Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/vladolaru/claude-code-plugins/grokgit clone --depth 1 https://github.com/vladolaru/claude-code-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00017 | $0.01270 |
| Opus 5 | $0.00009 | $0.00635 |
| Sonnet 5 | $0.00003 | $0.00254 |
| Haiku 4.5 | $0.00002 | $0.00127 |
Grade A, and why
grok scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dex:grok
Deeply understand the current conversation, classify the knowledge, and delegate to the right capture flow. This command asks one question, then hands off — keep it fast.
digraph grok_routing {
"Start" [shape=doublecircle];
"Agent behavior topic?" [shape=diamond];
"Delegate to /dex:sharpen" [shape=doublecircle];
"Knowledge signals found?" [shape=diamond];
"Nothing to capture" [shape=doublecircle];
"Classify type" [shape=box];
"Confirm with user" [shape=box];
"User selected?" [shape=diamond];
"Reusability signals?" [shape=diamond];
"Upgrade to pattern?" [shape=diamond];
"Execute /dex:learn" [shape=doublecircle];
"Execute /dex:pattern" [shape=doublecircle];
"Execute /dex:research" [shape=doublecircle];
"Execute decision flow" [shape=doublecircle];
"Start" -> "Agent behavior topic?";
"Agent behavior topic?" -> "Delegate to /dex:sharpen" [label="yes"];
"Agent behavior topic?" -> "Knowledge signals found?" [label="no"];
"Knowledge signals found?" -> "Nothing to capture" [label="none"];
"Knowledge signals found?" -> "Classify type" [label="found"];
"Classify type" -> "Confirm with user";
"Confirm with user" -> "User selected?";
"User selected?" -> "Reusability signals?" [label="Learning"];
"User selected?" -> "Execute /dex:pattern" [label="Pattern"];
"User selected?" -> "Execute decision flow" [label="Decision"];
"User selected?" -> "Execute /dex:research" [label="Research"];
"Reusability signals?" -> "Upgrade to pattern?" [label="yes"];
"Reusability signals?" -> "Execute /dex:learn" [label="no"];
"Upgrade to pattern?" -> "Execute /dex:pattern" [label="yes"];
"Upgrade to pattern?" -> "Execute /dex:learn" [label="no (default)"];
}
Step 1: Classify
If the conversation is primarily about agent behavior (wrong tools, inefficient discovery, missed shortcuts), route to /dex:sharpen instead. Grok captures domain knowledge; sharpen captures operational knowledge.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 111 lines · 17 tokens per session scan A 040e228d6fba
grok is a command published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed 4d ago), licensed MIT. It adds 17 tokens to every session and 1,270 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
component
Scaffold a new React component grounded in the paper-mono primitives. Requires explicit kind or a nearest-existing-component match. No empty divs, no speculative scaffolding.
memory-store
Store an insight, decision, or pattern to memory.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".