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/arishofmann/opus-to-fable/fable-debugnpx skills add arishofmann/opus-to-fable --skill fable-debuggit clone --depth 1 https://github.com/arishofmann/opus-to-fableWrote 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/arishofmann/opus-to-fable/fable-debug)<a href="https://agentmods.dev/skills/arishofmann/opus-to-fable/fable-debug"><img src="https://agentmods.dev/badge/skills/arishofmann/opus-to-fable/fable-debug.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00105 | $0.00592 |
| Opus 5 | $0.00053 | $0.00296 |
| Sonnet 5 | $0.00021 | $0.00118 |
| Haiku 4.5 | $0.00011 | $0.00059 |
Grade A, and why
fable-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 4d 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.
What it actually says
Fable Debug — wissenschaftliches Debugging
Opus' häufigster Fehler: eine vermeintliche Ursache instinktiv diagnostizieren und sofort losfixen, ohne zu prüfen, ob der Fehler überhaupt real ist oder woher die Daten kommen. Dieser Skill verbietet das und erzwingt ein methodisches Vorgehen.
Vorgehen (in Reihenfolge)
1. Reproduzieren
- Erst den Fehler reproduzierbar machen. Lies die tatsächliche Fehlermeldung / den Stacktrace — nicht die vermutete. Notiere die exakten Schritte/Eingaben, die ihn auslösen.
- Lässt er sich nicht reproduzieren: erst klären, ob er real ist, bevor du irgendetwas "fixt".
2. Erst beobachten, dann erklären
- Verfolge, woher die betroffenen Daten/Werte kommen (Quelle → Transformationen → Stelle des Fehlers).
- Sammle Fakten (Logs, Werte, Zustände), bevor du eine Erklärung formulierst.
3. Hypothesen bilden — mehrere
- Formuliere ≥2 konkrete, falsifizierbare Hypothesen für die Ursache.
- Für jede: Welche Beobachtung würde sie bestätigen oder widerlegen? Spring nicht auf die erste.
4. Gezielt testen — eine Variable pro Schritt
- Ändere/prüfe jeweils nur eine Sache, damit die Ursache eindeutig zuordenbar bleibt.
- Nutze gezielte Logs/Asserts/minimale Repro statt breiter, hoffnungsbasierter Änderungen.
5. Root Cause vor Fix
- Behebe die Ursache, nicht das Symptom. Erkläre kurz, warum der Fehler entsteht.
- Prüfe, ob dieselbe Ursache an anderen Stellen ebenfalls auftritt.
6. Nach dem Fix verifizieren
- Repro erneut ausführen → wirklich behoben? Keine Regression im Happy Path und an den Error-Paths?
- Wenn möglich, einen Test ergänzen, der genau diesen Bug künftig fängt.
Antimuster (vermeiden)
- Diagnostizieren, ohne den Fehler reproduziert zu haben.
- Annehmen, ein gemeldeter Fehler sei echt, ohne ihn zu verifizieren.
- Mehrere Dinge gleichzeitig ändern und hoffen, dass eines wirkt.
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.
- 4d ago First seen · 47 lines · 105 tokens per session scan A 2d8ea88e3fd4
fable-debug is a skill published in the GitHub repository arishofmann/opus-to-fable (2 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 592 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 2026-08-31.
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…