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 agentmods add skills/mturac/hermes-supercode-skills/quantum-debuggernpx skills add mturac/hermes-supercode-skills --skill quantum-debuggergit clone --depth 1 https://github.com/mturac/hermes-supercode-skillsWhat 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 | $0.00143 | $0.01619 |
| Opus 5 | $0.00072 | $0.00809 |
| Sonnet 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 2d 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.
- 2d 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 3mo ago), licensed MIT. It adds 143 tokens to every session and 1,619 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
kaspa-sovereign-architect-engine
Source-grounded Kaspa protocol and Toccata engineering for Rusty Kaspa, KIPs, wallets, Kasware/Kaspium, indexers, WASM/TypeScript, covenants, ZK, vProgs, mining, infrastructure, repository audits, and current network or release status. Use when Codex must research, explain, design, implement, review, or verify Kaspa…
swift-networking
Builds a protocol-based async/await networking layer with URLSession, testable abstractions, error handling, and mock support for Swift projects. Use when user says "add networking", "create an API layer", "fetch data from API", "build a network service", "add URLSession", "implement HTTP requests", "create a REST…
swift-architecture-audit
Audits an existing Swift/SwiftUI/UIKit codebase for MVVM compliance, testability issues, architectural violations, concurrency problems, and anti-patterns. Use when user says "audit the codebase", "review the architecture", "why is this hard to test", "onboard to this project", "analyze the code structure", "find…
swift-code-review
Reviews Swift, SwiftUI, and UIKit code for MVVM compliance, testing standards, naming conventions, async correctness, and anti-patterns. Produces structured feedback grouped by severity. Use when user says "review this code", "check this PR", "code review", "is this correct", "give me feedback on", "review my…
swift-testing
Writes unit tests and UI tests for Swift, SwiftUI, and UIKit projects following enterprise or indie testing standards. Use when user says "write tests", "add unit tests", "test this code", "create test cases", "add XCTest", "write Swift Testing tests", "help me test this", or "add tests for". Applies enterprise or…
swiftui-component
Creates SwiftUI views and screens following MVVM with thin view layers, ViewModel extraction, previews, accessibility support, and loading/error states. Use when user says "create a SwiftUI view", "build a screen", "add a new view", "create a component", "build the UI for", "add a SwiftUI screen", or "make a new…