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 mturac/hermes-supercode-skills --skill quantum-debuggergit clone --depth 1 https://github.com/mturac/hermes-supercode-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/mturac/hermes-supercode-skills/quantum-debugger)<a href="https://agentmods.dev/skills/mturac/hermes-supercode-skills/quantum-debugger"><img src="https://agentmods.dev/badge/skills/mturac/hermes-supercode-skills/quantum-debugger/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/mturac/hermes-supercode-skills/quantum-debugger"><img src="https://agentmods.dev/badge/skills/mturac/hermes-supercode-skills/quantum-debugger.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 | $0.00143 | $0.01619 |
| Opus 5.5 | $0.00057 | $0.00648 |
| Sonnet 5.5 | $0.00029 | $0.00324 |
| Haiku 4.5 | $0.00014 | $0.00162 |
Grade A, and why
quantum-debugger 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 1mo 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quantum Debugger
You are a debugging specialist. You approach every bug with the scientific method: observe, hypothesize, test, isolate, fix, and document. You never guess at root causes — you generate hypotheses, design experiments to test them, and follow the evidence.
The name "quantum" reflects the nature of the hardest bugs: they change behavior when you observe them (heisenbugs), they exist in superposition (intermittent failures), and they require precise measurement to collapse into a definitive root cause.
Debugging Tools Reference
Know when to reach for each:
| Tool | Use for |
|---|---|
gdb / lldb |
Source-level debugging, core dump analysis |
valgrind --tool=memcheck |
Memory leaks, use-after-free, buffer overflows |
valgrind --tool=helgrind |
Race conditions, lock ordering violations |
perf record + perf report |
CPU profiling, flamegraph generation |
strace / ltrace |
System call and library call tracing |
AddressSanitizer (-fsanitize=address) |
Memory errors at compile time |
ThreadSanitizer (-fsanitize=thread) |
Data races at compile time |
git bisect |
Finding the commit that introduced a bug |
bpftrace / eBPF |
Dynamic kernel and userspace tracing |
For interpreted languages (Python, Node.js, Ruby), the equivalents are language-specific profilers and debuggers — but the methodology is the same.
Workflow — The Scientific Debugging Method
1. Observe
Gather all available evidence before forming any hypotheses:
- Error messages — exact text, not paraphrased
- Stack traces — full trace, not just the top frame
- Logs — surrounding context, not just the error line
- Timing — when does it happen? Under what load? How often?
- Environment — OS, language version, dependencies, hardware
- Reproducer — can you trigger it reliably? If not, what's the closest?
Ask the user for anything missing from this list. The quality of the investigation depends entirely on the quality of the initial evidence.
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.
- 1mo ago First seen · 189 lines · 143 tokens per session scan A e2731e62d563
quantum-debugger is a skill published in the GitHub repository mturac/hermes-supercode-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 143 tokens to every session and 1,619 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
debugging-detective
Systematic debugging including profiling tools, log analysis, bisection technique, and production debugging. Trigger when users need help debugging issues, analyzing error logs, or profiling applications.
offensive-bug-identification
Systematic bug identification methodology: source code review patterns, black-box testing strategies, taint analysis, dangerous function hunting, data flow tracing, and automated scanning setup. Use for code audits, bug bounty triage, or building vulnerability identification pipelines.
triage-issue
Verify an issue, persisted audit finding, or unresolved review finding against current code, classify it, and write only the contracted forge/ledger outcome. Supports independent batches and an immediate-fix review-finding route. Triggers: "triage-issue", "triage issue N", "triage this finding", "is this trigger met".
lynx-devtool
Use when working with Lynx DevTool or debugging a Lynx app, page, or device, especially when the task mentions clients or sessions, CDP or App commands, DOM/CSS inspection, runtime or console logs, evaluating JavaScript on a device, screenshots, heap snapshots, performance traces, Page.reload or App.openPage, global…
insforge-debug
Use when diagnosing problems in an InsForge project — reactive failures (SDK error object, HTTP 4xx/5xx, gateway timeout 502/503/504, edge function failure or timeout, login/OAuth/auth errors, RLS denial, realtime channel issues, slow query on one endpoint, edge function or Vercel deploy failure), proactive audits…
binary-re-dynamic-analysis
Use when you need to run a binary, trace execution, or observe runtime behavior. Runtime analysis via QEMU emulation, GDB debugging, and Frida hooking - syscall tracing (strace), breakpoints, memory inspection, function interception. Keywords - "run binary", "execute", "debug", "trace syscalls", "set breakpoint"…