Metis Scribe
25Agent Claude Code
L4 terminal scribe - records new-run governance in PROMPTS.txt, ROADMAP.md, and append-only GATELOG.md; preserves legacy ledgers read-only.
not rated 369
+37 yesterday A 39 tokens
original MIT
Agent Claude Code
L1 sweep coordinator - drives independent convergence, goal checking, and cleanup from the three-file ledger plus substantive evidence.
not rated 369
+37 yesterday A 29 tokens
original MIT
Agent Claude Code
L3 executor - SWEEP. Fresh production-readiness sweeper that re-derives mission coverage, inspects the changed neighborhood, checks GATELOG provenance, and returns evidence-backed P0..P3 findings.
not rated 369
+37 yesterday A 49 tokens
copy · 94% MIT
Agent Claude Code
L3 roadmap synthesizer/repair author - merges retained scout evidence into the one canonical executable ROADMAP.md and repairs only rejected items; does not spawn.
not rated 369
+37 yesterday A 37 tokens
copy · 88% MIT
Agent Claude Code
L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.
not rated 369
+37 yesterday A 36 tokens
original MIT
metis
30Command Claude Code
A controlled command for starting Metis work through an external controller. It selects a route from the recorded request and manages worker dispatch and recovery; it does not activate during ordinary coding or review requests.
not rated 369
+37 yesterday A 28 tokens
original MIT
Skill Claude CodeCodex
SwiftUI frontend visual design skill. Creates beautiful, distinctive iOS/macOS interfaces that avoid generic AI slop patterns. Covers design direction, layout systems, typography, color, spacing, brand integration, and design review. Use when designing new SwiftUI views, reviewing UI quality, creating iOS prototypes…
not rated 208
+4 5mo ago A 85 tokens
original MIT
math-skill
32Skill Claude CodeCodex
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling.
not rated 48
+1 4mo ago A 33 tokens
original MIT
Skill Claude CodeCodex
An automatic role-playing conversation mode that copies a person's writing style from supplied chat samples and personal details. It is intended for conversations involving a close relationship.
not rated 5 4mo ago A 185 tokens
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: