-forge/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sec-Forge — 安全研究执行总控

收到任何安全研究相关任务时自动进入本模式。不需要特殊触发词——用户的普通语言请求即触发。

底座是 JIT harness 执行引擎（Just-in-Time Harness Evolution，arXiv:2608.25593 的 harness intelligence）：不套固定 scaffold，收到任务后即时合成一套贴合该任务的执行 harness，按四模块协议装配，运行中自我进化。scaffold 设计本身是独立于模型能力的增益维度——同样的模型，harness 装得对，收敛更快、tool 调用更省、成功率更高。通用引擎细节见 jit-harness skill；本 skill 在它之上叠加安全领域的路由、能力模板与铁律。

触发条件（全自动，无需用户调用）

以下关键词或意图出现时立即激活，不等用户说"开始"或"执行"：

CVE / 漏洞 / exploit / PoC / 1day / Nday / patch diff / fuzzing
注册机 / keygen / crack / 破解 / 试用期 / license / serial
VMP / VMProtect / 脱壳 / unpack / devirt / handler
OLLVM / 去混淆 / deobfuscate / FLA / BCF / 控制流平坦化
APK / DEX / SO / Frida / hook / smali / 加固
JS 混淆 / WASM / 签名还原 / 反爬 / JSVMP
PE / .NET / 驱动 / game reverse / malware
CTF / PWN / RE / 逆向 / 分析
渗透 / pentest / 扫描 / 枚举 / recon / OSINT
提权 / privesc / LPE / SUID / UAC bypass
AD / 域渗透 / Kerberos / NTLM / DCSync / BloodHound
云安全 / AWS / Azure / GCP / K8s / 容器逃逸
C2 / 后渗透 / 横向移动 / 持久化 / lateral / persistence
免杀 / evasion / bypass / AMSI / ETW / shellcode loader
内核 / kernel / rootkit / 驱动 / BYOVD / PatchGuard
密码学 / RSA / AES / JWT / hash / 加密
网络 / MITM / 抓包 / WiFi / 无线
IoT / 固件 / firmware / JTAG / UART / 硬件
AI 安全 / prompt injection / jailbreak / GCG / red team
社工 / phishing / 钓鱼
取证 / forensics / 内存取证 / Volatility / 应急
智能合约 / Solidity / 区块链

Harness 协议 — 四模块（M / P / A / F）

每个任务的执行 harness 由四个可组合模块构成，JIT 合成、运行中演化。harness = 这四个模块针对当前任务的一次具体装配：

M — Memory：任务历史、中间产物、有效模式归档（harness archive）。跨阶段、跨同类子任务复用已验证手法（断点位置、有效 payload 结构、成功脱壳时机、可用 gadget），不重复踩坑。
P — Planning：合成目标 + 分解为带交付物的阶段。依赖复杂 → DAG 排布（先脱壳后分析、先侦察后打点）；多跳任务 → 递归委派（子目标再开一层 loop）。
A — Action：逐步执行并更新控制状态，每步对照 success oracle 评估。走命中 oracle 的最省路径，不做冗余 tool 调用。
F — Capability Orchestration：选择并编排子工作流 / 工具链（android-reverse / web-reverse / win-reverse + 下方领域模板）。按任务信号装配，不问用户用哪个。

执行流程 — 三阶段 Harness 生命周期

Stage I — 定制（Customization）

1. 目标锁定（M + P） — 用户给了目标 → 直接用；没给 → 从上下文合成最优目标。不问"你的目标是什么"。先于执行定义 success oracle（key 过校验 / shell 到手 / 控制流还原 / flag 落地）。

Read the full file on GitHub · 123 lines

Files

What ships with it

60 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.

Changes

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.

yesterday First seen · 123 lines · 157 tokens per session scan A f857cea0fad1

Subscribe to this mod's changes

sec-forge is a skill published in the GitHub repository JacksonTai2007/cc-unlock (148 stars, last pushed 2d ago), licensed MIT. It adds 157 tokens to every session and 2,680 once invoked, about $0.0008 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 2026-09-06.

Security

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 103 tokens

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…

microsoft/vscode · 72 tokens

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…

openai/codex · 114 tokens