decision-quality-auditor

decision-quality-auditor is a skill for Claude Code, Codex from caiaffa/claude-code-ultimate-engineering-system. It costs 37 tokens per session (479 once invoked), scanned A, original, MIT.

A review skill for testing whether a proposal, product requirements document, architecture decision record, or other decision has enough evidence and careful comparison behind it.

In plain words
What is it for?
Use it before approving major technical decisions, reviewing PRDs or ADRs, prioritizing work, or deciding whether to proceed, revise, or reject a proposal.
Why use it?
It exposes untested assumptions, missing alternatives, unclear trade-offs, weak rollback plans, and undefined measures of success before work is committed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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/caiaffa/claude-code-ultimate-engineering-system/decision-quality-auditor
Any agent
npx skills add caiaffa/claude-code-ultimate-engineering-system --skill decision-quality-auditor
Clone the repo
git clone --depth 1 https://github.com/caiaffa/claude-code-ultimate-engineering-system

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 decision-quality-auditor

README.md
[![agentmods](https://agentmods.dev/badge/skills/caiaffa/claude-code-ultimate-engineering-system/decision-quality-auditor.svg)](https://agentmods.dev/skills/caiaffa/claude-code-ultimate-engineering-system/decision-quality-auditor)
Your own site
<a href="https://agentmods.dev/skills/caiaffa/claude-code-ultimate-engineering-system/decision-quality-auditor"><img src="https://agentmods.dev/badge/skills/caiaffa/claude-code-ultimate-engineering-system/decision-quality-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 479 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 $0.00037 $0.00479
Opus 5 $0.00018 $0.00239
Sonnet 5 $0.00007 $0.00096
Haiku 4.5 $0.00004 $0.00048

Measured 6d ago against content hash 3d94297c2a5f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

decision-quality-auditor 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 6d 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/decision-quality-auditor/SKILL.md · 49 lines

What it actually says

Mission

Raise the quality of decisions before execution locks the team into avoidable cost, risk, or rework.

When to use

  • Approving significant decisions.
  • Reviewing PRDs or ADRs.
  • Checking prioritization quality.
  • Final gate before committing resources.

Handoff

  • Receives from: prd-challenger or adr-reviewer (after initial review).
  • Hands off to: principal-engineer (with verdict: proceed / revise / reject).

Before answering

Identify: assumed problem relevance, evidence quality, option quality, reversibility, success criteria quality, decision urgency.

The decision quality test

A decision is only as strong as its weakest link:

Dimension Strong Weak Missing
Problem Evidenced, measured, urgent Plausible but unmeasured Assumed
Alternatives 2+ real options compared One real + strawmen Only one option
Trade-offs Named, sized, accepted Acknowledged vaguely "No significant trade-offs"
Reversibility Rollback plan exists "We can revert if needed" Not mentioned
Success criteria Metric + target + timeline "We'll monitor" Not mentioned
Falsifiability Kill criteria defined "We'll evaluate" Not mentioned

Red flags — send back for revision

  • Document looks complete but reasoning is thin.
  • Decision was rushed without cost-of-delay analysis.
  • Alternatives included but clearly not seriously considered.
  • Success criteria exist but won't inform any action.
  • No one can explain what happens if the hypothesis is wrong.

Output format

  1. Decision quality score: strong / adequate / weak / reject
  2. Evidence gaps (what data is missing)
  3. Option quality (were alternatives real?)
  4. Trade-off clarity (explicit / vague / missing)
  5. Reversibility (planned / vague / absent)
  6. Measurement plan (will we know if this worked?)
  7. Verdict: proceed / revise / reject
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. 6d ago First seen · 49 lines · 37 tokens per session scan A 3d94297c2a5f

Subscribe to this mod's changes

decision-quality-auditor is a skill published in the GitHub repository caiaffa/claude-code-ultimate-engineering-system (17 stars, last pushed 2mo ago), licensed MIT. It adds 37 tokens to every session and 479 once invoked, about $0.0002 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens