core-qna-synthesis

core-qna-synthesis is a skill for Claude Code, Codex from oodaris/autocodex. It costs 18 tokens per session (331 once invoked), scanned A, original, MIT.

A workflow for turning several related or vague questions into a clearer question set and practical answers. It includes assumptions, trade-offs, and recommended next steps.

In plain words
What is it for?
Use it to group questions, identify missing information, answer each part, and propose three to seven next steps.
Why use it?
It helps when a broad request is difficult to answer directly or leaves important questions unstated. The workflow keeps the guidance focused on concrete actions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to group questions, identify missing information, answer each part, and propose three to seven next steps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oodaris/autocodex/core-qna-synthesis
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.

Any agent
npx skills add oodaris/autocodex --skill core-qna-synthesis
Clone the repo
git clone --depth 1 https://github.com/oodaris/autocodex

Made for: Claude Code, Codex.

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 core-qna-synthesis

README.md
[![agentmods](https://agentmods.dev/badge/skills/oodaris/autocodex/core-qna-synthesis/github.svg)](https://agentmods.dev/skills/oodaris/autocodex/core-qna-synthesis)
Your own site
<a href="https://agentmods.dev/skills/oodaris/autocodex/core-qna-synthesis"><img src="https://agentmods.dev/badge/skills/oodaris/autocodex/core-qna-synthesis/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.

agentmods 80×15 button for core-qna-synthesis

Your own site · 80×15
<a href="https://agentmods.dev/skills/oodaris/autocodex/core-qna-synthesis"><img src="https://agentmods.dev/badge/skills/oodaris/autocodex/core-qna-synthesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 331 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.
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 $0.00018 $0.00331
Opus 5 $0.00009 $0.00166
Sonnet 5 $0.00004 $0.00066
Haiku 4.5 $0.00002 $0.00033

Measured 11d ago against content hash 5fdcf870e7e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

core-qna-synthesis 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 11d 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.

skills/core-qna-synthesis/SKILL.md · 53 lines

What it actually says

Interpretive Q&A Synthesis

Repo anchors (autocodex)

  • CLI_PATH: cmd/autocodex/
  • INTERNAL_PATH: internal/
  • DOCS_PATH: docs/
  • SKILLS_PATH: skills/

When to use

  • The user asks multiple related questions or a vague “big” question.

Preconditions

  • The questions are visible in the thread.
  • If critical inputs are missing, STOP and use core-ask-questions-if-underspecified.

Inputs to confirm

  • Primary goal and success criteria
  • Constraints (time, environment, tooling)

Required artifacts

  • Refined question list
  • Practical answers with explicit assumptions
  • Recommended next steps

Quick path

  • Restate and cluster questions.
  • Add missing questions.
  • Answer with assumptions and tradeoffs.
  • Provide 3–7 concrete next steps.

Steps

  1. Restate and group questions.
  2. Expand missing-but-required questions.
  3. Answer each question clearly.
  4. Provide recommendations and next steps.

Failure modes and responses

  • Over-expansion: keep added questions minimal.
  • Abstract answers: replace with concrete actions.

Definition of done

  • Questions are refined and answered with practical guidance.

Example (minimal)

  • Input: “How should the plugin system work?”
  • Output: Protocol choice, manifest rules, call flow, and next steps.
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. 11d ago First seen · 53 lines · 18 tokens per session scan A 5fdcf870e7e4

Subscribe to this mod's changes

core-qna-synthesis is a skill published in the GitHub repository oodaris/autocodex (16 stars, last pushed 6mo ago), licensed MIT. It adds 18 tokens to every session and 331 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 2026-08-30.