Command Claude Code
Help me create a new release of a memory-hub component.
not rated 20 today A 0 tokens
20Stars on the repository
25Mods indexed here, across every type
todayLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied
create-tools
02Command Claude Code
Generate and implement tools from TOOLSPLAN.md using parallel subagents.
not rated 20 today B 13 tokens
deploy-mcp
03Command Claude Code
Deploy MCP server to OpenShift with pre-flight checks.
not rated 20 today B 10 tokens
ds
04Command Claude Code
Break down complex tasks into sub-problems, solve them efficiently, then aggregate results.
not rated 20 today A 16 tokens
Command Claude Code
Test tool ergonomics by role-playing as the consuming agent.
not rated 20 today A 11 tokens
Command Claude Code
Implement an MCP component (tool/resource/prompt/middleware) efficiently.
not rated 20 today A 13 tokens
Command Claude Code
Use this skill for ALL issue operations. Never create issues manually without using the skill -- it enforces our conventions.
not rated 20 today A 23 tokens
Command Claude Code
Manage MemoryHub graph, curation, and project operations via the CLI. This skill wraps cold-path operations that are used less frequently than search/write/read.
not rated 20 today A 0 tokens
plan-tools
09Command Claude Code
Plan MCP tools by reading Anthropic's guidance and creating TOOLSPLAN.md.
not rated 20 today A 15 tokens
update-docs
10Command Claude Code
Update README.md and ARCHITECTURE.md based on implemented components.
not rated 20 today A 13 tokens
Command Claude Code
Create an AI agent system prompt based on implemented tools.
not rated 20 today A 10 tokens
add-hook
12Command Claude Code
Add a lifecycle hook to the agent. Hooks are shell commands that fire at specific points in the agent lifecycle, configured via YAML files in hooks/.
not rated 20 today A 0 tokens
add-memory
13Command Claude Code
Wire MemoryHub integration into the agent for persistent memory across runs. This command configures both the SDK path (self.memory for agent code) and the MCP path (MemoryHub tools for the LLM).
not rated 20 today A 0 tokens
add-skill
14Command Claude Code
Add a new skill directory following the agentskills.io specification. Skills are capabilities that are too large to keep in context all the time — they load on demand via progressive disclosure.
not rated 20 today A 0 tokens
add-tool
15Command Claude Code
Add a new tool to the agent with the @tool decorator. This command walks through designing the tool, generating the code, and verifying it integrates with the tool registry.
not rated 20 today A 0 tokens
create-agent
16Command Claude Code
Scaffold the agent implementation from an approved AGENTPLAN.md. This command generates the agent subclass, tools, prompts, skills, rules, and configuration based on the plan produced by /plan-agent.
not rated 20 today A 0 tokens
deploy-agent
17Command Claude Code
Build the container image and deploy the agent to OpenShift. This command handles the full path from source code to a running pod.
not rated 20 today B 0 tokens
Command Claude Code
Test agent behavior through structured role-play scenarios. This command validates that the agent responds correctly, uses tools appropriately, and handles edge cases gracefully — all without deploying to OpenShift.
not rated 20 today A 0 tokens
plan-agent
19Command Claude Code
Design an agent before writing any code. This command produces an AGENTPLAN.md file that captures what the agent does, what tools it needs, what prompts it uses, and how it behaves. The plan is reviewed and approved before any implementation begins.
not rated 20 today A 0 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: