builder
01Agent Claude Code
Full implementation agent with all tools for coding tasks.
not rated 5 5mo ago C 11 tokens
original Apache-2.0
explore
02Agent Claude Code
Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns, search code for keywords, or answer questions about the codebase.
not rated 5 5mo ago A 36 tokens
original Apache-2.0
graph
03Command Claude Code
Answer any codebase question using the toroidal-indexer code graph. One tool call, compact result — no grep/find/glob.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
skill
04Skill Claude CodeCodex
When the user says "/mode on coding", "/mode off", "/mode list", or wants to switch behavioral modes.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
market
05Skill Claude Code
Market analysis, portfolio review, backtesting, and performance reporting.
not rated 5 5mo ago A 14 tokens
original Apache-2.0
prp-run
06Skill Claude CodeCodex
When user says "prp run", "run prp", "run tasks", or wants to execute a PRP's tasks via fresh Claude instances for maximum reasoning quality.
not rated 5 5mo ago B 0 tokens
original Apache-2.0
Skill Claude CodeCodex
When the user says "analyze error", "why failing", "pattern", "recurring", "diagnose", "root cause", or wants to understand why an error keeps happening, find patterns in failures, or build a prevention strategy.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
audit
08Skill Claude CodeCodex
When the user says "audit", "review", "check everything", or wants a comprehensive project review.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
benchmark
09Skill Claude Code
Measure and track framework performance metrics over time. Collects test pass rates, memory counts, gate fire rates, hook latencies, and session metrics. Compares against previous baselines stored in memory to detect regressions or improvements. Saves results with type:benchmark tags for longitudinal tracking.
not rated 5 5mo ago B 59 tokens
original Apache-2.0
diagnose
10Skill Claude CodeCodex
When user says "diagnose", "gate health", "which gates fire most", "gate effectiveness", "analyze gates", "gate stats", "gate report", or wants to understand how framework gates are performing.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
introspect
11Skill Claude CodeCodex
Deep framework self-analysis tool. Enumerates all components, collects health metrics, compares against prior introspect results stored in memory, identifies gaps and missing coverage, and produces a prioritized improvement roadmap. Read-only — never modifies files.
not rated 5 5mo ago C 49 tokens
original Apache-2.0
sprint
12Skill Claude Code
When user says "sprint", "self-improve sprint", "autonomous improvement", "launch improvement swarm", or wants to run a coordinated multi-agent improvement session.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
super-evolve
13Skill Claude CodeCodex
Ultimate self-evolution skill. Merges evolve + self-improve into one comprehensive meta-skill with external research, area focus, dry-run mode, and expanded memory mining.
not rated 5 5mo ago C 35 tokens
original Apache-2.0
super-health
14Skill Claude CodeCodex
Merged from: /health + /health-report + /status.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
Skill Claude CodeCodex
Skill "super-prof-optimize" from OZmasterAI/Torus-Framework, covering /super-prof-optimize — performance profiling & optimization, when to use, commands, steps and 1. memory check.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
browser
16Skill Claude CodeCodex
When user says "browser", "screenshot", "visual verify", "check the UI", or when implementing UI features that need visual proof of correctness.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
document
17Skill Claude CodeCodex
When the user says "document", "docs", "docstring", "README", "API docs", "architecture", "changelog", or wants to create, update, or fill gaps in project documentation.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
prp
18Skill Claude CodeCodex
When user says "prp", "create a prp", "blueprint", "structured plan", or wants a comprehensive implementation blueprint for a complex feature.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
refactor
19Skill Claude CodeCodex
When the user says "refactor", "extract", "rename", "simplify", "dead code", "cleanup", "restructure", or wants to reorganize code without changing behavior.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
report
20Skill Claude Code
When user says "report", "summary", "what did we do", "sprint report", "session summary", or wants a comprehensive overview of recent work.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
Skill Claude Code
Run a comprehensive security scan of the framework.
not rated 5 5mo ago C 12 tokens
original Apache-2.0
teach
22Skill Claude Code
When user says "teach", "explain framework", "onboard", "how does this work", "tutorial", "walk me through", or wants a structured overview of the Torus framework.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
chain
23Skill Claude CodeCodex
When the user says "chain", "pipeline", "then", "sequence", "workflow", "run all", or wants to compose multiple skills into a sequential execution pipeline.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
deploy
24Skill Claude CodeCodex
When the user says "deploy", "push to prod", "ship it", or wants to deploy to a server.
not rated 5 5mo ago A 0 tokens
original Apache-2.0
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: