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.
curl -O https://raw.githubusercontent.com/svnscha/dap-dbgeng/develop/.claude/skills/dap-request-coverage/SKILL.mdgit clone --depth 1 https://github.com/svnscha/dap-dbgengWrote 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/svnscha/dap-dbgeng/dap-request-coverage)<a href="https://agentmods.dev/skills/svnscha/dap-dbgeng/dap-request-coverage"><img src="https://agentmods.dev/badge/skills/svnscha/dap-dbgeng/dap-request-coverage/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/svnscha/dap-dbgeng/dap-request-coverage"><img src="https://agentmods.dev/badge/skills/svnscha/dap-dbgeng/dap-request-coverage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.01761 |
| Opus 5.5 | $0.00013 | $0.00704 |
| Sonnet 5.5 | $0.00007 | $0.00352 |
| Haiku 4.5 | $0.00003 | $0.00176 |
Grade A, and why
dap-request-coverage 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 2mo 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DAP Request Coverage
Use this workflow to validate, explain, or improve coverage for a specific DAP request
area such as launch, initialize, attach, configurationDone, stackTrace,
scopes, variables, continue, evaluate, setBreakpoints, or disconnect.
Each implemented request already lives in its own translation unit
(src/service/dap_server_<command>.cpp) - that handler-file boundary is a project
convention, so unlike the prior C# layout you do not need to extract a partial first;
just confirm the file exists and is the inspection target.
The most important coverage signal in this repository is command verification through
the out-of-process session replay tests (tests/replay). Treat replay coverage as
the broader source of truth: it validates request/response ordering against realistic
DAP traffic recorded from real sessions. Line/branch coverage tooling (covdbg) is a
later addition; until then, the replay fixtures plus the request matrix are the
coverage map.
Principles
- Start from behavior: identify the DAP command, its expected protocol messages, and the existing replay fixtures before chasing percentages.
- Prefer session replay verification for broad command behavior and message ordering.
- Do not add direct
dap_serverrequest-behavior assertions where a replay fixture is the right surface. Verify request behavior through recorded session replay. - If a request's behavior is not covered, recommend capturing or updating a recorded session fixture that replays the scenario - do not hard-code request behavior into a unit test instead.
- Reserve focused unit tests (
tests/util/*,tests/service/dap_server_handler_tests.cpp,tests/service/dap_server_tests.cpp) for pure logic that sits below the request surface: argument parsing, classifiers, the engine-path resolver, pure helpers. - Use coverage to find meaningful missing behavior, not to chase a number.
Workflow
-
Identify the request area.
Determine the DAP command and its handler (
launch->handle_launch_requestinsrc/service/dap_server_launch.cpp). Search for the command string, the response type, and existing replay fixtures.
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.
- 2mo ago First seen · 182 lines · 33 tokens per session scan A 9fdcd83683ea
dap-request-coverage is a skill published in the GitHub repository svnscha/dap-dbgeng (11 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,761 once invoked, about $0.0001 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.