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/on-deck-society/love-stack/parallel-debuggingnpx skills add on-deck-society/love-stack --skill parallel-debugginggit clone --depth 1 https://github.com/on-deck-society/love-stackWhat 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 | $0.00028 | $0.00540 |
| Opus 5 | $0.00014 | $0.00270 |
| Sonnet 5 | $0.00006 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
parallel-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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Debugging
When activated, help the user debug a reported issue by pursuing multiple hypotheses in parallel instead of the traditional linear "try one thing, see if it works" loop.
The Process
-
Clarify the symptom: Ask for the exact behavior observed, the expected behavior, and the reproduction steps. Do not skip this. A vague symptom makes parallel debugging impossible because you can't score evidence against hypotheses.
-
Generate 3-5 hypotheses: Before touching code, list the possible causes. Each hypothesis should be a concrete, testable claim. Examples:
- "The API returns stale data because the cache TTL is longer than we think."
- "The race condition fires when two users submit within the same 100ms window."
- "The migration didn't run in production but did in staging."
-
For each hypothesis, identify a cheap test: What's the single fastest check that would either rule this in or rule it out? A log statement, a database query, a git log, a test repro.
-
Run all tests in parallel: Execute the cheap tests for every hypothesis before drawing conclusions. Do not pick a favorite and chase it to the end.
-
Score the evidence: After all tests return, rank hypotheses by how well the evidence supports them. Eliminate the disproven ones.
-
Narrow and repeat if needed: If no hypothesis is clearly correct, generate new ones based on what you learned.
Anti-patterns to Avoid
- Fixating on the first hypothesis and ignoring contradicting evidence
- Running tests sequentially when they're independent
- Skipping the clarification step because you "already know" what's wrong
- Confirming a hypothesis without also running tests that would disprove it
Output
For each debugging session, produce:
- The stated symptom and reproduction
- The 3-5 hypotheses considered
- The test and result for each
- The conclusion with evidence references
- The fix (or the next round of hypotheses if not yet resolved)
When to Invoke
What ships with it
1 file 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 · 49 lines · 28 tokens per session scan A 50dc61143ba6
parallel-debugging is a skill published in the GitHub repository on-deck-society/love-stack (5 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 540 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.
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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…