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 gmh5225/awesome-llvm-security --skill dynamic-instrumentationgit clone --depth 1 https://github.com/gmh5225/awesome-llvm-securityWrote 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/gmh5225/awesome-llvm-security/dynamic-instrumentation)<a href="https://agentmods.dev/skills/gmh5225/awesome-llvm-security/dynamic-instrumentation"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-llvm-security/dynamic-instrumentation/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/gmh5225/awesome-llvm-security/dynamic-instrumentation"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-llvm-security/dynamic-instrumentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.02558 |
| Opus 5 | $0.00021 | $0.01279 |
| Sonnet 5 | $0.00008 | $0.00512 |
| Haiku 4.5 | $0.00004 | $0.00256 |
Grade A, and why
dynamic-instrumentation 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.
How it starts
The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dynamic Instrumentation Skill
This skill covers dynamic binary instrumentation (DBI), runtime tracing, and program monitoring using LLVM infrastructure.
Dynamic Binary Instrumentation Overview
What is DBI?
Dynamic Binary Instrumentation allows modifying program behavior at runtime without source code access:
- Insert analysis code at arbitrary points
- Monitor program execution
- Modify control flow and data
LLVM-Based DBI Tools
- QBDI: QuarkslaB Dynamic Binary Instrumentation
- Instrew: Fast instrumentation through LLVM lifting
- binopt: Runtime optimization of binary code
QBDI (QuarkslaB DBI)
Basic Usage
#include <QBDI.h>
// Callback function for instrumentation
QBDI::VMAction onInstruction(QBDI::VMInstanceRef vm,
QBDI::GPRState *gprState,
QBDI::FPRState *fprState,
void *data) {
// Get current instruction info
const QBDI::InstAnalysis *inst = vm.getInstAnalysis();
printf("Executing: 0x%lx - %s %s\n",
inst->address,
inst->mnemonic,
inst->operandsStr);
return QBDI::VMAction::CONTINUE;
}
int main() {
QBDI::VM vm;
// Get current stack
uint8_t *fakestack;
QBDI::allocateVirtualStack(vm.getGPRState(), 0x100000, &fakestack);
// Add instrumentation callback
vm.addCodeCB(QBDI::PREINST, onInstruction, nullptr);
// Run target function
QBDI::rword retval;
vm.call(&retval, (QBDI::rword)targetFunction, {arg1, arg2});
return 0;
}
Memory Access Tracking
QBDI::VMAction onMemoryAccess(QBDI::VMInstanceRef vm,
QBDI::GPRState *gprState,
QBDI::FPRState *fprState,
void *data) {
// Get memory accesses for current instruction
std::vector<QBDI::MemoryAccess> memAccesses = vm.getMemoryAccess();
for (const auto &access : memAccesses) {
const char* type = (access.type == QBDI::MEMORY_READ) ? "READ" : "WRITE";
printf("%s: addr=0x%lx, size=%d, value=0x%lx\n",
type, access.accessAddress, access.size, access.value);
}
return QBDI::VMAction::CONTINUE;
}
// Register callback for memory access events
vm.addMemAccessCB(QBDI::MEMORY_READ_WRITE, onMemoryAccess, nullptr);
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.
- 10d ago First seen · 378 lines · 42 tokens per session scan A f7fdfa35ff95
dynamic-instrumentation is a skill published in the GitHub repository gmh5225/awesome-llvm-security (880 stars, last pushed 26d ago), licensed MIT. It adds 42 tokens to every session and 2,558 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 2026-08-30.
Other skills, from other repositories
Deobfuscation
Systematic binary deobfuscation — string decryption, control flow flattening (CFF) removal, opaque predicate elimination, mixed boolean-arithmetic (MBA) simplification, bogus control flow, instruction substitution reversal, dead code removal, and anti-disassembly fixes. Trigger: deobfuscate, unobfuscate…
defeating-control-flow-flattening
Defeats control-flow-flattening obfuscation by identifying the dispatcher/state- variable structure and reconstructing the original control flow so the logic becomes readable. Activates for requests to defeat control-flow flattening, deobfuscate an OLLVM-flattened function, or recover original control flow from a…
stop-chasing-the-optimizer-reduce-instead
After two failed anti-optimization patches, stop and reduce; don't keep bolting on volatile / noinline.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.