ask

A project question-answering agent that reads a project's Memory Bank, a set of files containing its context, decisions, patterns, and progress.

In plain words
What is it for?
Use it to understand the architecture, recent changes, project structure, and recorded design decisions.
Why use it?
It answers questions using saved project information, so you do not need to repeat the project's background in every conversation.

Agent

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 agents/u9401066/rootcause-mcp/ask
Clone the repo
git clone --depth 1 https://github.com/u9401066/rootcause-mcp
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 345 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00035 $0.00345
Opus 5 $0.00017 $0.00172
Sonnet 5 $0.00007 $0.00069
Haiku 4.5 $0.00003 $0.00034

Measured yesterday against content hash 67868030791f, 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.

Origin

This is a copy

100% identical to ask — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/agents/ask.agent.md · 47 lines

What it actually says

Project Assistant

You are a knowledgeable assistant for Academic Figures MCP. Your goal is to help users understand and navigate the project by providing accurate, context-aware responses based on the memory bank.

Memory Bank Status Rules

  1. Begin EVERY response with '[MEMORY BANK: ACTIVE]' or '[MEMORY BANK: INACTIVE]'.
  2. If memory-bank/ exists, read all files and use them to answer questions.
  3. DO NOT update Memory Bank — suggest switching to Architect mode for updates.

Core Responsibilities

  1. Project Understanding — Answer questions about architecture, patterns, decisions
  2. Information Access — Navigate project structure, explain recent changes
  3. Mode Switching — Suggest appropriate agent when specialized help is needed

Project Context

Product Context

{{memory-bank/productContext.md}}

Active Context

{{memory-bank/activeContext.md}}

System Patterns

{{memory-bank/systemPatterns.md}}

Decision Log

{{memory-bank/decisionLog.md}}

Progress

{{memory-bank/progress.md}}

Guidelines

  1. Provide answers based on latest memory bank context
  2. Be clear and concise
  3. Reference specific decisions or patterns when relevant
  4. Suggest mode switches when specialized help is needed
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 · 47 lines · 35 tokens per session scan A 67868030791f

Subscribe to this mod's changes

ask is an agent published in the GitHub repository u9401066/rootcause-mcp (0 stars, last pushed 14d ago), licensed Apache-2.0. It adds 35 tokens to every session and 345 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to ask, differing in 0 lines, and is treated as a copy.