Skip to content

ByteLandTechnology/headless-ghidra / headless-ghidra-intake

headless-ghidra-intake

Verified

P0 phase skill for Headless Ghidra intake. Use when a target binary/archive needs identity confirmation, workspace initialization, Ghidra discovery, binary inspection, or analysis scope setup before any Ghidra analysis runs.

FileKindSize
README.ja-JP.mdmarkdown4.9 KB
README.mdmarkdown4.4 KB
README.zh-CN.mdmarkdown4.1 KB
SKILL.mdskill md2.0 KB
examples/intake-speckit-handoff.mdmarkdown2.9 KB
planning-brief.mdmarkdown4.9 KB
---
name: "headless-ghidra-intake"
description: "P0 phase skill for Headless Ghidra intake. Use when a target binary/archive needs identity confirmation, workspace initialization, Ghidra discovery, binary inspection, or analysis scope setup before any Ghidra analysis runs."
phase: "P0"
---

# Headless Ghidra Intake — P0

P0 prepares a target for the rest of the workflow. It is responsible for
turning an input binary or archive path into a valid `ghidra-agent-cli`
workspace target and recording the initial analysis scope.

## Required ghidra-agent-cli Commands

- `ghidra-agent-cli workspace init`
- `ghidra-agent-cli ghidra discover`
- `ghidra-agent-cli inspect binary`
- `ghidra-agent-cli scope show`
- `ghidra-agent-cli scope set`
- `ghidra-agent-cli scope add-entry`
- `ghidra-agent-cli scope remove-entry`
- `ghidra-agent-cli gate check --phase P0`

Archive normalization and any target-specific bootstrap scripts may still
run as backend details until the CLI exposes them directly.

## Inputs

- User-provided binary or archive path
- Workspace root
- Local environment needed for Ghidra discovery

## Outputs

- `targets/<target-id>/ghidra-projects/`
- `artifacts/<target-id>/pipeline-state.yaml`
- `artifacts/<target-id>/scope.yaml`
- Optional phase-owned intake records under `artifacts/<target-id>/intake/`

## Exit Expectations

- Target workspace exists and is addressable through `--target <id>`.
- `pipeline-state.yaml` records the selected binary path.
- `scope.yaml` records the selected functions, addresses, symbols, or explicit
  whole-target scope.
- Ghidra discovery and binary inspection have been run and reviewed.

## Constraints

- Do not run actual Ghidra analysis in this phase.
- Do not write baseline, evidence, decompilation, or verification outputs.
- Do not bypass `ghidra-agent-cli workspace init`, `ghidra discover`, or
  `inspect binary` for supported steps.
- Do not create or run a new Ghidra script if the CLI lacks a capability; pause
  and ask the user first.

## Next Step

- P0 gate passes → `headless-ghidra-baseline`
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall