rice

rice is a skill for Claude Code, Codex from tmj-90/gaffer. It costs 68 tokens per session (907 once invoked), scanned A, original, Apache-2.0.

A prioritisation method called RICE that ranks feature ideas using Reach, Impact, Confidence, and Effort.

In plain words
What is it for?
It calculates scores, ranks a backlog, calibrates estimates, and checks that selected work fits within a sprint’s available capacity.
Why use it?
It gives teams a consistent way to compare competing work instead of choosing based mainly on who argues most loudly.

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/tmj-90/gaffer/rice
Any agent
npx skills add tmj-90/gaffer --skill rice
Clone the repo
git clone --depth 1 https://github.com/tmj-90/gaffer

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 rice

README.md
[![agentmods](https://agentmods.dev/badge/skills/tmj-90/gaffer/rice.svg)](https://agentmods.dev/skills/tmj-90/gaffer/rice)
Your own site
<a href="https://agentmods.dev/skills/tmj-90/gaffer/rice"><img src="https://agentmods.dev/badge/skills/tmj-90/gaffer/rice.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 907 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 $0.00068 $0.00907
Opus 5 $0.00034 $0.00453
Sonnet 5 $0.00014 $0.00181
Haiku 4.5 $0.00007 $0.00091

Measured 4d ago against content hash 58ec023b2834, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rice 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 4d 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.

runner/skills/rice/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prioritise features with RICE scoring

RICE cuts through "loudest voice" prioritisation. Every feature gets a score from the same formula; the list sorts itself.

The formula

RICE = (Reach × Impact × Confidence) / Effort
Factor What it measures Scale
Reach Users affected per time period (e.g. per quarter) Raw number (not a 1–5 scale)
Impact Effect on the metric per user who encounters the feature 0.25 (minimal) / 0.5 / 1 / 2 / 3 (massive)
Confidence How certain are the estimates? 0.5 (low) / 0.8 (medium) / 1.0 (high)
Effort Person-months of work Raw number (not a 1–5 scale)

A higher score = build sooner. Within a sprint, also apply capacity constraints (effort sum ≤ sprint capacity).

Common calibration mistakes

  • Reach is per time period — "all users" is meaningless; specify the window (per quarter / per month).
  • Impact uses the fixed scale — resist the urge to invent 1–10 scales; the fixed scale forces honest comparisons.
  • Confidence should hurt — if you're guessing, use 0.5. Most estimates that feel like 0.8 are actually 0.5.
  • Effort in person-months — a 1-week task for 2 engineers = 0.5 person-months, not 1.

Steps

  1. Define the metric. RICE scores are only comparable when measuring impact on the same metric. Establish the North Star before scoring.
  2. List features. Collect all candidates. Don't pre-filter — let scoring do the filtering.
  3. Score each feature using the four factors. Be explicit about assumptions; document them next to the score.
  4. Apply confidence calibration. Push back on confidence scores above 0.8 unless there is user research, analytics, or a successful prior experiment behind the estimate.
  5. Rank. Sort descending by RICE score.
  6. Apply capacity constraints (if sprint planning). Sum effort from the top until capacity is consumed. Flag any item ≥ 5 person-months for decomposition.
  7. Sanity-check the top 5. Do the top items match intuition? If not — is the formula right, or is intuition wrong? Challenge both.

Read the full file on GitHub · 69 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. 4d ago First seen · 69 lines · 68 tokens per session scan A 58ec023b2834

Subscribe to this mod's changes

rice is a skill published in the GitHub repository tmj-90/gaffer (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 68 tokens to every session and 907 once invoked, about $0.0003 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

plan-creation

Create structured implementation plans via a 4-role scrum team (Product Owner, Architect, Eng/Delivery Lead, QA/Critic) with optional Agent Teams peer debate mode.

QBall-Inc/the-bulwark · 38 tokens

pact-init

Initialize PACT governance files in the current project.

jonathanmr22/pact · 9 tokens

titanclip

Interact with the TitanClip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, set up or manage routines (recurring scheduled tasks), or call any TitanClip API endpoint. Do NOT use for…

CES-Ltd/TitanClip · 87 tokens

backlog-grooming-assistant

Execute backlog grooming assistant operations. Auto-activating skill for Enterprise Workflows. Triggers on: backlog grooming assistant, backlog grooming assistant Part of the Enterprise Workflows skill category. Use when working with backlog grooming assistant functionality. Trigger with phrases like "backlog grooming…

nek1987/auto-agent-harness · 72 tokens

agile-product-owner

Agile product ownership toolkit for Senior Product Owner including INVEST-compliant user story generation, sprint planning, backlog management, and velocity tracking. Use for story writing, sprint planning, stakeholder communication, and agile ceremonies.

nek1987/auto-agent-harness · 47 tokens

confluence-expert

Atlassian Confluence expert for creating and managing spaces, knowledge bases, documentation, planning, product discovery, page layouts, macros, templates, and all Confluence features. Use for documentation strategy, space architecture, content organization, and collaborative knowledge management.

nek1987/auto-agent-harness · 56 tokens