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/xdido/chiron/debugnpx skills add xDido/chiron --skill debuggit clone --depth 1 https://github.com/xDido/chironWhat 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 | $0.00040 | $0.03218 |
| Opus 5 | $0.00020 | $0.01609 |
| Sonnet 5 | $0.00008 | $0.00644 |
| Haiku 4.5 | $0.00004 | $0.00322 |
Grade D, and why
debug scanned grade D with 2 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 yesterday.
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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
**Critical rule:** never refuse to fix a bug when the user explicitly asks for it. Phrases like *"just fix it"*, *"give me the fix"*, *"skip the diagnosis"* are hard overrides — ship the fix immediately with a one-line r Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
1. **Do not moralize.** Never say *"you should have caught this earlier"* or *"this is a basic mistake."* Bugs happen to everyone. Feedback is about the bug, not the developer. How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/debug — structured debugging with hypothesis testing
Quick start:
/debug— debug the current error in context/debug path/to/file.go:42— debug starting from a specific location/debug "connection refused after deploying new config"— debug a described symptom
Step 0 — Load project context
Check if .chiron-context.md exists in the project root.
If it exists: Read it. This file is your complete project reference. DO NOT scan the codebase or read additional files beyond .chiron-context.md and the specific file(s) the user mentions in their request. Proceed to the next step.
If it does NOT exist: Tell the user:
No project context found. Run
/teach-chironfirst — it scans your codebase once and generates.chiron-context.mdso all chiron skills work without re-scanning.
Then stop.
┌──────────────────────────────────────────────┐
│ /debug │
├──────────────────────────────────────────────┤
│ REQUIRES .chiron-context.md │
│ Run /teach-chiron once to generate it │
├──────────────────────────────────────────────┤
│ CORE (always active) │
│ ✓ Hypothesis-driven debugging (L0–L4) │
│ ✓ Root cause categorization │
│ ✓ Verification step checklists │
├──────────────────────────────────────────────┤
│ ENHANCED (with rich project context) │
│ + Project-aware symptom categorization │
│ + Framework-specific debugging guidance │
│ + Convention-aware fix suggestions │
└──────────────────────────────────────────────┘
The user's request
$ARGUMENTS
Treat the above as the user's bug report or debugging request. Apply the behavior described below.
If $ARGUMENTS is empty or whitespace-only: derive the bug from the current conversation instead of asking "what's broken?" from scratch. Scan the recent turns for the dominant failure signal — a stack trace, panic, test failure output, error message, failing command output, or an explicit "this isn't working" complaint. Open your response with a one-line confirmation: "Inferring bug from conversation: . Say otherwise and I'll retarget." Then run the normal decision tree with that symptom in place of $ARGUMENTS.
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.
- yesterday First seen · 257 lines · 40 tokens per session scan D a6903d1583e2
debug is a skill published in the GitHub repository xDido/chiron (2 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 3,218 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (tells the agent never to refuse, strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
extreme-router-gateway-engine
AI Gateway routing, provider management, and core engine expertise for ExtremeRouter. Use when working on request routing, provider fallback, token refresh, format translation, streaming, or when the user asks about "how does routing work", "add a new provider", "fix the fallback logic", "optimize token usage", or…
extreme-router-refactor
Code refactoring, tech debt cleanup, and code review expertise for ExtremeRouter. Use when cleaning up code, fixing bugs, reviewing PRs, identifying tech debt, or when the user asks to "improve this code", "fix this mess", "why is this broken", "make this cleaner", or mentions code smells, duplication, or poor…
extreme-router-ui-design
UI/UX design and page redesign expertise for ExtremeRouter dashboard. Use when redesigning pages, creating new UI components, improving visual hierarchy, or when the user mentions design, layout, styling, or user experience. Also use when the user asks to "make it look better", "improve the dashboard", "redesign this…
extremerouter-stt
Speech-to-text via ExtremeRouter /v1/audio/transcriptions using OpenAI Whisper / Groq / Gemini / Deepgram / AssemblyAI / NVIDIA / HuggingFace models. Use when the user wants to transcribe audio, convert speech to text, or get subtitles from audio files.
extremerouter-web-search
Web search via ExtremeRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity. Use when the user wants to search the web, look up information, find articles, or query a search engine.
extremerouter
Entry point for ExtremeRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions ExtremeRouter, NINEROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant…