agentleFS
Sign inStart free
AlyhnteAlyhnte/conduit/SKILL.md

conduit

Skill1 starsChanged 43 days agoMITView on GitHub

Drive radare2, x64dbg, cdb, and Frida from an MCP client. Use for disassembly, control-flow graphs, cross-references, strings, and live debugging.

  • Installs packages

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. err0rgod/skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

Create a free account to mount
Files
SKILL.md

Conduit

Conduit is an MCP server, not a subcommand CLI. Start it, then call tools.

Install

npm install -g github:Alyhnte/conduit

Node.js 20 or newer and npm. Static tools need radare2 on PATH. Rendering a control-flow graph needs Graphviz (dot on PATH). An x64dbg session needs portable x64dbg plus Python 3.10+ with iced_x86 (python -m pip install iced_x86); 64-bit Python on PATH or PYTHON_HOME_X64. 32-bit Python is only for x86 targets. cdb is a separate Windows debugger. The Frida engine is pulled by the npm install. Python is not required to install Conduit itself.

Run

conduit
conduit --transport http --port 3847

Cursor, Claude Desktop, Cline, and OpenCode configs are in configs/.

Tool order

  1. health — expect status: ok and name: conduit.
  2. session_open with engine set to radare2, x64dbg, cdb, or frida.
  3. Static session: open_target with mode: "static", then disassemble, get_cfg, xrefs, strings, dump.
  4. Live session: debug_open or debug_attach, then debug_breakpoint, debug_continue, debug_registers, debug_callstack.
  5. Live memory, code, threads, plugins, and snapshots need confirm: true.
  6. explain reads an assembly window. A live session still needs confirm: true.
  7. close_target and session_close when finished.

A tool the engine does not implement returns capability_unsupported. Frida hardware execute breakpoints use four slots; a fifth returns no_breakpoint_slot.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free