mece

mece is a skill for Claude Code, Codex from uxderrick/mece-skill. It costs 81 tokens per session (1,489 once invoked), scanned A, original, MIT.

A checker for lists of requirements, plans, or categories using MECE: items should not overlap, and together they should cover everything in scope.

In plain words
What is it for?
Use it to review PRDs, feature lists, user stories, API designs, state-management plans, and roadmaps.
Why use it?
It helps reveal duplicated work, unclear boundaries, and missing cases before a plan or specification is used.

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/uxderrick/mece-skill/mece
Any agent
npx skills add uxderrick/mece-skill --skill mece
Clone the repo
git clone --depth 1 https://github.com/uxderrick/mece-skill

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 mece

README.md
[![agentmods](https://agentmods.dev/badge/skills/uxderrick/mece-skill/mece.svg)](https://agentmods.dev/skills/uxderrick/mece-skill/mece)
Your own site
<a href="https://agentmods.dev/skills/uxderrick/mece-skill/mece"><img src="https://agentmods.dev/badge/skills/uxderrick/mece-skill/mece.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,489 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 $0.00081 $0.01489
Opus 5 $0.00041 $0.00745
Sonnet 5 $0.00016 $0.00298
Haiku 4.5 $0.00008 $0.00149

Measured 5d ago against content hash 57eec601ee22, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

mece 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/mece/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MECE — Mutually Exclusive, Collectively Exhaustive

You are a structured-thinking validator. Your job is to ensure that any set of categories, requirements, specifications, or plans is MECE: every item belongs to exactly one bucket (no overlaps), and all possibilities are covered (no gaps).

Modes

1. Validate (default — when given existing content)

When the user provides or references a list, spec, plan, PRD, or any structured breakdown:

Step 1 — Identify the structure

  • What are the top-level categories or groupings?
  • What level of abstraction are they at?
  • What is the domain boundary (what's in scope)?

Step 2 — Test for Mutual Exclusivity For each pair of categories, ask:

  • Can any item belong to both categories?
  • Are there grey-area items that could fit either?
  • Is the same concept described with different names in different categories?
  • Are categories at different levels of abstraction (mixing "what" with "how")?

Step 3 — Test for Collective Exhaustiveness Ask:

  • What real-world scenarios, items, or cases exist that don't fit any category?
  • Are there edge cases at the boundaries?
  • Is there an implicit "other" bucket that should be explicit?
  • Would a practitioner in this domain immediately spot something missing?

Step 4 — Score and report

Calculate a MECE Score out of 100:

  • Start at 100
  • Each overlap: -10 points (categories counting the same thing twice)
  • Each critical gap: -15 points (missing something that will cause rework or failure)
  • Each minor gap: -5 points (missing something that can be added later without rework)
  • Minimum score: 0

Classify each finding by severity:

  • 🔴 Critical: Will cause rework, duplication, or missed requirements in implementation
  • 🟡 Moderate: Should be addressed but won't block progress
  • 🟢 Minor: Nice to fix, low impact if deferred

Step 5 — Deliver the report

Format the output as:

MECE Score: [N]/100

[For each finding, in severity order:]

🔴 OVERLAP: "[Category A]" ↔ "[Category B]"
   [One line: why these overlap and what the impact is]

🔴 CRITICAL GAP: [What's missing]
   [One line: why this matters]

🟡 GAP: [What's missing]
   [One line: why this matters]

🟢 MINOR GAP: [What's missing]
   [One line: why this matters]

Fix these now?

Read the full file on GitHub · 160 lines

Files

What ships with it

2 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. 5d ago First seen · 160 lines · 81 tokens per session scan A 57eec601ee22

Subscribe to this mod's changes

mece is a skill published in the GitHub repository uxderrick/mece-skill (18 stars, last pushed 5mo ago), licensed MIT. It adds 81 tokens to every session and 1,489 once invoked, about $0.0004 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

utility-pm-skill-iterate

Applies targeted improvements to an existing pm-skills skill based on feedback, validation reports, or convention changes. Reads current files, previews proposed changes, writes on confirmation, and suggests a version bump. Use when improving a skill after validation or feedback.

product-on-purpose/pm-skills · 58 tokens

tool-foundation-sprint-founding-hypothesis

Day 2 end capstone move of a Foundation Sprint. Compresses the sprint's full strategic frame into a single canonical sentence (the Founding Hypothesis) plus an assumption scorecard, why-we-believe, what-could-prove-us-wrong, and recommended next validation step. Use after Magic Lenses is signed. Strict canonical…

product-on-purpose/pm-skills · 109 tokens

utility-pm-workflow-builder

Guides a contributor from a workflow idea to a complete Workflow Implementation Packet (draft workflow file, draft workflow command, cross-cutting update checklist) in a staging area for review. Runs overlap analysis against the existing workflows with a Why Gate, then helps select and sequence skills with authored…

product-on-purpose/pm-skills · 126 tokens

measure-survey-analysis

Analyze survey results into actionable PM insights. Produces persona segmentation, hypothesis validation status, thematic clustering of open-text responses, statistical confidence labels, prioritized recommendations, and what-NOT-to-conclude warnings. Refuses to overstate statistical significance from weak samples or…

product-on-purpose/pm-skills · 59 tokens

foundation-meeting-agenda

Produces an attendee-facing agenda that sets what will be discussed, who owns each topic, and how time will be spent. Supports ten meeting type variants (standup, planning, review, decision-making, brainstorm, 1-on-1, stakeholder-review, project-kickoff, working-session, exec-briefing). Emits a shareable summary…

product-on-purpose/pm-skills · 101 tokens

tool-design-sprint-decide-and-storyboard

Day 3 (Wednesday) move of a Design Sprint that runs the art museum layout, heat map, speed critique, straw poll, Decider supervote, rumble-vs-all-in-one decision, and the storyboard that drives Thursday's prototype build. The most decision-heavy day of the sprint. Use Wednesday morning and afternoon after Tuesday's…

product-on-purpose/pm-skills · 102 tokens