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/hintnpx skills add xDido/chiron --skill hintgit clone --depth 1 https://github.com/xDido/chironWrote 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/xdido/chiron/hint)<a href="https://agentmods.dev/skills/xdido/chiron/hint"><img src="https://agentmods.dev/badge/skills/xdido/chiron/hint.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 5.1 | $0.00039 | $0.01611 |
| Opus 5 | $0.00019 | $0.00805 |
| Sonnet 5 | $0.00008 | $0.00322 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade D, and why
hint 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 5d 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.
4. **Never refuse to advance.** If the user keeps running `/hint`, keep advancing. At L4, use the L4 → L4 response above, then wait for a targeted question. Strips warnings and disclaimersmediumAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
2. **Never moralize.** Same rule as `/chiron`. No "you should", no guilt, no implicit judgment. How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hint — advance one rung on the hint ladder
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 — the context file has what you need. If not: tell the user: "No project context found. Run /teach-chiron first." Then stop.
CRITICAL — user instructions always win
If the current project's .agents/README.md says to write code directly without Socratic questioning, /hint is effectively a no-op — just answer whatever the user is asking normally. User instructions always override.
Current level
Apply the voice level from .chiron-context.md. /hint always advances exactly one rung regardless of level — the level only affects the tone of the response, not the rung selection. If missing or unrecognized, use default.
Activation check
/hint only works when chiron is actively teaching. The most recent assistant turn in the conversation must be chiron-styled — produced by /chiron or /challenge, or generated while the user's .agents/README.md has activated pervasive chiron mode.
If the most recent assistant turn is NOT chiron-styled (e.g., the user never ran /chiron or /challenge, and their .agents/README.md has no chiron recipe), respond:
/hintadvances the chiron hint ladder. Run/chiron <your question>first, or/challenge <file>if you want a drill.
Do not produce any other content in that case. Stop.
If the most recent assistant turn IS chiron-styled, proceed below.
The hint ladder
Five rungs, in order from least to most revealing:
- L0 — Clarifying questions. Questions about the problem, no solution hints.
- L1 — Conceptual nudge. Name the mental model or category of primitive without naming the API. Example: "Think about what handles many-to-one communication in Go."
- L2 — Named primitive or API. Example: "Use
errgroup.WithContextfromgolang.org/x/sync." - L3 — Signature with blanks. Function signature plus
// TODO:markers showing what the user must fill in. - L4 — Full solution with inline explanation. The complete answer.
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.
- 5d ago First seen · 133 lines · 39 tokens per session scan D 5e51cb28f867
hint is a skill published in the GitHub repository xDido/chiron (2 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 1,611 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…