dap-dbgeng: Skill for Claude Code

.claude/skills/dap-analyze-trace/SKILL.md

dap-analyze-trace is a skill for Claude Code from svnscha/dap-dbgeng. It costs 33 tokens per session (2,006 once invoked), scanned A, original, MIT.

A workflow for investigating debugger failures through DAP traces. DAP, the Debug Adapter Protocol, is the message format used between an editor and a debugger.

In plain words
What is it for?
Use it to format and analyse recorded debugging sessions, trace a live debugging bug, and make a focused fix before creating a replay test.
Why use it?
It makes the actual sequence of debugger requests, responses, and events visible before changing code.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is svnscha/dap-dbgeng's own configuration. It tells Claude Code how to work on dap-dbgeng itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dap-dbgeng configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./build/windows-x64/tests/dap-dbgeng-tests.exe --gtest_filter=<Suite.Case>.

Reuse

Borrowing it

Nothing to install: this file belongs to svnscha/dap-dbgeng. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/svnscha/dap-dbgeng/develop/.claude/skills/dap-analyze-trace/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/svnscha/dap-dbgeng

Made for: Claude Code.

Wrote 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.

agentmods badge for dap-analyze-trace

README.md
[![agentmods](https://agentmods.dev/badge/skills/svnscha/dap-dbgeng/dap-analyze-trace/github.svg)](https://agentmods.dev/skills/svnscha/dap-dbgeng/dap-analyze-trace)
Your own site
<a href="https://agentmods.dev/skills/svnscha/dap-dbgeng/dap-analyze-trace"><img src="https://agentmods.dev/badge/skills/svnscha/dap-dbgeng/dap-analyze-trace/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.

agentmods 80×15 button for dap-analyze-trace

Your own site · 80×15
<a href="https://agentmods.dev/skills/svnscha/dap-dbgeng/dap-analyze-trace"><img src="https://agentmods.dev/badge/skills/svnscha/dap-dbgeng/dap-analyze-trace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,006 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.02006
Opus 5 $0.00016 $0.01003
Sonnet 5 $0.00007 $0.00401
Haiku 4.5 $0.00003 $0.00201

Measured 9d ago against content hash 4033a3db7ca6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dap-analyze-trace 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 9d 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.

.claude/skills/dap-analyze-trace/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DAP Analyze Trace

Use this workflow when the user provides a recorded session trace, describes a live debugging failure, and wants the investigation driven by the real request and event flow before deciding whether code changes are needed.

A trace is the JSON file written when a launch/attach configuration sets a trace path (for example "trace": "${workspaceFolder}/recordings/session.json"). It has the { "version", "messages": [ { direction, message } ] } shape - the same format as the replay fixtures under tests/replay/data.

This skill is intentionally human-in-the-loop. The first pass is for trace formatting, protocol analysis, and a focused code fix or clarification request. Do not create a new replay fixture or automated regression test from the first failing trace. First fix the implementation based on the trace plus the user's description, then ask the user to rerun the live scenario. Only if that rerun succeeds should the fresh trace become an automated replay back-test.

Principles

  • Start from the user's reported live behavior, not from a guessed test scenario.
  • Format the trace first so request, response, and event ordering are easy to inspect before reasoning about code.
  • Treat the trace as evidence of protocol ordering, timing, and state transitions.
  • Do not claim the bug is fixed because a synthetic or partial test passes while the live scenario still fails.
  • Keep the first implementation change focused on the behavior the user described and the trace supports.
  • Ask for missing reproduction details if the trace and description are insufficient to identify the owning code path.
  • Do not create a new recorded-session fixture or replay test from the initial failing trace.
  • After making a fix, ask the user to rerun the real scenario and provide a fresh trace.
  • Only after the user confirms the live scenario behaves correctly should the fresh trace become the source for automated back-testing.

Required First Step

Before analyzing code, format the trace with the repository script:

Read the full file on GitHub · 206 lines

Changes

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.

  1. 9d ago First seen · 206 lines · 33 tokens per session scan A 4033a3db7ca6

Subscribe to this mod's changes

dap-analyze-trace is a skill published in the GitHub repository svnscha/dap-dbgeng (10 stars, last pushed 9d ago), licensed MIT. It adds 33 tokens to every session and 2,006 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 2026-08-31.

Related

Other skills, from other repositories

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…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

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.

open-metadata/OpenMetadata · 37 tokens

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.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens