prioritize-bets

prioritize-bets is a skill for Claude Code from arozumenko/sdlc-skills. It costs 193 tokens per session (2,987 once invoked), scanned C, original, MIT.

A ranking skill for deciding which validated product ideas or bets should be built first. It uses scoring methods such as RICE, WSJF, or ICE and records the evidence behind each score.

In plain words
What is it for?
Use it to rank incubating or promotion-ready bets, especially when there are more approved ideas than the team can handle.
Why use it?
A validation check can show that an idea may proceed, but it does not show which idea comes first when the team cannot build everything. This creates an ordered, reviewable backlog instead of relying on gut feeling.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the sdlc-skills plugin — 53 skills shipped together

Good fit Use it to rank incubating or promotion-ready bets, especially when there are more approved ideas than the team can handle.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arozumenko/sdlc-skills/prioritize-bets
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 arozumenko/sdlc-skills --skill prioritize-bets
Clone the repo
git clone --depth 1 https://github.com/arozumenko/sdlc-skills

Made for: Claude Code.

Or install sdlc-skills, the plugin that ships this one along with the rest of its 53 skills.

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 prioritize-bets

README.md
[![agentmods](https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/prioritize-bets/github.svg)](https://agentmods.dev/skills/arozumenko/sdlc-skills/prioritize-bets)
Your own site
<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/prioritize-bets"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/prioritize-bets/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 prioritize-bets

Your own site · 80×15
<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/prioritize-bets"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/prioritize-bets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 193 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,987 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00193 $0.02987
Opus 5 $0.00097 $0.01494
Sonnet 5 $0.00039 $0.00597
Haiku 4.5 $0.00019 $0.00299

Measured 11d ago against content hash 2b47a39beebc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

prioritize-bets scanned grade C with 1 finding 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.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

the warning: the ordering is honest about being a guess. Never refuse to rank — the PO may
bundles/product-management/skills/prioritize-bets/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

prioritize-bets

The ranking skill. It answers "which of these validated bets comes first?" — the question the promotion gate never asks. A promotion gate tells you a hypothesis may proceed; it never tells you in what order. When more bets clear the gate than the team's appetite can build, this skill turns the backlog into a defensible ordered list and writes the ranks where they survive the session.

The load-bearing rule: a RICE or ICE score cannot exist without its evidence class. RICE's (and ICE's) confidence factor is not a number the PO types in — it is derived from the hypothesis's own evidence-banded confidence: block. Prioritization therefore consumes the validation pipeline instead of vibes: a bet nobody has validated cannot borrow a high confidence to jump the queue. Every persisted score carries an evidence_note naming the dimensions and band it came from, so the ranking is auditable.

What this skill reads (config, by name)

From .agents/profile.md, if it carries a prioritization: note:

  • the active framework: (RICE | WSJF | ICE) and its scales: the RICE impact_scale (massive:3 high:2 medium:1 low:0.5 minimal:0.25), reach_unit, effort_unit; the WSJF cost-of-delay components and job-size unit; the ICE scales. The framework and its numbers live in the profile note, never hardcoded in this skill — change the note and the math changes. If .agents/profile.md carries no prioritization: note (or the note doesn't exist), default to RICE with the default scales documented in references/frameworks.md, and say plainly that the default is in effect.
  • a staleness_days value, if the note carries one: a persisted scored_on older than this is what a later status/review pass would flag as stale. This skill writes the stamp that such a check would read; it does not itself audit staleness.

From .agents/profile.md and the project's docs/, more broadly: the product one-liner and stakeholder cast, so a reach estimate names a real customer count rather than an invented one.

Read the full file on GitHub · 183 lines

Files

What ships with it

3 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. 11d ago First seen · 183 lines · 193 tokens per session scan C 2b47a39beebc

Subscribe to this mod's changes

prioritize-bets is a skill published in the GitHub repository arozumenko/sdlc-skills (20 stars, last pushed 6d ago), licensed MIT. It adds 193 tokens to every session and 2,987 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). 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