Agent skill

Cpython Runtime Introspection

by manyuegong33 in manyuegong33/r0crawl_skills

Inspect embedded or packaged CPython processes at runtime by tracing child processes, acquiring the GIL, injecting Python, replacing builtins.input, walking frame.fback, exporting frame code…

No licenceAuto-check passed

Install Cpython Runtime Introspection

skills CLI
$ npx skills add manyuegong33/r0crawl_skills --skill cpython-runtime-introspection -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install manyuegong33/r0crawl_skills cpython-runtime-introspection --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/manyuegong33/r0crawl_skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cpython-runtime-introspection .claude/skills/cpython-runtime-introspection && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cpython-runtime-introspection
GitHub stars
306
Token cost
~537 tokens
SKILL.md length
215 words
Files
4 (incl. scripts, references)
Skills in repo
9
Repo updated
First seen
Licence
None found

At a glance

Inspect embedded or packaged CPython processes at runtime by tracing child processes, acquiring the GIL, injecting Python, replacing builtins.input, walking frame.fback, exporting frame code…

  • Works in 4 steps: Handle one-file parent and child… → Record module bases and the exact Python… → Capture an input or output stack and… → …
  • Static extraction misses executed logic
  • SKILL.md covers Prove the process and runtime, Prefer semantic injection, Walk caller frames and Fallback boundaries, plus 1 more section
  • Runs Python scripts from its folder

What it does

Cpython Runtime Introspection is an agent skill from manyuegong33/r0crawl_skills. Inspect embedded or packaged CPython processes at runtime by tracing child processes, acquiring the GIL, injecting Python, replacing builtins.input, walking frame.fback, exporting frame code objects, locals, globals, and disassembly, and hooking PyEval or marshal boundaries. Use when static extraction misses executed logic or when Python behavior is visible only in memory.

Its SKILL.md is about 540 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/injection-boundaries.md` and `scripts/frame_probe.py`).

It works with Python. The repository describes itself as: r0crawlskills is a massive reverse-engineering skill arsenal for web, Android, iOS, Frida, native binaries, protocols, malware, firmware, and anti-analysis—built for beginners…

When your agent uses it

  • Static extraction misses executed logic
  • Python behavior is visible only in memory

Example prompts

  • “/cpython-runtime-introspection”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Handle one-file parent and child processes separately.
  2. Record module bases and the exact Python version.
  3. Capture an input or output stack and confirm it enters CPython.
  4. Match injector and target architecture.

What it can do on your machine

Read from SKILL.md and the folder at commit b9eb545. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cpython Runtime Introspection loads about 537 tokens when it runs, and up to ~772 if it reads all its reference files. Until then it costs about 102 tokens; SKILL.md has 215 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~102
When it runs · the whole SKILL.md, loaded when a task matches
~537
With references · SKILL.md plus every file in references/, read only if the agent opens them
~772

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 215 words (~537 tokens).

“Inject Python-level code instead of reverse engineering the evaluator first:”

— opening of SKILL.md by manyuegong33
name
cpython-runtime-introspection

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files (scripts, references) in skills/cpython-runtime-introspection of manyuegong33/r0crawl_skills.

  • SKILL.md
  • agents/openai.yaml
  • references/injection-boundaries.md
  • scripts/frame_probe.py

Open the folder on GitHubat commit b9eb545

Compare with similar skills

Cpython Runtime Introspection next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cpython Runtime Introspection compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cpython Runtime Introspection this skillmanyuegong33/r0crawl_skills306—~537Automated safety check: PassNone
MCP Server Builderanthropics/skills180k64 repos~2.3kAutomated safety check: PassApache-2.0
PDF Processinganthropics/skills180k48 repos~2kAutomated safety check: PassProprietary
NotebookLM Research AssistantPleasePrompto/notebooklm-skill7.8k14 repos~2.4kAutomated safety check: NotesMIT
Manim Video Productionbrowser-use/video-use28k6 repos~3kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 64 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • PDF Processing

    anthropics/skills

    Official

    Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.

    180k GitHub starsUsed in 48 repos~2k tokens
    Documents & OfficeAuto-check passed
  • NotebookLM Research Assistant

    PleasePrompto/notebooklm-skill

    Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.

    7.8k GitHub starsUsed in 14 repos~2.4k tokens
    Knowledge ManagementAuto-check: notes
  • Manim Video Production

    browser-use/video-use

    Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.

    28k GitHub starsUsed in 6 repos~3k tokens
    Media & CreativeAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • PPT Master

    hugohe3/ppt-master

    Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.

    58k GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed

More from manyuegong33/r0crawl_skills

All 9 skills in this repo
  • Ctf Key Recovery

    manyuegong33/r0crawl_skills

    Reconstruct CTF key, serial, and flag verifiers using known plaintext, repeating XOR, encoded constants, bytecode replacement, hash constraints, SMT, and bounded brute force.

    306 GitHub stars~434 tokensUpdated 18 days ago
    Auto-check passed
  • Kctf ML Backdoor Linear

    manyuegong33/r0crawl_skills

    Solve KCTF model backdoors and small linear/ReLU crackmes from raw weights.

    306 GitHub stars~443 tokensUpdated 18 days ago
    Auto-check passed
  • Python Frozen App Reversing

    manyuegong33/r0crawl_skills

    Recover logic from PyInstaller, cxFreeze, py2exe, Nuitka, and other frozen Python applications, including modified bootloaders, decoy entry scripts, patched frozen standard-library modules, embedded…

    306 GitHub stars~666 tokensUpdated 18 days ago
    Auto-check passed
  • R0crawl Skills

    manyuegong33/r0crawl_skills

    面向新手的全谱系逆向工程路由器,覆盖 Web/JavaScript、Android/iOS、Frida、脱壳、反分析、原生二进制、协议、固件、恶意软件、游戏、云 API、CTF、可复现一致性测试。用于逆向、起步、脱壳、反编译、hook、Frida、绕过检测、APK/SO/DEX/JS/PCAP/WASM/PE/ELF/Mach-O 分析、签名还原,或从样本到验证结果的完整调查。

    306 GitHub stars~1.2k tokensUpdated 18 days ago
    Auto-check passed
  • Kctf Algebraic Crackme Chain

    manyuegong33/r0crawl_skills

    Solve KCTF Windows crackmes with layered codecs, 32/64-bit shell thunks, .data-resident code, and final algebraic or polynomial checks.

    306 GitHub stars~467 tokensUpdated 18 days ago
    Auto-check passed
  • Kctf Windows Smc Chain

    manyuegong33/r0crawl_skills

    KCTF 2026 第八题“亥子合辰·塔影迷楼”两级 SMC、反调试、Feistel 与 GF(2^127-39) 多项式求根的可复用解题流程。

    306 GitHub stars~467 tokensUpdated 18 days ago
    Auto-check passed

Works with

Questions about Cpython Runtime Introspection

What does Cpython Runtime Introspection do?

Inspect embedded or packaged CPython processes at runtime by tracing child processes, acquiring the GIL, injecting Python, replacing builtins.input, walking frame.fback, exporting frame code…. Cpython Runtime Introspection is an agent skill from manyuegong33/r0crawl_skills.fback, exporting frame code objects, locals, globals, and disassembly, and hooking PyEval or marshal boundaries.

When should I use Cpython Runtime Introspection?

Cpython Runtime Introspection fits situations like: static extraction misses executed logic; Python behavior is visible only in memory.

How do I install Cpython Runtime Introspection in Claude Code?

Run `npx skills add manyuegong33/r0crawl_skills --skill cpython-runtime-introspection -a claude-code`. Or copy the skill folder (skills/cpython-runtime-introspection in manyuegong33/r0crawl_skills) into .claude/skills/cpython-runtime-introspection in your project. Claude Code loads it when a task matches its description.

How do I install Cpython Runtime Introspection in Codex?

Run `npx skills add manyuegong33/r0crawl_skills --skill cpython-runtime-introspection -a codex`. Or copy the skill folder (skills/cpython-runtime-introspection in manyuegong33/r0crawl_skills) into .agents/skills/cpython-runtime-introspection in your project. Codex loads it when a task matches its description.

Can I use Cpython Runtime Introspection in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add manyuegong33/r0crawl_skills --skill cpython-runtime-introspection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cpython-runtime-introspection, .gemini/skills/cpython-runtime-introspection, .github/skills/cpython-runtime-introspection and .opencode/skills/cpython-runtime-introspection in your project.

What does Cpython Runtime Introspection need to run?

Going by SKILL.md and its folder, Cpython Runtime Introspection needs Python for the scripts in its folder. Our summary lists: Python 3.

Does Cpython Runtime Introspection access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cpython Runtime Introspection safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Cpython Runtime Introspection use?

No licence was found for Cpython Runtime Introspection or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Cpython Runtime Introspection use?

About 537 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 235 tokens, read only when the agent opens those files.

What are the alternatives to Cpython Runtime Introspection?

Skills that share tags, products or a category with Cpython Runtime Introspection: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cpython Runtime Introspection?

manyuegong33 (a GitHub user) maintains it in manyuegong33/r0crawl_skills, which has 306 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 20, 2026.

Source: manyuegong33/r0crawl_skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.