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-backtest-loop/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-backtest-loop)<a href="https://agentmods.dev/skills/svnscha/dap-dbgeng/dap-backtest-loop"><img src="https://agentmods.dev/badge/skills/svnscha/dap-dbgeng/dap-backtest-loop/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-backtest-loop"><img src="https://agentmods.dev/badge/skills/svnscha/dap-dbgeng/dap-backtest-loop.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 | $0.00062 | $0.00966 |
| Opus 5.5 | $0.00025 | $0.00386 |
| Sonnet 5.5 | $0.00012 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
dap-backtest-loop 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Back-testing features against real targets
The loop is: script a scenario -> run it -> read the trace -> fix what it exposes -> keep the trace as a fixture. A feature is back-tested when a recorded session proves it works against a real target and a replay test locks that behavior in.
The harness is C:\Users\svnscha\Code\dap-dbgeng-rc (uv run dap-dbgeng-rc run <scenario>). Scenarios live in src/dapdbgeng_rc/scenarios/.
What can and cannot run in parallel
Live scenarios cannot run in parallel, and no amount of fanning out changes it:
- one desktop: two windows fight over focus, and the Remote Control extension binds one port,
- one kernel target: KDNET accepts a single debugger,
- one service per machine: starting it twice is the same service.
Run live scenarios one at a time. What does parallelize is everything after the trace exists: reading traces, cross-checking the request matrix, drafting fixtures and tests. Fan out there.
Running a scenario
The launch configuration must set trace (a path under recordings/), or the
run produces nothing to analyze:
"trace": "${workspaceFolder}/recordings/kernel.session.json"
The trace is written when the adapter exits cleanly, from the recorder's destructor. A killed adapter leaves no trace - which is itself a finding, not a harness glitch. Copy the file to a scenario-specific name straight after the run; the next run overwrites it.
Reading the trace, not the screen
A scenario that sleeps through a failed session looks exactly like one that worked: steps print, the window looks plausible, nothing fails. Judge a run by its trace, never by the step log.
pwsh scripts/Format-DapSessionFlow.ps1 -Path recordings/<scenario>.session.json
Check: every request the scenario is about is present and status=ok; the stops
match what the scenario asked for; the session ends with exited/terminated
and a disconnect response. Screenshots are for what the viewer sees; the
trace is for what the adapter did. Both lie in different directions, so use
each for its own question.
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 · 96 lines · 62 tokens per session scan A 579ff49a93f3
dap-backtest-loop is a skill published in the GitHub repository svnscha/dap-dbgeng (11 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 966 once invoked, about $0.0002 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
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
reality-verification
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…
debugging
Playwright test debugging conventions for the scaffold — reading failure messages, classifying failure modes (TimeoutError, ZodError, strict-mode violation, locator not found, network errors, schema drift), the playwright.config.ts capture defaults (trace on-first-retry, screenshot only-on-failure, video…
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…