unknowns-first

unknowns-first is a skill for Claude Code, Codex from bahayonghang/my-ai-cli-toolkit. It costs 93 tokens per session (1,468 once invoked), scanned A, original, MIT.

A diagnosis guide for turning an unclear task into a defined brief with a clear measure of success before work begins.

In plain words
What is it for?
Use it when the request is vague, the user is unfamiliar with the problem, or success criteria and required references need to be established before execution.
Why use it?
It exposes missing information that could change the deliverable, quality standard, or implementation path, and prompts focused clarification questions.

Skill for Claude CodeCodex

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 skills/bahayonghang/my-ai-cli-toolkit/unknowns-first
Any agent
npx skills add bahayonghang/my-ai-cli-toolkit --skill unknowns-first
Clone the repo
git clone --depth 1 https://github.com/bahayonghang/my-ai-cli-toolkit

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 unknowns-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/unknowns-first.svg)](https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/unknowns-first)
Your own site
<a href="https://agentmods.dev/skills/bahayonghang/my-ai-cli-toolkit/unknowns-first"><img src="https://agentmods.dev/badge/skills/bahayonghang/my-ai-cli-toolkit/unknowns-first.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 1,468 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 $0.00093 $0.01468
Opus 5 $0.00046 $0.00734
Sonnet 5 $0.00019 $0.00294
Haiku 4.5 $0.00009 $0.00147

Measured 5d ago against content hash 9bb113b50c7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

unknowns-first 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 5d 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/development-workflows/unknowns-first/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unknowns First

Use this skill to diagnose a task before doing it. The goal is to find the unknowns that could change the task direction, quality bar, deliverable, or execution path.

Do not execute the user's substantive task during the opening diagnosis unless the user explicitly asks to skip diagnosis.

Routing: for brainstorming a feature into an implementation plan use spark.

Core Contract

Before execution, produce an opening diagnosis:

  1. Restate your understanding of the task.
  2. Judge the user's starting point.
  3. Identify four kinds of unknowns:
    • known knowns
    • known unknowns
    • unknown knowns
    • unknown unknowns
  4. Judge the task level.
  5. Identify the true expert for that level.
  6. Establish current success standards.
  7. Decide whether references, prototypes, examples, or HTML interaction are needed.
  8. Identify only the key unknowns.
  9. Ask focused clarification questions.
  10. Stop and wait for user confirmation.

The numbered list is a thinking order, not necessarily a conversation-turn order. A first response may cover steps 1-9 together, but step 10 must remain a real stop.

Four Unknowns

Use these meanings:

  • Known knowns: facts, goals, constraints, and standards the user has already made explicit.
  • Known unknowns: gaps the user already knows need clarification.
  • Unknown knowns: tacit judgment, taste, context, examples, or standards the user can recognize but has not verbalized yet.
  • Unknown unknowns: domain risks, expert failure modes, missing concepts, hidden dependencies, or success criteria the user may not know to ask about.

Mode Selection

Use full mode when the task is ambiguous, unfamiliar, high-stakes, cross-functional, strategic, creative, learning-oriented, or likely to create rework.

Use lite mode when the task is simple but underspecified:

  1. Restate the task.
  2. Name the likely success standard.
  3. Surface the key unknowns.
  4. Ask 1-3 questions.
  5. Stop for confirmation.

Skip diagnosis only when the user explicitly asks for immediate execution, the request is trivial, or the answer is already fully constrained.

Read the full file on GitHub · 175 lines

Files

What ships with it

4 files 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.

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. 5d ago First seen · 175 lines · 93 tokens per session scan A 9bb113b50c7b

Subscribe to this mod's changes

unknowns-first is a skill published in the GitHub repository bahayonghang/my-ai-cli-toolkit (16 stars, last pushed today), licensed MIT. It adds 93 tokens to every session and 1,468 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.