re
General reverse-engineering and debugging workflow for authorized software.
Skill by bvts
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/bvts-re
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/re
What's inside
- Skill name
re- Description
- General reverse-engineering and debugging workflow for authorized software. Use with /re <program or path> for the default IDA Pro workflow, /re x64dbg [program or PID] for x64dbg, or /re gdb [program or PID] and /re gdp [program or PID] for GDB. Can scan active processes, resolve files, fingerprint targets, launch the selected tool, persist sessions, generate evidence-backed analysis tasks, and resume follow-up queries without losing the target context.
- License
- MIT
- Instructions
- 510 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- body: 510 lines (spec recommends under 500)
Files (1)
- SKILL.md
SKILL.md (first lines)
# /re — REVERSE ENGINEERING
## Purpose
`/re` is a universal reverse-engineering entry point. It is not limited to crackmes or `.exe` files. It can work with executables, DLLs/shared libraries, binaries, firmware images, dumps, and other files supported by the selected analysis tool and installed tooling.
The default backend is **IDA Pro**. Two alternate debugger backends are built in:
- `x64dbg` for Windows user-mode debugging.
- `gdb` for targets supported by the installed GDB build.
`gdp` is accepted as an alias for `gdb` because the command form is part of Max Prompter's public command set.
Use `/re` only for software the user owns, has permission to inspect, or is explicitly authorized to analyze. The workflow should favor static analysis first, avoid executing unknown files merely because they were named, and clearly distinguish observations from assumptions.
## Command syntax
### Default IDA Pro
```text
/re <program name>
/re <absolute or relative path>
```
Examples:
```text
/re myapp.exe
/re mylibrary.dll
/re .\samples\program.exe
/re C:\work\samples\firmware.bin
```
### Explicit debugger/backend
```text
/re ida <program or path>
/re x64dbg <program or path>
/re gdb <program or path>
/re gdp <program or path>
```
Examples:
```text
/re x64dbg myapp.exe
/re gdb ./server
/re gdp ./server
/re x64dbg C:\work\sample.dll
```
### Active-process mode
When no target is supplied, or when the named target is not found as a file, scan currently running processes and show matching candidates.
```text
/re
/re x64dbg
/re gdb
/re gdp
```
A user may also explicitly target a PID when invoking the helper scripts:
```text
python scripts/re/resolve_target.py --pid 1234
python scripts/re/launch_debugger.py --tool x64dbg --pid 1234
```
Do not silently select one process when multiple candidates match. Show PID, process name, path when accessible, architecture when known, and access limitations, then let the user choose.
### Resume the active session
```text
/re
```
If `.max-prompter/re/RE_SESSION.json` exists and the user did not provide a new backend or target, treat the session as the current RE context.
## What `/re` does
The high-level workflow is:
```text
/re request
↓
parse backend + target intent
↓
resolve local file OR scan active processes
↓
fingerprint target when a file is available
↓
resolve selected debugger
↓
launch/attach where supported
↓
persist RE session
↓
ask for / process the natural-language analysis query
↓
produce evidence-backed findings
```
Every stage must have an explicit success/failure state. Never say a debugger was launched when the launcher process immediately exited.
## Backend rules
### IDA Pro — default
Prefer IDA Pro for static analysis, disassembly, cross-references, graph views, type reconstruction, and decompilation when Hex-Rays is installed.
For a local file:
```text
ida64.exe target.exe
```
or the 32-bit equivalent when appropriate. Current Hex-Rays documentation supports graphical launch with `ida input-file` / `ida64 input-file`; batch automation can use `-A` together with `-S` scripts. citeturn825372search21From bvts/max-the-prompter, MIT.
More from bvts/max-the-prompter
- 0.579score
build
bvts
Implements an approved plan in coherent, verifiable slices while preserving existing architecture and behavior.
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
council
bvts
Pressure-tests meaningful decisions through a five-advisor Council using Contrarian, First Principles, Expansionist, Outsider, and Executor perspectives, peer…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
audit
bvts
Performs a broad project audit across correctness, architecture, UX, accessibility, security, performance, runtime behavior, and maintainability.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
cleanmemory
bvts
Reset Max Prompter's project-context memory boundary so unrelated projects and prior-project notes do not influence the current workspace.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ship
bvts
Prepares and verifies a project for production release, including tests, build, deployment configuration, security, observability, rollback, documentation…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
design
bvts
Designs or redesigns user interfaces with a coherent visual system, appropriate component sources, motion, responsive behavior, and rendered-browser…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
skillinstall
bvts
Install a third-party or local Agent Skill into the current workspace under a clean skills/<skill-name>/ directory, optionally discovering the repository from…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
spec
bvts
Creates a complete, implementation-ready project or feature specification before code.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
review
bvts
Runs a structured pre-merge review of changes for correctness, architecture, readability, maintainability, security, performance, tests, and accidental scope…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
prompt
bvts
Generates an execution-ready implementation prompt from a user request or project context using the Max Prompter workflow.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
constraints
bvts
Establishes and enforces a measurable project quality bar, normally persisted as CONSTRAINTS.md.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
plan
bvts
Converts a project specification into dependency-ordered, atomic, verifiable implementation tasks.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 23, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/bvts/max-the-prompter
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from bvts
- 0.579score
build
bvts
Implements an approved plan in coherent, verifiable slices while preserving existing architecture and behavior.
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
council
bvts
Pressure-tests meaningful decisions through a five-advisor Council using Contrarian, First Principles, Expansionist, Outsider, and Executor perspectives, peer…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
cleanmemory
bvts
Reset Max Prompter's project-context memory boundary so unrelated projects and prior-project notes do not influence the current workspace.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
audit
bvts
Performs a broad project audit across correctness, architecture, UX, accessibility, security, performance, runtime behavior, and maintainability.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
ship
bvts
Prepares and verifies a project for production release, including tests, build, deployment configuration, security, observability, rollback, documentation…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
design
bvts
Designs or redesigns user interfaces with a coherent visual system, appropriate component sources, motion, responsive behavior, and rendered-browser…
SkillBFreshness: B★ 1Claude Code +9
Cite this page
re skill. Agent Mart. https://agentmart.dev/skills/bvts-re (last updated 2026-10-24)