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 SLP-DEV1/qwen-dap-mcp --skill native-runtime-debuggit clone --depth 1 https://github.com/SLP-DEV1/qwen-dap-mcpWrote 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/slp-dev1/qwen-dap-mcp/native-runtime-debug)<a href="https://agentmods.dev/skills/slp-dev1/qwen-dap-mcp/native-runtime-debug"><img src="https://agentmods.dev/badge/skills/slp-dev1/qwen-dap-mcp/native-runtime-debug/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/slp-dev1/qwen-dap-mcp/native-runtime-debug"><img src="https://agentmods.dev/badge/skills/slp-dev1/qwen-dap-mcp/native-runtime-debug.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 | $0.00095 | $0.05021 |
| Opus 5.5 | $0.00038 | $0.02008 |
| Sonnet 5.5 | $0.00019 | $0.01004 |
| Haiku 4.5 | $0.00010 | $0.00502 |
Grade A, and why
native-runtime-debug 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 — 483 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Native Runtime Debugging
Use qwen-dap-mcp to reason from structured debugger evidence instead of guessing from logs. This skill is for software, crash artifacts, and authorized local targets the user owns or is permitted to debug.
Choose the high-level workflow first
Use debug_this_crash for fatal exceptions/signals, invalid memory accesses, aborts, and crash verification. Use debug_this_hang when the process appears stuck, deadlocked, waiting forever, or spinning without useful forward progress.
When a known-good reproduction and a failing/changed reproduction can be stopped at comparable runtime states, use debug_compare_runs before guessing from source. If that comparison identifies a suspicious debugger-visible value and the live target is safe to resume, use debug_trace_value to gather bounded temporal writer evidence.
Do not use a crash-only interpretation for a hang snapshot and do not turn a hang heuristic, static runtime difference, or observed writer into certainty.
Runtime debugging v2
Prefer debug_adaptive_evidence when the required evidence depth is unknown and a cheap first pass may be sufficient. Use the richer debug_runtime_report directly when you already need modules, disassembly, crash-family fingerprints, API argument analysis, stack-integrity evidence, competing hypotheses, and the breakpoint plan.
Use debug_time_travel for record/replay work. record executes only the explicit program under rr with literal argv and no shell; replay-plan returns a loopback GDB handoff; replay-start/status/stop manage only that fixed loopback rr process and can optionally use the hardened GDB attach path. Reverse execution still requires an adapter that advertises reverse support.
Use debug_trace_lifetime for suspected stale object ownership or use-after-free. Prefer sanitizer allocation/free provenance over poison patterns, and remember that an observed writer can propagate an already-invalid pointer.
Use debug_thread_timeline when one hang snapshot cannot distinguish starvation, livelock, lock contention, or changing progress. Only call a lock cycle proven when the tool returns lockGraph.cycleProven=true; generic waits without explicit owner thread IDs remain heuristic.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +36 lines cb48a29ddf82
- 1mo ago First seen · 447 lines · 95 tokens per session scan A 4af7f4ed7e4e
native-runtime-debug is a skill published in the GitHub repository SLP-DEV1/qwen-dap-mcp (3 stars, last pushed 6d ago), licensed Apache-2.0. It adds 95 tokens to every session and 5,021 once invoked, about $0.0004 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
Debugium DAP Debugger
Drive live debug sessions for Python, Node.js, TypeScript, C, C++, Rust, Java, Scala, and WebAssembly using the Debugium MCP tools. Use when asked to debug code, set breakpoints, inspect variables, step through execution, trace bugs, or find why something crashes.
codegraph
Analyze indexed codebases via graph database (neug) and vector index (zvec). Covers call graphs, dependencies, dead code, hotspots, module coupling, architecture reports, semantic search, impact analysis, bug root cause from GitHub issues, class diagrams (UML), and PR review (risk scoring, conflict detection…
stuck
Diagnose frozen, stuck, or slow Qwen Code sessions on this machine. Scans for problematic processes, high CPU/memory usage, hung subprocesses, and debug logs. Use /stuck or /stuck to focus on a specific process.
structured-debugging
Hypothesis-driven debugging methodology for hard bugs. Use this skill whenever you're investigating non-trivial bugs, unexpected behavior, flaky tests, or tracing issues through complex systems. Activate proactively when debugging requires more than a quick glance — especially when the first attempt at a fix didn't…
memory-leak-debug
Diagnose memory leaks in the Qwen Code CLI using heap snapshots and the chrome-devtools CLI. Use when investigating high memory usage, unbounded growth, or suspected object retention issues.
bugfix
Fix a bug from a GitHub issue, following the reproduce-first workflow. Use when the user asks to fix a bug, investigate a GitHub issue, or debug a user-reported problem. Takes a GitHub issue URL or number as input.