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.
npx skills add dariushoule/x64dbg-skills --skill find-oepgit clone --depth 1 https://github.com/dariushoule/x64dbg-skillsWrote 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.
[](https://agentmods.dev/skills/dariushoule/x64dbg-skills/find-oep)<a href="https://agentmods.dev/skills/dariushoule/x64dbg-skills/find-oep"><img src="https://agentmods.dev/badge/skills/dariushoule/x64dbg-skills/find-oep/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.
<a href="https://agentmods.dev/skills/dariushoule/x64dbg-skills/find-oep"><img src="https://agentmods.dev/badge/skills/dariushoule/x64dbg-skills/find-oep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.02609 |
| Opus 5 | $0.00026 | $0.01305 |
| Sonnet 5 | $0.00010 | $0.00522 |
| Haiku 4.5 | $0.00005 | $0.00261 |
Grade A, and why
find-oep 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
find-oep
Smart trace-based OEP finder for packed/protected PE executables. Walks through unpacking stages using intelligent stepping, anti-debug evasion, and heuristic OEP detection. Once the OEP is found, captures a state snapshot for downstream use (PE reconstruction, analysis, etc.).
Instructions
1. Gather input and assess target
Ask the user (via AskUserQuestion) for any information not already provided:
- Target path — absolute path to the packed PE on disk
- x64dbg path — absolute path to x64dbg/x32dbg (if not already known)
- Bitness — 64-bit or 32-bit (default: 64)
Determine the CIP register name: rip for 64-bit, eip for 32-bit.
Determine the stack pointer register: rsp for 64-bit, esp for 32-bit.
Determine the debugger variant: x64dbg.exe for 64-bit, x32dbg.exe for 32-bit.
2. Launch the debugger and load the target
Use mcp__x64dbg__start_session with:
executable_path: the packed PE pathx64dbg_path: the appropriate debugger binary
Always start a new session for a clean environment. Wait for the debugger to settle — call mcp__x64dbg__get_debugger_status and confirm the debuggee is paused at the entry point. If running, call mcp__x64dbg__pause.
Record the session PID and x64dbg path for later reconnection.
3. Initial reconnaissance
Gather information about the packed binary to inform the unpacking strategy:
- Capture entry state: Call
mcp__x64dbg__get_all_registersto record the initial register state (especially the stack pointer — packers often restore it before jumping to OEP). - Memory map: Call
mcp__x64dbg__get_memory_mapto identify the module's sections, their protections, and any suspicious characteristics (e.g., sections with write+execute, sections with zero raw size but large virtual size, non-standard section names). - Entry point disassembly: Disassemble 50–100 instructions from the entry point using
mcp__x64dbg__disassembleto identify the packer stub pattern. - YARA scan: Invoke
/yara-sigsviaSkill("yara-sigs")to identify the packer and obvious crypto/anti-debug signatures.- You may rerun this YARA scan if the packer contains self-decrypting code that hides signatures until unpacked.
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.
- 12d ago First seen · 147 lines · 51 tokens per session scan A 6a37682f0bca
find-oep is a skill published in the GitHub repository dariushoule/x64dbg-skills (205 stars, last pushed 6mo ago), licensed MIT. It adds 51 tokens to every session and 2,609 once invoked, about $0.0003 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.
Other skills, from other repositories
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
gke-node-notready
Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node status, or when workloads are evicted or stuck Pending due to node health. Don't…
gke-ai-troubleshooting-jobset-interruption
Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously. Use when troubleshooting JobSet restart loops, spot VM preemptions, node readiness failures, host VM issues, or coordinator worker crashes. Don't use for general GKE cluster creation, basic workload deployment, or…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
fixing-motion-performance
Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance.