Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/rstackjs/agent-skills/rstest-debuggingnpx skills add rstackjs/agent-skills --skill rstest-debugginggit clone --depth 1 https://github.com/rstackjs/agent-skillsWhat 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 | $0.00093 | $0.00614 |
| Opus 5 | $0.00046 | $0.00307 |
| Sonnet 5 | $0.00019 | $0.00123 |
| Haiku 4.5 | $0.00009 | $0.00061 |
Grade A, and why
rstest-debugging 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 2d 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 — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rstest Debugging
Diagnose the measured lifecycle stage before changing configuration. Keep behavior and the test manifest fixed, change one variable at a time, and remove experiments that do not produce a repeatable benefit.
Workflow
- Establish comparable single-file and full-scope baselines with
references/performance-measurement.md. - Run
rstest --tracewhen supported and classify the cost as host build/startup, runtime load/setup/collect, test bodies/hooks, or CLI/report/teardown overhead. - Use
DEBUG=rstestfor resolved config and build output. For Rstest 0.11.7+ experimental per-test bundle coverage, followreferences/performance-measurement.md. Use Rsdoctor only after evidence points to the compiler. Use verbose reporting or a profiler only after narrowing to runtime files/cases. - If dependency loading or compilation is implicated, read
references/dependency-bundling.md. Compare the environment default,bundleDependencies: false, andbundleDependencies: true; neither bundling nor externalization is universally faster. - If a fully mocked heavy module still reaches the build graph, read
references/mocked-module-build-graph.mdbefore testing an exact external. - If assets, console output, pools, isolation, or memory dominate, read
references/runtime-output-memory.md. - Rerun the representative file and full scope. Keep a change only when behavior, discovery, snapshots, and coverage remain valid and the benefit survives repeated measurement. Remove traces, profiles, and
.rstestdebug artifacts created by the diagnosis before handing off.
Guardrails
- Use the project's installed Rstest for final claims. Label local checkout or unreleased diagnostic results separately.
- Keep Node version, test files, coverage, cache state, environment, workers, and command shape fixed while comparing.
- Do not add worker durations that overlap or subtract runner/build/tests values without verifying their lifecycle boundaries.
- Do not treat aggregate process-tree RSS as physical memory; it can double-count shared pages.
- Do not disable isolation, reduce coverage, silence failures, or change production/test semantics for a benchmark win.
- Do not stack speculative aliases, externals, compiler hooks, pool settings, or caches. Preserve only the measured minimum.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 32 lines · 93 tokens per session scan A 98a2c241e117
rstest-debugging is a skill published in the GitHub repository rstackjs/agent-skills (90 stars, last pushed 6d ago), licensed MIT. It adds 93 tokens to every session and 614 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.