dedupe
01Command Claude Code
Find duplicate GitHub issues.
82k
+22 today A 5 tokens
quiz-result
02Command
Analyze quiz progress over time and the weak areas to study next, from a KMS scores log.
1.2k 2d ago A 24 tokens
original Apache-2.0
quiz
03Command
Generate and play an interactive study quiz from a KMS knowledge base, URL, file, or topic — and record the score back into the KMS.
1.2k 2d ago A 32 tokens
original Apache-2.0
doctor
04Command Claude Code
Health-check the harness: kernel load, MCP wiring, memory backend, host adapter.
624
+1 yesterday A 17 tokens
original MIT
review-diff
05Command Claude Code
Review the current working diff for correctness, security, and reuse.
624
+1 yesterday A 13 tokens
original MIT
Command
Show LACP hardening status — active hooks, context mode, eval checkpoint state, recent quality gate decisions.
300 11d ago A 25 tokens
original MIT
Command Claude Code
Launch the unattended / overnight AMK autoresearch driver on $ARGUMENTS (model [gpu] [minutes|iters]).
135 2mo ago A 25 tokens
original MIT
amk-compile
08Command Claude Code
One-shot compile + verify a model into a CUDA megakernel via amk compile on $ARGUMENTS (model [gpu]).
135 2mo ago A 29 tokens
original MIT
amk-optimize
09Command Claude Code
Drive an interactive AMK propose -> eval -> keep/revert megakernel schedule session on $ARGUMENTS (model [gpu]).
135 2mo ago A 27 tokens
original MIT
autonomous
10jcarlosrodicio/opencode-agent-orchestration-kit
Command
Run a bounded, locally verifiable autonomous engineering workflow.
105 3d ago A 11 tokens
original Apache-2.0
evolve
11jcarlosrodicio/opencode-agent-orchestration-kit
Command
Run an optional AHE iteration to evaluate or improve this OpenCode harness with evidence and attribution.
105 3d ago A 19 tokens
original Apache-2.0
loop
12jcarlosrodicio/opencode-agent-orchestration-kit
Command
Design and run a bounded engineering loop with durable state, human approval, and independent verification.
105 3d ago A 18 tokens
original Apache-2.0
status
13Command
Show test-plugin status.
75 4d ago A 6 tokens
original Apache-2.0
goal
14Command
Extract a full task specification up front (goal, constraints, definition of done), then execute — the primary documented lever for Opus 4.8 long-horizon quality.
38 2mo ago A 35 tokens
original MIT
retro
15Command
Write this session's lessons into the project's lessons/ directory using the memory-discipline format.
38 2mo ago A 18 tokens
original MIT
verify
16Command
Spawn a fresh-context verifier subagent to check completed work against its specification before trusting it.
38 2mo ago A 18 tokens
original MIT
Command
Explore an agent and design a tailored memory system.
23 2mo ago A 13 tokens
Command
Implement a memory system from an existing design document.
23 2mo ago A 14 tokens
Command
Run the Critic-Improver refine loop until completion.
23 2mo ago A 16 tokens
_prime-rails
20Command Claude Code
These rails apply to every session-runner session (PM, Dev, and Teammate roles). Each role prime instructs you to read and apply this file before acting.
22 4d ago A 0 tokens
GPL-3.0
Command Claude Code
Prime the PM (project manager) persona for the headless session runner. Receives the user message as $ARGUMENTS.
22 4d ago A 26 tokens
GPL-3.0
Command Claude Code
Prime the Teammate persona for the headless session runner. Receives the user message as $ARGUMENTS.
22 4d ago A 24 tokens
GPL-3.0
Command Claude Code
Brownfield change workflow — propose, apply, verify, archive (OpenSpec-aligned).
18 11d ago A 18 tokens
original MIT
Command Claude Code
Research and map a domain/industry/technology into a structured Markdown database.
18 11d ago A 14 tokens
original MIT