dap-dbgeng: Skill for Claude Code

.claude/skills/dap-request-review/SKILL.md

dap-request-review is a skill for Claude Code from svnscha/dap-dbgeng. It costs 29 tokens per session (1,764 once invoked), scanned A, original, MIT.

A review guide for handlers that process requests in the Debug Adapter Protocol, the standard used by debuggers and development tools to communicate. It focuses on parsing, validation, typed arguments, and safe state changes.

In plain words
What is it for?
Use it when reviewing or refactoring DAP handlers such as launch, attach, breakpoints, stepping, variables, evaluate, or disconnect.
Why use it?
It helps prevent malformed requests from changing debugger state before their inputs have been checked.

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 →

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-request-review/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-request-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/svnscha/dap-dbgeng/dap-request-review"><img src="https://agentmods.dev/badge/skills/svnscha/dap-dbgeng/dap-request-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,764 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 $0.00029 $0.01764
Opus 5 $0.00015 $0.00882
Sonnet 5 $0.00006 $0.00353
Haiku 4.5 $0.00003 $0.00176

Measured 10d ago against content hash 3c63c0eaf4b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dap-request-review 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.

.claude/skills/dap-request-review/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DAP Request Review

Use this skill when reviewing or tightening the implementation of any DAP request handler such as launch, attach, initialize, configurationDone, continue, evaluate, stackTrace, setBreakpoints, pause, next, stepIn, stepOut, threads, scopes, variables, terminate, or disconnect.

This skill is for implementation quality, not coverage (see dap-request-coverage for that). The goal is to make each handler easy to audit: parse first, validate required inputs early, turn arguments into typed values, and only then touch debugger-session state, server state, or protocol side effects.

Principles

  • Parse request arguments first. Do not interleave parsing with session creation, engine calls, thread selection, event emission, or state mutation.
  • Validate required inputs before any side effect. If a required argument is missing or malformed, send the protocol error before creating or mutating anything.
  • Prefer typed locals or a typed request-specific struct. Do not pass raw nlohmann::json into dap_server helpers, debugger_session methods, or engine-facing code - convert to typed values at the top and pass those down.
  • Use canonical option names. The wire format and the implementation agree on one name per option (program, cwd, dbgengPath, stopAtEntry, sources, symbolPath, processId, connectionString, kernel, dumpFile). There are no alias chains or legacy fallbacks in this repo - keep it that way; do not add a ?? b reads.
  • Use the project's lower_case naming for locals (a stopAtEntry argument reads into stop_at_entry); never carry a JSON spelling that differs from the canonical key.
  • Keep comments rare but useful: explain why a branch, validation, or ordering constraint exists, not what the code does.
  • Make the handler read top-to-bottom as: parse -> validate -> build typed inputs -> perform session/state changes -> send responses/events.

Review Procedure

Read the full file on GitHub · 175 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. 10d ago First seen · 175 lines · 29 tokens per session scan A 3c63c0eaf4b5

Subscribe to this mod's changes

dap-request-review is a skill published in the GitHub repository svnscha/dap-dbgeng (10 stars, last pushed 9d ago), licensed MIT. It adds 29 tokens to every session and 1,764 once invoked, about $0.0001 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

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

gsd-ns-review

Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.

open-gsd/gsd-core · 16 tokens

issue

Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…

jeremylongshore/tons-of-skills-marketplace · 115 tokens

gitnexus

A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.

hashgraph-online/awesome-codex-plugins · 58 tokens

cleanup-code-inspections

Reduce technical debt and improve code quality by systematically resolving static analysis warnings.

flutter/flutter-intellij · 19 tokens

superlint

This skill describes the mandatory standard operating procedure for using our internal SuperLint tool. Use this when tasks require fixing code quality issues according to corporate standards.

mgechev/skillgrade · 0 tokens