rice-scoring

rice-scoring is a skill for Claude Code, Codex from tupe12334/instinct. It costs 23 tokens per session (1,940 once invoked), scanned A, original, MIT.

A scoring method for comparing features or projects using four factors: how many people they affect, how much they help, how certain the estimates are, and how much work they require.

In plain words
What is it for?
Use it to rank a development backlog, choose between initiatives, and decide what should be worked on first.
Why use it?
It replaces gut-feel ranking with explicit estimates and one comparable score for each option.

Skill for Claude CodeCodex

Part of the instinct plugin — 54 skills, 1 hook shipped together

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/tupe12334/instinct/rice-scoring
Any agent
npx skills add tupe12334/instinct --skill rice-scoring
Clone the repo
git clone --depth 1 https://github.com/tupe12334/instinct

Made for: Claude Code, Codex.

Or install instinct, the plugin that ships this one along with the rest of its 54 skills, 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 rice-scoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/tupe12334/instinct/rice-scoring.svg)](https://agentmods.dev/skills/tupe12334/instinct/rice-scoring)
Your own site
<a href="https://agentmods.dev/skills/tupe12334/instinct/rice-scoring"><img src="https://agentmods.dev/badge/skills/tupe12334/instinct/rice-scoring.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,940 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 5.1 $0.00023 $0.01940
Opus 5 $0.00012 $0.00970
Sonnet 5 $0.00005 $0.00388
Haiku 4.5 $0.00002 $0.00194

Measured 5d ago against content hash 6a432d1b7275, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

rice-scoring 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/rice-scoring/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RICE Scoring

Overview

RICE is a quantitative prioritization framework that computes a single comparable score for each feature or initiative. It prevents gut-feel ranking by forcing explicit estimates across four dimensions: how many people are affected, how much it helps them, how sure you are, and how much work it takes.

RICE Score = (Reach × Impact × Confidence) / Effort

Higher score = higher priority. Items are ranked by score descending.

The Four Dimensions

Reach — "How many people, in what time window?"

Count the number of users or customers affected per time period (typically per quarter). Use real data: DAU, MAU, conversion funnel counts, support ticket volume. Do NOT estimate in percentages here — use absolute numbers.

  • Example: 2,400 users/quarter who go through the checkout flow

Impact — "How much does this move the needle per person?"

Rate the impact on the individual user when they encounter the feature. Use a fixed scale:

Score Meaning
3 Massive (transforms the experience)
2 High (clear improvement)
1 Medium (noticeable)
0.5 Low (minor)
0.25 Minimal (barely perceptible)

Confidence — "How sure are we about Reach and Impact?"

Express as a percentage reflecting evidence quality:

% Evidence
100% Hard data (A/B test, analytics, user research)
80% Some data (anecdotal, partial research)
50% Weak data (gut feel, one conversation)

Never exceed 100%. Round to 100/80/50 — false precision is noise.

Effort — "How many person-months does this take?"

Estimate total engineering + design + PM time in person-months. Minimum value: 0.5 (half a person-month). Do NOT use story points — convert to time.

  • 1 engineer for 2 weeks = 0.5 person-months
  • 2 engineers + 1 designer for 1 month = 3 person-months

How to Apply

Step 1 — List all candidates

Write out every feature, project, or initiative under consideration. Aim to score at least 5–10 items so the ranking is meaningful.

Read the full file on GitHub · 137 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. 5d ago First seen · 137 lines · 23 tokens per session scan A 6a432d1b7275

Subscribe to this mod's changes

rice-scoring is a skill published in the GitHub repository tupe12334/instinct (1 stars, last pushed 19d ago), licensed MIT. It adds 23 tokens to every session and 1,940 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.

Related

Other skills, from other repositories

thinking-theory-of-constraints

When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.

tjboudreaux/cc-thinking-skills · 37 tokens

thinking-lindy-effect

Use when longevity of a non-perishable option matters. Treat survival duration as a remaining-life prior, then check domain drift before favoring the proven.

tjboudreaux/cc-thinking-skills · 35 tokens

thinking-kepner-tregoe

Use when a selective defect needs IS/IS-NOT difference analysis or a consequential option choice needs must/want weighting and adverse-consequence comparison.

tjboudreaux/cc-thinking-skills · 37 tokens

alive:demo

Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.

alivecontext/alive · 52 tokens

alive:session-history

Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…

alivecontext/alive · 76 tokens

alive:world

The human doesn't know what to work on, or wants to see everything at once. They need the big picture — what's active, what's stale, what needs attention. Renders a live world view grouped by ALIVE domain, then routes to open, tidy, find, history, or map.

alivecontext/alive · 63 tokens