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 MingyiSecLab/Mingyi-Atlas --skill anti-debug-bypassgit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/anti-debug-bypass)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/anti-debug-bypass"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/anti-debug-bypass/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/mingyiseclab/mingyi-atlas/anti-debug-bypass"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/anti-debug-bypass.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 | $0.00035 | $0.01984 |
| Opus 5 | $0.00017 | $0.00992 |
| Sonnet 5 | $0.00007 | $0.00397 |
| Haiku 4.5 | $0.00003 | $0.00198 |
Grade A, and why
anti-debug-bypass 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 8d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anti-Debug Bypass Playbook
Malware and protected commercial software check for debuggers and sandboxes before running real logic. Bypassing these checks is required to dynamically analyze them. Each check has a known counter.
1. Enumerate anti-debug techniques in the binary
Static signature scan
# Windows API calls
strings /tmp/sample | grep -iE 'IsDebuggerPresent|NtQuery|CheckRemoteDebugger|OutputDebugString'
# Linux ptrace check
strings /tmp/sample | grep -iE 'ptrace|/proc/self/status|TracerPid'
# CPUID hypervisor check
strings /tmp/sample | grep -iE 'vmware|VirtualBox|qemu|xen'
# Detect via YARA rules
yara -r /opt/yara-rules/anti_debug.yar /tmp/sample
Atlas helper:
bin_anti_debug_scan("/tmp/sample")
2. Common checks + bypasses
Windows checks
| Check | What it does | Bypass |
|---|---|---|
IsDebuggerPresent() |
reads PEB.BeingDebugged byte | Set PEB.BeingDebugged = 0 in debugger; ScyllaHide handles |
CheckRemoteDebuggerPresent() |
calls NtQueryInformationProcess(ProcessDebugPort) | Patch return to FALSE; ScyllaHide hooks the syscall |
NtQueryInformationProcess(ProcessDebugPort) |
returns nonzero if debugger attached | Hook + return 0 |
NtQueryInformationProcess(ProcessDebugFlags) |
returns 0 if debugger, 1 if not | Force return 1 |
NtQueryInformationProcess(ProcessDebugObjectHandle) |
nonzero handle if attached | Force NULL |
PEB.NtGlobalFlag |
0x70 if heap debugging | Set to 0 |
PEB.HeapFlags & PEB.ForceFlags |
non-default if debugger | Reset to defaults |
NtSetInformationThread(ThreadHideFromDebugger) |
unhook debugger from thread | Hook NtSetInformationThread |
INT 2D / INT 3 exception handling |
normal flow if no debugger | Set exception handler in debugger |
Hardware breakpoint detection (GetThreadContext check) |
reads DR0-3, fails if BPs set | Use software BPs, or zero DRs before check |
ScyllaHide (x64dbg/x32dbg/IDA plugin) handles essentially all of these automatically.
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.
- 8d ago First seen · 197 lines · 35 tokens per session scan A 477595d2a85c
anti-debug-bypass is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,984 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.12
Ensure access keys are rotated every 90 days or less.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.
cis-aws-foundations-6.1.2
Ensure CIFS access is restricted to trusted networks to prevent unauthorized access.
cis-aws-foundations-2.3
Ensure security contact information is registered.