decisions-need-an-alternative

decisions-need-an-alternative is a skill for Claude Code from redhuntlabs/wizard. It costs 29 tokens per session (861 once invoked), scanned A, original, MIT.

A decision-making discipline that requires an explicit alternative for every recommendation or commitment, along with the reason that alternative was rejected.

In plain words
What is it for?
Use it when recommending an option, choosing a project direction, closing a comparison, or telling someone to proceed with a plan.
Why use it?
It exposes whether a choice was compared with another plausible option instead of being accepted as obvious. This helps reveal overlooked trade-offs before the decision is final.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the wizard plugin — 37 skills, 6 commands, 1 agent, 1 hook shipped together

Good fit Use it when recommending an option, choosing a project direction, closing a comparison, or telling someone to proceed with a plan.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhuntlabs/wizard/decisions-need-an-alternative
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 redhuntlabs/wizard --skill decisions-need-an-alternative
Clone the repo
git clone --depth 1 https://github.com/redhuntlabs/wizard

Made for: Claude Code.

Or install wizard, the plugin that ships this one along with the rest of its 37 skills, 6 commands, 1 agent, 1 hook.

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 decisions-need-an-alternative

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhuntlabs/wizard/decisions-need-an-alternative/github.svg)](https://agentmods.dev/skills/redhuntlabs/wizard/decisions-need-an-alternative)
Your own site
<a href="https://agentmods.dev/skills/redhuntlabs/wizard/decisions-need-an-alternative"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/decisions-need-an-alternative/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 decisions-need-an-alternative

Your own site · 80×15
<a href="https://agentmods.dev/skills/redhuntlabs/wizard/decisions-need-an-alternative"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/decisions-need-an-alternative.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 861 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 $0.00029 $0.00861
Opus 5 $0.00015 $0.00430
Sonnet 5 $0.00006 $0.00172
Haiku 4.5 $0.00003 $0.00086

Measured 10d ago against content hash 56878c3abd36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

decisions-need-an-alternative 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 10d 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.

spells/thinking/decisions-need-an-alternative/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decisions Need an Alternative

What this does

Forces every decision to name at least one explicit alternative that was considered and the reason it lost. Prevents the "obvious choice" trap that's the source of most preventable bad calls.

When to use

  • About to recommend an option to someone
  • About to commit to a path
  • About to close out a comparison
  • About to tell someone "let's do X"

What you bring (Inputs)

  • The decision being made
  • The recommended option

What you get (Output)

The decision PLUS an explicit "considered alternative" with reason rejected.

How it works (Steps)

This is a discipline. The behavioral structure is: a non-negotiable rule (below), an excuses-and-counters table to defeat rationalizations, warning signs to spot the moment of risk, and a hard gate that fires before declaring the decision. Apply the gate at every decision; name an alternative or pause.

The non-negotiable rule

No decision is final without naming at least one alternative considered and the specific reason it was rejected.

Excuses and counters

If you think... Reality
"There's an obvious choice" "Obvious" is the rationalization that costs the most. Name an alternative.
"I considered alternatives in my head" If they're not written down, they don't count. Write them.
"We're in a hurry" The cost of a bad decision is bigger than the cost of writing one alternative.
"There's no real alternative" "Do nothing" is always an alternative. So is "wait a week." Name one.
"Everyone agrees on this" Universal agreement is a warning sign, not a green light. Name the dissent.
"This is reversible, doesn't need rigor" Reversible decisions still benefit from one named alternative. 30 seconds.

Warning signs

  • Reasoning includes "obviously," "clearly," "the answer is"
  • You're recommending something without having to think about why
  • You feel time pressure to skip the comparison
  • Everyone in the room nodded immediately
  • You can't say what would have been a reasonable second-best

Read the full file on GitHub · 92 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. 10d ago First seen · 92 lines · 29 tokens per session scan A 56878c3abd36

Subscribe to this mod's changes

decisions-need-an-alternative is a skill published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 861 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 2026-08-31.