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/kmajerowicz/get-shit-right/debugnpx skills add kmajerowicz/get-shit-right --skill debuggit clone --depth 1 https://github.com/kmajerowicz/get-shit-rightWhat 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 | $0.00051 | $0.01676 |
| Opus 5 | $0.00026 | $0.00838 |
| Sonnet 5 | $0.00010 | $0.00335 |
| Haiku 4.5 | $0.00005 | $0.00168 |
Grade A, and why
gsr-debug 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/gsr:debug — Debug Skill
You are executing the /gsr:debug command. Your job is to run a persistent, systematic debug investigation that survives /clear and session crashes.
Iron Laws
- One hypothesis at a time. Current Focus holds exactly one falsifiable hypothesis. Never two. If a hypothesis branches into a sub-investigation, create a sibling file referencing the parent — don't cram two hypotheses into one section.
- Write before you proceed. Every phase transition writes the file. Never advance to the next phase without updating the on-disk record first.
- Append only. Evidence and Eliminated sections grow; they never shrink. A deleted entry is a lost data point.
- Understand the fix. "It works now, not sure why" is not CONCLUDE — it's still TEST. Root cause must be named.
Entry: No active session
- Ask the user: "What's the symptom? Describe what you observe — exact error message, unexpected behavior, or failing test."
- Derive a slug from the symptom (kebab-case, max 5 words). Example:
auth-token-undefined-on-reload. - Create
docs/debug/<YYYY-MM-DD>-<slug>.mdfrom${CLAUDE_PLUGIN_ROOT}/templates/debug-md.md. Fill in:status: activefeature: the feature currently being built, or "general" if unknowncreatedandupdated: today's date- Symptom section: user's description, cleaned up to one paragraph
- Reproduction section: ask for steps if not provided; do not guess
- Next Step: "Enter OBSERVE phase — gather facts before forming any hypothesis."
- Timeline:
[<date>] Session created — OBSERVE
- Tell the user: "Here's your debug session file:
docs/debug/<slug>.md— it'll survive a/clearor session crash. Starting OBSERVE phase."
Entry: Resume existing session
- Read
docs/debug/<slug>.md. - Announce current state: "Picking up
docs/debug/<slug>.md. Current Focus:<hypothesis>. Next Step:<next step>." - Continue from the recorded Next Step. Do not re-run phases already completed unless the user asks.
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 · 145 lines · 51 tokens per session scan A 56f0b2b16436
gsr-debug is a skill published in the GitHub repository kmajerowicz/get-shit-right (5 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 1,676 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
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…