agent-sort

Classifies ECC skills, commands, rules, and hooks into DAILY and LIBRARY buckets using repo evidence.

Updated Mar 18, 2026
One-click install
npx skills add https://github.com/freedom909/real-estate-saas --skill agent-sort-freedom909
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-sort
Source: https://github.com/freedom909/real-estate-saas/tree/main/.trae/skills/agent-sort
Command: npx skills add https://github.com/freedom909/real-estate-saas --skill agent-sort-freedom909

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Full ECC installs load every skill, rule, and hook regardless of whether a project actually uses that stack, creating noisy context and stale configurations. This Skill builds an evidence-backed install plan so a repo only loads what its language, framework, and workflow actually require. ## Core Features & Use Cases - Evidence-Based Classification: Greps the repo for file extensions, lockfiles, framework configs, and CI settings to justify every DAILY vs LIBRARY decision. - Parallel Review Passes: Splits classification across agents, skills, commands, rules, hooks, and extras when subagents are available, or runs them sequentially. - Install Plan and Verification: Produces a DAILY inventory, LIBRARY inventory, install plan, and verification report, plus an optional skill-library router. - Use Case: A TypeScript/Next.js repo inherits the full ECC bundle including Python and Django rules. Run this Skill to demote off-stack surfaces to LIBRARY, keep TypeScript rules in DAILY, and verify no incompatible hooks remain active. ## Quick Start Analyze this repository and sort the ECC skills, commands, rules, and hooks into DAILY and LIBRARY buckets with an install plan.

Frequently Asked Questions about agent-sort

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I trim an ECC install to only what my repo needs?▼

Run the agent-sort workflow to classify every ECC skill, command, rule, and hook into DAILY or LIBRARY buckets. Each DAILY decision must cite concrete repo evidence such as file extensions, lockfiles, or framework configs, producing an install plan and verification report.

What is the difference between DAILY and LIBRARY buckets in ECC?▼

DAILY components load every session because they match the repo's active language, framework, or workflow. LIBRARY components stay accessible through search or a router skill but are not loaded by default, reducing context overhead without deleting anything.

What repo evidence is used to classify ECC components?▼

Classification uses file extensions, package managers and lockfiles, framework configs, CI and hook configs, build and test scripts, dependency manifests, and repo docs. Commands like rg --files and reading package.json, pyproject.toml, Cargo.toml, or go.mod establish the real stack.

Can agent-sort run without parallel subagents?▼

Yes. If parallel subagents are unavailable, the same six review passes (agents, skills, commands, rules, hooks and scripts, extras) run sequentially. The classification model and evidence requirements remain identical.

Does LIBRARY classification delete ECC components?▼

No. LIBRARY means the component remains installed and reachable through search, a skill-library router, or selective manual use. It only removes the component from the default always-loaded surface, so off-stack tools stay available for future needs.