decision-rubric

decision-rubric is a skill for Claude Code from ai-sdlc-framework/ai-sdlc. It costs 168 tokens per session (2,834 once invoked), scanned A, original, Apache-2.0.

A decision-making guide for resolving non-trivial design, architecture, policy, or default-value choices.

In plain words
What is it for?
Use it when deciding how to resolve open questions in design documents, issue trackers, architecture proposals, or policy discussions.
Why use it?
It prevents a complex decision from being reduced to simply approving someone else's recommendation without comparing alternatives and trade-offs.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the ai-sdlc plugin — 1 skill, 17 commands, 9 agents shipped together

Good fit Use it when deciding how to resolve open questions in design documents, issue trackers, architecture proposals, or policy discussions.

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

Made for: Claude Code.

Or install ai-sdlc, the plugin that ships this one along with the rest of its 1 skill, 17 commands, 9 agents.

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 decision-rubric

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-sdlc-framework/ai-sdlc/decision-rubric.svg)](https://agentmods.dev/skills/ai-sdlc-framework/ai-sdlc/decision-rubric)
Your own site
<a href="https://agentmods.dev/skills/ai-sdlc-framework/ai-sdlc/decision-rubric"><img src="https://agentmods.dev/badge/skills/ai-sdlc-framework/ai-sdlc/decision-rubric.svg" alt="Measured on agentmods" height="20"></a>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,834 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00168 $0.02834
Opus 5 $0.00084 $0.01417
Sonnet 5 $0.00034 $0.00567
Haiku 4.5 $0.00017 $0.00283

Measured 8d ago against content hash 765ed8919453, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

decision-rubric 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 8d 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.

ai-sdlc-plugin/skills/decision-rubric/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decision rubric — how to ask the operator a non-trivial design question

Shallow question-asking is worse than not asking at all. The failure mode this rubric exists to prevent, as the operator who prompted it put it:

"I don't like this new method of resolving the questions. It doesn't go through the thinking rubric we have been doing with the questions that produces meaningful answers — it just skims over the questions and recommends the authors recommendations."

That failure shape: read the OQ → restate the author's lean → ask "agree?". The operator picks "yes" because there's nothing else to compare against, and the decision they thought they were making was actually the author's decision rubber-stamped. Six months later a real edge case surfaces and the resolution is too thin to interpret.

This skill exists so future-you doesn't do that.

When to invoke this rubric

YES — apply the rubric when the user is choosing:

  • An open-question or design-decision resolution on any work item — an RFC Open Question, a backlog task's unresolved design point, a GitHub / Jira / Linear issue asking "how should we…", a design-doc comment thread
  • A default value that ships to adopters (timeouts, retry counts, grace periods, batch sizes, severity thresholds)
  • A library, framework, or major dependency
  • An architectural pattern (single-tenant vs multi-tenant, push vs pull, sync vs async, monolith vs split)
  • A deprecation / migration / lifecycle policy
  • A schema shape that's hard to change later (DB columns, public API contracts, file formats, URI structures)
  • A trade-off between two real engineering concerns (performance vs simplicity, strict vs lazy, eager vs lazy)
  • Anything where the user's likely answer depends on context they have and you don't

NO — skip the rubric when:

  • The choice is a personal preference (file naming, commit message style, which color emoji)
  • The choice is fully reversible in <5 minutes (which directory, what to call a variable)
  • One option is dominant on every axis (there's no real trade-off)
  • The user has already stated a preference in this session or in memory
  • You're asking for missing facts ("what's the issue number?", "which branch?") — those get a plain AskUserQuestion or just-ask-in-text

Read the full file on GitHub · 162 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. 8d ago First seen · 162 lines · 168 tokens per session scan A 765ed8919453

Subscribe to this mod's changes

decision-rubric is a skill published in the GitHub repository ai-sdlc-framework/ai-sdlc (105 stars, last pushed yesterday), licensed Apache-2.0. It adds 168 tokens to every session and 2,834 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

golang-testing

Go testing best practices including table-driven tests, test helpers, benchmarking, race detection, coverage analysis, and integration testing patterns. Use when writing or improving Go tests.

affaan-m/ECC · 37 tokens

golang-patterns

Go-specific design patterns and best practices including functional options, small interfaces, dependency injection, concurrency patterns, error handling, and package organization. Use when working with Go code to apply idiomatic Go patterns.

affaan-m/ECC · 45 tokens

printing-press-amend

Amend a published CLI from one of two input sources: (1) dogfood mode mines the active Claude Code session transcript for friction (missing flags, hand- rolled API payloads, silent-null returns); (2) direct-input mode accepts user-supplied asks (rename a command, add commands or feeds, fix a named bug, optionally…

mvanhorn/cli-printing-press · 222 tokens

printing-press-output-review

Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…

mvanhorn/cli-printing-press · 102 tokens

printing-press-score

Score a generated CLI against the Steinberger bar, compare two CLIs side-by-side.

mvanhorn/cli-printing-press · 22 tokens

use-modern-go

Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.

JetBrains/go-modern-guidelines · 32 tokens