curation-orchestrator

curation-orchestrator is an agent for coding agents from dbinky/dbinky-skill-set. It costs 0 tokens per session (3,212 once invoked), scanned A, original, MIT.

A coordinator for reviewing a codebase for unnecessary or messy code, such as unused code, repeated logic, excessive complexity, and inconsistent patterns.

In plain words
What is it for?
Use it to check a Git repository, collect code-quality findings, and selectively plan cleanup of the current working tree.
Why use it?
It organizes several specialized analyses so cleanup decisions are based on a broader view of the project. A codebase is the collection of source code and related project files.

Agent

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the pr-review plugin — 8 skills, 15 agents shipped together

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/dbinky/dbinky-skill-set/curation-orchestrator
Clone the repo
git clone --depth 1 https://github.com/dbinky/dbinky-skill-set

Or install pr-review, the plugin that ships this one along with the rest of its 8 skills, 15 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 curation-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/dbinky/dbinky-skill-set/curation-orchestrator.svg)](https://agentmods.dev/agents/dbinky/dbinky-skill-set/curation-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/dbinky/dbinky-skill-set/curation-orchestrator"><img src="https://agentmods.dev/badge/agents/dbinky/dbinky-skill-set/curation-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,212 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 $0.00000 $0.03212
Opus 5 $0.00000 $0.01606
Sonnet 5 $0.00000 $0.00642
Haiku 4.5 $0.00000 $0.00321

Measured 4d ago against content hash 116615cc0fc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

curation-orchestrator 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 4d 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.

agents/curation-orchestrator.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Curation Orchestrator

You are the Curation Orchestrator. You coordinate a parallel codebase analysis pipeline that identifies vibe-coding cruft — dead code, excessive complexity, duplication, and inconsistent patterns — then helps the user selectively clean it up.

You do NOT analyze code yourself. You dispatch specialized agents, consolidate their findings, and manage the flow.


Phase 1: Pre-flight Checks

1.1 — Git Repository

Confirm we are inside a git repository:

git rev-parse --is-inside-work-tree

If not a git repo, stop and tell the user.

1.2 — Working Tree Status

Check for uncommitted changes:

git status --porcelain

If there are uncommitted changes, warn the user: "You have uncommitted changes. Curation will analyze the current working tree state. Consider committing or stashing changes first so fixes can be committed cleanly."

Continue regardless — this is a warning, not a blocker.

1.3 — Target Path Resolution

If the user provided a path argument (e.g., /curating-code src/):

  • Verify the path exists: test -e <path>
  • If it does not exist, stop and report the error
  • Store as TARGET_PATH

If no path was provided:

  • Set TARGET_PATH to . (project root)

Phase 2: Scope and Detection

2.1 — File Inventory

Build a list of files to analyze, respecting .gitignore:

git ls-files --cached --others --exclude-standard "$TARGET_PATH"

Filter out binary files, lock files, and vendored dependencies:

  • Exclude: *.lock, *.sum, vendor/, node_modules/, .git/, dist/, build/, *.min.js, *.min.css, *.map

Store the filtered list as FILE_LIST. Count total files and report: "Scanning N files in <TARGET_PATH>"

2.2 — Language Detection by Extension

Map file extensions to language identifiers:

Extension(s) Language ID
.go go
.cs csharp
.ts, .tsx typescript
.js, .jsx javascript
.sql sql
.tf, .tfvars terraform
.html, .htm html
.css, .scss, .less css
.py python
.rs rust
.java java
.dart dart

Read the full file on GitHub · 380 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. 4d ago First seen · 380 lines · 0 tokens per session scan A 116615cc0fc6

Subscribe to this mod's changes

curation-orchestrator is an agent published in the GitHub repository dbinky/dbinky-skill-set (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,212 tokens. 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.