Agent Sort

This is how you trim ECC to what a repo actually uses instead of loading everything by default. It scans your codebase for real evidence (file extensions, package manifests, framework configs) and sorts skills, rules, hooks, and commands into DAILY (load every session) versus LIBRARY (keep searchable, don't auto-load). The workflow is evidence-first: every decision needs grep-backed proof from the repo, not vibes about what might be useful. Best for teams that want a repeatable, defensible install plan when the default bundle is too noisy or the stack has drifted. Outputs a classification table, install plan, and optional router skill for the library bucket.

skills.sh installs: 5.5K
GitHub stars: 300.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/ecc --skill agent-sort --agent claude-code

Installs into .claude/skills of the current project.

Files

Agent Sort

Use this skill when a repo needs a project-specific ECC surface instead of the default full install.

The goal is not to guess what "feels useful." The goal is to classify ECC components with evidence from the actual codebase.

When to Use

A project only needs a subset of ECC and full installs are too noisy
The repo stack is clear, but nobody wants to hand-curate skills one by one
A team wants a repeatable install decision backed by grep evidence instead of opinion
You need to separate always-loaded daily workflow surfaces from searchable library/reference surfaces
A repo has drifted into the wrong language, rule, or hook set and needs cleanup

Non-Negotiable Rules

Use the current repository as the source of truth, not generic preferences
Every DAILY decision must cite concrete repo evidence
LIBRARY does not mean "delete"; it means "keep accessible without loading by default"
Do not install hooks, rules, or scripts that the current repo cannot use
Prefer ECC-native surfaces; do not introduce a second install system