aget: Skill for Claude Code

/aget-check-evolution

Monitor the health of the .aget/evolution/ directory by checking file counts, types, naming conventions, and disk usage.

Purpose

Provide self-diagnostic capability for AGET agents to assess their evolution directory health without supervisor intervention.

Execution

When invoked, perform these checks. First verify .aget/evolution/ is a readable directory and the required tools (find, wc, du, jq, Python 3) are available. If a tool or inventory operation fails, report UNAVAILABLE with the failed check; do not turn incomplete readings into an OK result. These checks inspect filenames and JSON syntax, not lesson schema conformance or index-to-file references.

Run each shell block in Bash and inspect its exit status. A nonzero inventory/naming/disk exit means that reading is unavailable, regardless of partial stdout; discard its counts.

1. File Inventory

set -euo pipefail
# Count total files
find .aget/evolution -type f | wc -l

# Count by extension
find .aget/evolution -type f -name "*.md" | wc -l
find .aget/evolution -type f -name "*.json" | wc -l
find .aget/evolution -type f ! -name "*.md" ! -name "*.json" | wc -l

2. Naming Convention Check

Expected L-doc prefix and number width: L###_*.md or L####_*.md (three or four digits, as specified by AGET_LDOC_SPEC.md, CAP-LDOC-001). Examples: L588_skill_invocation_control_semantics.md, L1000_example.md. This check covers only the L prefix, three/four-digit number, underscore separator and .md extension. It does not validate snake_case titles, lesson contents, uniqueness or ID claims.

set -euo pipefail
# Count L-doc prefix/width matches (title conformance is not checked)
find .aget/evolution -type f \( -name "L[0-9][0-9][0-9]_*.md" -o -name "L[0-9][0-9][0-9][0-9]_*.md" \) | wc -l

# Find non-conforming files (excluding index.json)
find .aget/evolution -type f ! -name "L[0-9][0-9][0-9]_*.md" ! -name "L[0-9][0-9][0-9][0-9]_*.md" ! -name "index.json" ! -name "README.md"