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 skills add hxy91819/mason-skills --skill ask-oraclegit clone --depth 1 https://github.com/hxy91819/mason-skillsWrote 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/hxy91819/mason-skills/ask-oracle)<a href="https://agentmods.dev/skills/hxy91819/mason-skills/ask-oracle"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/ask-oracle/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hxy91819/mason-skills/ask-oracle"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/ask-oracle.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00017 | $0.00370 |
| Opus 5 | $0.00009 | $0.00185 |
| Sonnet 5 | $0.00003 | $0.00074 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
ask-oracle 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 today.
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
Ask Oracle
这是流程类 Skill，默认仅在用户显式调用 $ask-oracle 时运行。
Act only as a seeker: frame the problem, supply the decision context, and ask the oracle to provide the technical judgment. The brief must contain no agent-authored solution, recommendation, preference, or ranked options.
Process
- State the user's original goal faithfully and concisely. Keep the requested outcome and acceptance criteria here; move supporting facts to Decision context even when the user supplied them in the same message. Preserve exact wording only when its interpretation could affect the answer.
- Gather the context already available from the conversation, repository, documents, and tool results. Include every known fact, constraint, prior decision, dependency, and piece of evidence that could change the oracle's advice. Include only the few unknowns most likely to change that advice.
- Attribute any existing proposal to its source. Present it as context without endorsing, extending, or comparing it.
- Return only the following concise Markdown brief:
# Ask the Oracle
## Original request
<the user's request>
## Decision context
- <decision-relevant context>
## Request to the oracle
<the technical judgment or help being requested>
Give each fact one home. Prune background, implementation trivia, secondary unknowns, and anything that cannot affect the decision. State retained unknowns as unknowns instead of filling them with assumptions.
The brief is complete only when the original request is faithful, every known decision-changing context item is represented once, the requested help is explicit, and no technical proposal originates from the agent.
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.
- today Changed · +2 lines 59cd5ddf840a
- 8d ago Changed · +2 lines 21d926672a71
- 11d ago First seen · 34 lines · 17 tokens per session scan A 8807be44ab7a
ask-oracle is a skill published in the GitHub repository hxy91819/mason-skills (2 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 370 once invoked, about $0.0001 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…