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-feature-recording-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-feature-recording-loop)<a href="https://agentmods.dev/skills/svnscha/dap-dbgeng/dap-feature-recording-loop"><img src="https://agentmods.dev/badge/skills/svnscha/dap-dbgeng/dap-feature-recording-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-feature-recording-loop"><img src="https://agentmods.dev/badge/skills/svnscha/dap-dbgeng/dap-feature-recording-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 | $0.00061 | $0.01209 |
| Opus 5 | $0.00030 | $0.00605 |
| Sonnet 5 | $0.00012 | $0.00242 |
| Haiku 4.5 | $0.00006 | $0.00121 |
Grade A, and why
dap-feature-recording-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 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DAP Feature Recording Loop
The co-working workflow for taking a DAP feature from implementation to recorded-session replay coverage. The division of labor is fixed: the assistant implements, verifies, and does all bookkeeping; the human performs the manual VS Code sessions, because only a real client run proves the request ordering the strict-order replay matcher asserts. Synthetic or hand-crafted fixtures are not acceptable substitutes - a scripted driver once masked a bug that made a whole feature unreachable from VS Code (setExpression, unreachable because the watch evaluate path was broken and the driver never evaluated a watch).
The loop
- Implement the feature with unit/integration coverage, as usual.
- Author the manual recording protocol (below) and leave it as a checklist the
user can work off (repo-root
TODO.md, untracked, plus the durable copy indocs/development/recording-fixtures.md). - The user records one scenario and hands back
recordings/launch.session.jsonwith words like "verify and archive". - Verify the recording (below). If it exposes a failure, switch to the
dap-analyze-traceskill: fix the adapter first, have the user re-record; never normalize a failing trace into a fixture. - Archive + normalize + test (below), do the bookkeeping, commit, push.
- Repeat until the checklist is done.
Authoring the protocol (step 2)
Each scenario entry must name: the launch target (CMake Tools), the exact UI
gestures in order (which view, which button, which values), the expected stops
and values, and the fixture file it creates plus the TEST(Replay, ...) that
consumes it. Ground rules that go with every protocol:
- Start clean: no leftover breakpoints, watches, or exception filters.
- No hovering over variables while recording (each hover records an
evaluate). - End by continuing until the debuggee exits on its own.
- Copy
recordings/launch.session.jsontorecordings/<scenario>.session.jsonimmediately (every session overwrites it). - The launch configuration must set
"dbgengPath"soNormalize-DapRecording.ps1can tokenize it to${dbgEngPath}; without it the fixture only replays where the SDK Debugging Tools sit at the default path. - Memory scenarios need Microsoft's Hex Editor extension in Replace mode (Insert-mode edits resize the file and fail to save with "Not supported").
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.
- 9d ago First seen · 103 lines · 61 tokens per session scan A 041a4fa85618
dap-feature-recording-loop is a skill published in the GitHub repository svnscha/dap-dbgeng (10 stars, last pushed 8d ago), licensed MIT. It adds 61 tokens to every session and 1,209 once invoked, about $0.0003 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.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
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.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.