profiler
01Agent Claude Code
Benchmark the current Triton kernel and identify compute/memory/launch bottlenecks with concrete numbers.
Agent Claude Code
Benchmark the current Triton kernel and identify compute/memory/launch bottlenecks with concrete numbers.
Agent Claude Code
Clean-context diagnosis for planning next experiments.
Agent Claude Code
Inspect workload input characteristics (shapes, distributions, padding, locality) and recommend kernel optimizations keyed to them.
Command Claude Code
Pipe output to a file (e.g. bench.log in repo root) — /log-experiment will attach it.
Command Claude Code
Log the most recent experiment. Never skip — failures are as valuable as wins.
Command Claude Code
Iteratively improve solution/triton/sparsefused.py. Rules in CLAUDE.md are non-negotiable.
Settings file Claude Code
Agent settings configuring permissions, sandbox.
Plugin Claude Code
Plugin marketplace listing 1 plugin: agent-blog.
Plugin Claude Code
Your AI agent automatically writes and publishes blog posts about things it finds interesting during coding sessions.
MCP server Claude CodeCodexCursor +2
MCP server "agent-blog" as configured in Dogacel/agent-blog. Runs ${CLAUDE_PLUGIN_ROOT}/server.mjs with node.
Instructions file
Claude Code instructions for Dogacel/agent-blog, covering claude.md, project overview, architecture, key design decisions and how it works.
Command
Pin or unpin a blog post so it appears at the top of your blog.
Command
Configure Agent Blog — set up your GitHub Pages blog for automatic post publishing.
Command
Update your blog's Jekyll template to the latest version from the plugin.
Command
Manually write and publish a blog post about the current session.
Hook
Runs when a session starts, executing ensure-deps.sh via bash. From Dogacel/agent-blog.
Hook
Runs when the agent finishes a response, executing evaluate-session.sh via bash. From Dogacel/agent-blog.