concern-clusterer

A code-change organizer that groups related changes by architectural concern, such as data models, core logic, APIs, infrastructure, and tests.

In plain words
What is it for?
It assigns changes to layers, groups tightly connected work, and orders the groups from foundational code to user-facing code.
Why use it?
It provides a logical build order, so related work is easier to understand and dependencies are created before the code that uses them.

Agent for Claude Code

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 agents/utilitydelta/mcp-graph-engine/concern-clusterer
Clone the repo
git clone --depth 1 https://github.com/utilitydelta/mcp-graph-engine

Made for: Claude Code.

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 365 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 $0.00026 $0.00365
Opus 5 $0.00013 $0.00182
Sonnet 5 $0.00005 $0.00073
Haiku 4.5 $0.00003 $0.00036

Measured 2d ago against content hash 38995af11732, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

concern-clusterer 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 2d 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.

.claude/agents/concern-clusterer.md · 53 lines

What it actually says

Concern Clusterer

Group code changes by architectural layer for optimal replay ordering.

Layers (typical build order)

  1. Data Models — types, structs, enums representing domain concepts
  2. Traits/Interfaces — contracts between components
  3. Core Logic — business rules, algorithms, computations
  4. Integration — how components connect, glue code
  5. API Surface — public interface exposed to users
  6. Infrastructure — config, build, deployment, CI
  7. Tests — verification code

Rules

  • Assign each change to ONE primary layer
  • Group tightly coupled changes even if in different files
  • A feature that spans layers gets split across clusters
  • Order clusters by dependency (models → traits → logic → API)

Output Format

## Cluster 1: {Name}
**Layer**: Data Models
**Changes**:
- `TypeA` in `path/file.rs`
- `TypeB` in `path/file.rs`
**Cohesion**: {why these belong together}

## Cluster 2: {Name}
**Layer**: Core Logic
**Depends on**: Cluster 1
**Changes**:
- `fn_process()` in `path/file.rs`
**Cohesion**: {why these belong together}

## Build Order
1. Cluster 1 (no dependencies)
2. Cluster 2 (depends on Cluster 1)
3. ...

Keep clusters focused. Smaller clusters with clear boundaries are better than large mixed ones.

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. 2d ago First seen · 53 lines · 26 tokens per session scan A 38995af11732

Subscribe to this mod's changes

concern-clusterer is an agent published in the GitHub repository utilitydelta/mcp-graph-engine (6 stars, last pushed 7mo ago), licensed MIT. It adds 26 tokens to every session and 365 once invoked, about $0.0001 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.