Skip to content
Agentmart
Submit a tool

evaluate-mmi

Qualitative evaluation of Modularity Maturity Index across 4 axes: cohesion, coupling, independence, reusability.

Skill by wfukatsu

IndexedMIT★ 13
Write a review

Chalk Labs

Need help deploying evaluate-mmi?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/wfukatsu-evaluate-mmi

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Qualitative evaluation of Modularity Maturity Index across 4 axes: cohesion, coupling, independence, reusability. Requires analyze output as a prerequisite. Can run in parallel with evaluate-ddd.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/evaluate-mmi

What's inside

Skill name
evaluate-mmi
Description
Qualitative evaluation of Modularity Maturity Index across 4 axes: cohesion, coupling, independence, reusability. Requires analyze output as a prerequisite. Can run in parallel with evaluate-ddd.
License
MIT
Instructions
311 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: missing

Files (1)

  • SKILL.md

SKILL.md (first lines)

# MMI Evaluation

Shared files: a path written `@rules/…`, `@skills/…`, `@templates/…` or `@docs/…` is relative to the
plugin root, `${CLAUDE_PLUGIN_ROOT}` — not to the project being worked on. Read it from there.

**Usage:** `/architect:evaluate-mmi [target_path]`

## Desired Outcome

Evaluate each module of the target system across the 4 MMI axes and determine microservice readiness.

## Decision Criteria

For detailed scoring criteria and algorithms, refer to:
@rules/evaluation-frameworks.md

- 4 axes: Cohesion (30%), Coupling (30%), Independence (20%), Reusability (20%)
- Each axis scored 1-5
- MMI = (0.3 × C + 0.3 × K + 0.2 × I + 0.2 × R) / 5 × 100
- Maturity: 80-100 (Ready), 60-80 (Moderate), 40-60 (Needs Improvement), 0-40 (Immature)

## Prerequisites

| File | Required/Recommended | Source |
|------|---------------------|--------|
| reports/01_analysis/ | Required | /architect:analyze |

## Execution

### Step 1: Identify Modules

Glob for `reports/before/**/codebase-structure.md` to find the investigate-phase output, then read the found file. Also read `reports/01_analysis/domain-code-mapping.md`. Extract the list of modules to evaluate and record module names — these will be passed to sub-agents.

### Step 2: Collect Input File Paths

Glob for all analysis documents: `reports/01_analysis/**/*.md`

Record the full list of found file paths — these will be passed to all sub-agents.

### Step 3: Spawn Four Parallel Axis Evaluators

In a **single message**, issue all four Agent() calls simultaneously so they run in parallel.
Each evaluator scores ALL identified modules on its specific axis.

**Task A — Cohesion Axis**
```
Agent(
  subagent_type: "general-purpose",
  model: "sonnet",
  description: "MMI cohesion axis evaluation for all modules",
  prompt: """
You are evaluating COHESION (functional coherence within a module) for each module in a software system.

Modules to evaluate:
<MODULE_LIST>
[Insert the module names identified in Step 1, one per line]
</MODULE_LIST>

Read all analysis documents using the Read tool:
<FILE_LIST>
[Insert the full list of file paths found in Step 2, one per line]
</FILE_LIST>

For each module, score its Cohesion on a scale of 1-5:
- 5 (Exemplary): Single clear responsibility, all components tightly related, no leakage
- 4 (Good): Minor mixed concerns but mostly cohesive
- 3 (Acceptable): Some mixed responsibilities, identifiable but imperfect boundaries
- 2 (Concerning): Multiple unrelated responsibilities coexist
- 1 (Critical): No clear responsibility, god-class or utility-dumping-ground pattern

Return ONLY this JSON (no markdown fences, no explanation):
{
  "axis": "Cohesion",
  "weight": 0.30,
  "modules": [
    {
      "name": "<module name>",
      "score": <integer 1-5>,
      "rationale": "<1-2 sentence explanation>"
    }
  ]
}
"""
)
```

**Task B — Coupling Axis**
```
Agent(
  subagent_type: "general-purpose",
  model: "sonnet",
  description: "MMI coupling axis evaluation for all modules",
  prompt: """
You are evaluating COUPLING (degree of inter-module dependencies) for each module in a software system.

Modules to evaluate:
<MODULE_LIST>
[Insert the module names identified in Step 1, one per line]
</MODULE_LIST>

Read all analysis documents using the Read tool:
<FILE_LIST>
[Insert the full list of file paths found in Step 2, one per line]
</FILE_LIST>

For each module, score its Coupling (lower coupling = higher score) on a scale of 1-5:
- 5 (Exemplary): Minimal dependencies, well-defined interfaces, no circular dependencies
- 4 (Good): Few dependencies, mostly unidirectional
- 3 (Acceptable): Moderate dependencies, some bidirectional coupling
- 2 (Concerning): High fan-out or fan-in, implicit dependencies
- 1 (Critical): Circular dependencies, tight coupling, impossible to change in isolation

Return ONLY this JSON (no markdown fences, no explanation):
{
  "axis": "Coupling",
  "weight": 0.30,
  "modules": [
    {
      "name": "<module name>",

From wfukatsu/nexus-architect, MIT.

More from wfukatsu/nexus-architect

Signals

Stars
13
Forks
1
Open issues
0
Last commit (this folder)
Oct 8, 2026 (22 days ago)
Last release
Oct 9, 2026 (22 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from wfukatsu

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get evaluate-mmi running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying evaluate-mmi?

CallGet help
Cite this page

evaluate-mmi skill. Agent Mart. https://agentmart.dev/skills/wfukatsu-evaluate-mmi (last updated 2026-10-24)