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/explainnpx skills add xDido/chiron --skill explaingit 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 | $0.00067 | $0.02649 |
| Opus 5 | $0.00034 | $0.01324 |
| Sonnet 5 | $0.00013 | $0.00530 |
| Haiku 4.5 | $0.00007 | $0.00265 |
Grade D, and why
explain 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 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
2. **Do not refuse to ship a direct answer** when asked. If the user says *"just tell me which one"* or *"skip the comparison"*, give your recommendation immediately without the full compare-and-contrast. **Anti-pattern 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 *"the right way is"* or *"you should"* — present trade-offs and let the user decide. How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/explain — compare approaches with trade-offs
Quick start:
/explain REST vs gRPC for this service— compare two named options/explain how should I handle retries?— explore a design question/explain— no argument: infer the decision point from the current conversation
Step 0 — Load project context
Check if .chiron-context.md exists in the project root. If it exists: read it. DO NOT scan the codebase or read additional files unless the user's question references a specific file. If not: tell the user: "No project context found. Run /teach-chiron first." Then stop.
The user's question or decision:
$ARGUMENTS
If $ARGUMENTS is empty or whitespace-only: derive the decision point from the current conversation instead of asking the user to restate it. Scan the recent turns for a visible choice — "should we use A or B", "I'm torn between X and Y", "not sure which pattern fits", "wondering whether to …" — or any discussion where two or more approaches are being weighed. Open with a one-line confirmation: "Inferring decision from conversation: . Say otherwise and I'll retarget." Then run the normal decision tree with that question in place of $ARGUMENTS.
Inference rules:
- Prefer an explicit comparison ("A vs B") over an implicit one. If both are present, use the most recent.
- If the user named the options themselves, preserve those exact option names in the inferred question.
- If the conversation is about implementing a specific approach (not choosing between several), redirect: "That reads like a how-to — try
/chironinstead." Do not convert an implementation question into a comparison. - If no decision point is visible, stop with: "No decision point visible in conversation — try
/explain <A vs B>or/explain <question>." - Never fabricate a decision or invent options that weren't discussed. Ambiguity → ask, don't guess.
CRITICAL — user instructions always win
If the current project's .agents/README.md conflicts with the behavior below, follow those instructions instead. This command is opt-in; the user invoked it explicitly.
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 · 191 lines · 67 tokens per session scan D 922be9dcb440
explain is a skill published in the GitHub repository xDido/chiron (2 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 2,649 once invoked, about $0.0003 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…