DeepReason: Skill for Claude Code

.claude/skills/dr-ask-the-right-question/SKILL.md

dr-ask-the-right-question is a skill for Claude Code from AHepi/DeepReason. It costs 93 tokens per session (2,448 once invoked), scanned A, original, MIT.

A question-routing guide for DeepReason that decides whether an answer should come from project records, written rules, or the operator.

In plain words
What is it for?
Use it when a request is short, ambiguous, or part of a workflow to translate shorthand into clear obligations and frame uncertainties as testable alternatives.
Why use it?
It prevents both invented facts and unnecessary questions by sending each uncertainty to the cheapest reliable source.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is AHepi/DeepReason's own configuration. It tells Claude Code how to work on DeepReason itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything DeepReason configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AHepi/DeepReason. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AHepi/DeepReason/main/.claude/skills/dr-ask-the-right-question/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AHepi/DeepReason

Made for: Claude Code.

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 dr-ask-the-right-question

README.md
[![agentmods](https://agentmods.dev/badge/skills/ahepi/deepreason/dr-ask-the-right-question.svg)](https://agentmods.dev/skills/ahepi/deepreason/dr-ask-the-right-question)
Your own site
<a href="https://agentmods.dev/skills/ahepi/deepreason/dr-ask-the-right-question"><img src="https://agentmods.dev/badge/skills/ahepi/deepreason/dr-ask-the-right-question.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,448 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 46
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 94
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 5.1 $0.00093 $0.02448
Opus 5 $0.00046 $0.01224
Sonnet 5 $0.00019 $0.00490
Haiku 4.5 $0.00009 $0.00245

Measured 8d ago against content hash 36f2d8880fce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dr-ask-the-right-question 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 8d 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.

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.

.claude/skills/dr-ask-the-right-question/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ask the right question

The two workflow families tell you what to PRODUCE. This skill tells you what to ASK, of whom, in what order — the reasoning that happens between an operator message and the first phase artifact. Working here fails in two ways: asking nothing (you invent facts and build on them) or asking the operator everything (their attention is the scarcest budget in the system). Both are the same mistake — a question routed to the wrong authority.

1. The three authorities, in cost order

Every question has a cheapest competent authority. Ascend only when the cheaper one genuinely cannot answer.

Authority Answers questions like Cost
THE RECORD — log.jsonl, objects/, typed verdicts, blobs, instruments (verify_root, tools/root_sweep.py, tools/docs_verify.py, the gate) what happened; which value was rejected; do two instruments agree; did anything move a command
THE FRAMEWORK — CLAUDE.md, docs/map/ (Traps first), docs/ERRATA.md, the tranche ledgers (REQUEST/GOAL/PARKED), prior DELIVERY reconciliations what is frozen; what has gone wrong here before; what did the operator already rule; where does X live a file read
THE OPERATOR genuine forks the record and framework underdetermine; frozen-surface approval; taste on user-facing shape the scarcest budget there is

Two rules that are always in force:

  • Cite the instrument with the number. Two instruments can both be right and disagree: the root census is 45 by direct manifest load over git ls-files and 42 rows by root_sweep.py, which scans experiments/ only. A number without its instrument is not a fact yet (docs/ERRATA.md E5, E8; DR-INV-frozen-surfaces, "The root sweep").
  • Model prose is never evidence. Yours included. If your answer to a record-question does not end in a command output or a file path, you have not asked the record yet.

2. Reading the operator

The operator writes tersely and expects the repo's context to carry the rest. Each row is a real committed exchange — look it up when unsure.

Read the full file on GitHub · 150 lines

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. 8d ago First seen · 150 lines · 93 tokens per session scan A 36f2d8880fce

Subscribe to this mod's changes

dr-ask-the-right-question is a skill published in the GitHub repository AHepi/DeepReason (142 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 2,448 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 170 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens