ask

ask is a command for coding agents from microsoft/skills. It costs 13 tokens per session (482 once invoked), scanned A, original, MIT.

A repository question-and-answer command that searches source files and wiki context before answering with code references.

In plain words
What is it for?
Use it to answer questions about implementation details, architecture, and data flow using relevant files and citations.
Why use it?
It helps developers understand an unfamiliar codebase without relying on guesses or unsupported explanations.

Command

Part of the deep-wiki plugin — 10 commands, 3 agents shipped together

About the project

microsoft/skills is a collection of skills, custom agents, AGENTS.md templates, plugins, hooks, commands, and MCP configurations that give AI coding agents context for Azure SDK and Microsoft AI Foundry development. Developers use it to install selected domain-specific guidance into coding-agent environments. The catalogue entries are the repository’s own agent resources and supporting configurations.

microsoft/skills · 2,989 stars · on GitHub

Install

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.

agentmods
npx agentmods add commands/microsoft/skills/ask
Clone the repo
git clone --depth 1 https://github.com/microsoft/skills

Or install deep-wiki, the plugin that ships this one along with the rest of its 10 commands, 3 agents.

Wrote 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.

agentmods badge for ask

README.md
[![agentmods](https://agentmods.dev/badge/commands/microsoft/skills/ask.svg)](https://agentmods.dev/commands/microsoft/skills/ask)
Your own site
<a href="https://agentmods.dev/commands/microsoft/skills/ask"><img src="https://agentmods.dev/badge/commands/microsoft/skills/ask.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 482 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00013 $0.00482
Opus 5 $0.00006 $0.00241
Sonnet 5 $0.00003 $0.00096
Haiku 4.5 $0.00001 $0.00048

Measured yesterday against content hash 1a95373a9984, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ask 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 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.

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.

.github/plugins/deep-wiki/commands/ask.md · 63 lines

What it actually says

Deep Wiki: Repository Q&A

Answer a question about this repository grounded in actual source code.

Source Repository Resolution (MUST DO FIRST)

Before answering, resolve the source repository context:

  1. Check for git remote: Run git remote get-url origin
  2. Ask the user: "Is this a local-only repository, or do you have a source repository URL?"
    • Remote URL → store as REPO_URL, use linked citations: [file:line](REPO_URL/blob/BRANCH/file#Lline)
    • Local → use (file_path:line_number)
  3. Determine default branch: Run git rev-parse --abbrev-ref HEAD
  4. Do NOT proceed until resolved

Question

$ARGUMENTS

Process

  1. Detect language of the question and respond in the same language
  2. Search the codebase for files relevant to the question
  3. Read those files to gather evidence
  4. Synthesize an answer grounded entirely in actual code — never invent or guess

Response Format

## [Concise Answer Title]

[1-2 paragraph direct answer]

### How It Works
[Detailed explanation with inline code citations and at least 1 Mermaid diagram when the answer involves architecture, flow, or relationships]

### Key Files
| File | Purpose | Source |
|------|---------|--------|
| `src/path/file.ts` | [Role in the system] | [linked citation] |

### Code Example
<!-- Source: file_path:line_number -->
[Relevant snippet from actual source, if helpful]

### Related
- [Related concepts or files to explore]

Rules

  • ONLY use information from actual source files in this repository
  • NEVER invent, guess, or use external knowledge
  • ALWAYS cite source files inline using the resolved citation format:
    • Remote: [src/path/file.ts:42](REPO_URL/blob/BRANCH/src/path/file.ts#L42)
    • Local: (src/path/file.ts:42)
  • Think step by step through complex questions
  • If information is insufficient, say so explicitly and suggest which files to examine
Changes

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.

  1. yesterday First seen · 63 lines · 13 tokens per session scan A 1a95373a9984

Subscribe to this mod's changes

ask is a command published in the GitHub repository microsoft/skills (2,989 stars, last pushed yesterday), licensed MIT. It adds 13 tokens to every session and 482 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 2026-09-03.