engage.crash

engage.crash is a command for Claude Code from hypnguyen1209/offensive-claude. It costs 16 tokens per session (948 once invoked), scanned A, original, MIT.

A command for analyzing native-program crashes, meaning failures in compiled software such as C or C++ programs, from the crash to its cause and possible exploitability.

In plain words
What is it for?
Use it with a target binary and optional crash input, source directory, or build command to reproduce the failure, trace the corrupting write with rr, and produce a machine-checkable exploitability verdict.
Why use it?
It connects crash reproduction, root-cause analysis, code reachability, and evidence about whether a bug can be exploited, while keeping exploit execution behind an authorization check.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the offensive-claude plugin — 30 skills, 18 commands, 8 agents, 1 hook shipped together

Good fit Use it with a target binary and optional crash input, source directory, or build command to reproduce the failure, trace the corrupting write with rr, and produce a machine-checkable exploitability verdict.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/hypnguyen1209/offensive-claude/engage.crash
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.

Clone the repo
git clone --depth 1 https://github.com/hypnguyen1209/offensive-claude

Made for: Claude Code.

Or install offensive-claude, the plugin that ships this one along with the rest of its 30 skills, 18 commands, 8 agents, 1 hook.

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.

agentmods badge for engage.crash

README.md
[![agentmods](https://agentmods.dev/badge/commands/hypnguyen1209/offensive-claude/engage.crash/github.svg)](https://agentmods.dev/commands/hypnguyen1209/offensive-claude/engage.crash)
Your own site
<a href="https://agentmods.dev/commands/hypnguyen1209/offensive-claude/engage.crash"><img src="https://agentmods.dev/badge/commands/hypnguyen1209/offensive-claude/engage.crash/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for engage.crash

Your own site · 80×15
<a href="https://agentmods.dev/commands/hypnguyen1209/offensive-claude/engage.crash"><img src="https://agentmods.dev/badge/commands/hypnguyen1209/offensive-claude/engage.crash.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 948 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.00948
Opus 5 $0.00008 $0.00474
Sonnet 5 $0.00003 $0.00190
Haiku 4.5 $0.00002 $0.00095

Measured 10d ago against content hash c4111ed74f0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

engage.crash 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 10d ago.

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.

commands/engage.crash.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/engage.crash

Takes a crash (or a fuzzing corpus) for a native target and produces a validated root cause plus a machine-checkable exploitability verdict — the crash→exploitability pipeline (raptor-adoption PR-3). It sequences the rr/coverage/feasibility skills under the engagement's scope and action gates. Runs in the binary-analysis devcontainer (.devcontainer/); the rr/gcov/compile steps need a Linux toolchain and degrade gracefully (skip with a notice) where a tool is absent.

Usage

/engage.crash --target <binary> [--input <poc>] [--source <dir>] [--build "<gcc {cflags} cmd>"]

Process

1. Scope + safety (always first)

  • scope_guard.py check <target> — reproduction/exec only inside authorization.
  • Reproduction and witness replay are analysis, but any exec is routed through action_guard.py; this command never auto-runs an exploit PoC (that stays behind the gate).

2. Reproduce + root cause (rr time-travel)

  • skills/reverse-engineering/scripts/rr_root_cause.sh <target> @@ (CRASH_INPUT=) — deterministic record/replay; reverse-step to the corrupting write. See skills/reverse-engineering/references/rr-time-travel.md.
  • Output: a trace_proof artifact (function trace) + a root-cause summary.

3. Prove reachability (coverage)

  • If source is available, build --coverage, run the witness, gcov the vulnerable line — see skills/reverse-engineering/references/coverage-reachability.md. Output: a coverage_proof (gcov line-hit).
  • Either artifact satisfies the native-bug reachability bar in validate_findings.py.

4. Empirical feasibility (mitigation matrix)

  • exploit_context.py build --target <binary> — cache checksec/libc/arch once.
  • feasibility_profile.py run --build "<gcc {cflags} ...>" --witness "<./w poc>" --context exploit-context.json — rebuild the witness under permissive/distro/hardened/asan, record which still fire, derive the blocked-technique map. See skills/exploit-development/references/exploit-feasibility.md.

Read the full file on GitHub · 66 lines

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.

  1. 10d ago First seen · 66 lines · 16 tokens per session scan A c4111ed74f0b

Subscribe to this mod's changes

engage.crash is a command published in the GitHub repository hypnguyen1209/offensive-claude (357 stars, last pushed 24d ago), licensed MIT. It adds 16 tokens to every session and 948 once invoked, about $0.0001 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 2026-08-30.