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 agents/f/poke-gate/creatinggit clone --depth 1 https://github.com/f/poke-gateWhat 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 | $0.00000 | $0.00960 |
| Opus 5 | $0.00000 | $0.00480 |
| Sonnet 5 | $0.00000 | $0.00192 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
creating 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 yesterday.
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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating Agents
There are two ways to create agents: ask Poke to generate one (recommended) or write one manually.
Generate with AI
The fastest way — describe what you want and Poke writes the code for you:
npx poke-gate agent create --prompt "monitor disk space and alert when above 85%"
Or interactively:
npx poke-gate agent create
> Describe the agent you want to create:
> track my git repos for uncommitted changes
Poke generates the complete agent code and saves it directly to your agents folder using the write_file tool (requires poke-gate to be running). You'll get a confirmation in your chat when it's done.
You can also generate agents from the macOS app — open Agents, click "Generate with AI", type your description, and Poke does the rest.
::: tip Poke may ask clarifying questions before writing the code. Just reply in your chat and it will proceed. :::
Write manually
If you prefer to write agents yourself, follow the steps below.
Step 1: Create the file
Agents live in ~/.config/poke-gate/agents/. Create a file with the naming convention name.interval.js:
touch ~/.config/poke-gate/agents/hello.1h.js
This creates an agent called "hello" that runs every hour.
Step 2: Add frontmatter
Start with the frontmatter block. This is optional but recommended — it's displayed in the macOS Agents editor.
/**
* @agent hello
* @name Hello World
* @description Sends a greeting to Poke every hour.
* @interval 1h
* @author you
*/
Step 3: Write your logic
Agents are standard Node.js ESM scripts. They can import the Poke SDK and any globally installed packages.
/**
* @agent hello
* @name Hello World
* @description Sends a greeting to Poke every hour.
* @interval 1h
*/
import { Poke, getToken } from "poke";
const token = getToken();
if (!token) {
console.error("Not signed in. Run: npx poke login");
process.exit(1);
}
const poke = new Poke({ apiKey: token });
await poke.sendMessage("Hello! This is an automated message from my Hello agent.");
console.log("Sent greeting to Poke.");
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.
- yesterday First seen · 161 lines · 0 tokens per session scan A 0560a548748c
creating is an agent published in the GitHub repository f/poke-gate (81 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 960 tokens. 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 2026-08-30.
Other agents, from other repositories
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理;适合在授权范围内做大范围情报汇总,并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…