eval-skill
01Command Claude Code
Run scenario-based tests on a skill to measure its quality.
not rated 15 yesterday A 0 tokens
original MIT
15Stars on the repository
13Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
evolve
02Command Claude Code
Analyze instincts and route each to the best implementation mechanism. Not everything becomes a skill.
not rated 15 yesterday A 0 tokens
original MIT
hm-goal
03Command Claude Code
If architecture.yaml exists, display the current goal tree and ask if changes are needed. If it doesn't exist, guide the user through creating one.
not rated 15 yesterday A 0 tokens
original MIT
hm-night
04Command Claude Code
Run the evolution pipeline. Depth depends on evolution-config.yaml (tier + schedule).
not rated 15 yesterday A 0 tokens
original MIT
hm-status
05Command Claude Code
Show the current state of the Homunculus evolution system.
not rated 15 yesterday A 0 tokens
original MIT
Command Claude Code
Iteratively improve a skill until its eval passes, using an eval → improve loop.
not rated 15 yesterday A 0 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: