hep-hub

hep-hub is a command for Claude Code from agentlas-ai/Agentlas-OS. It costs 11 tokens per session (1,021 once invoked), scanned A, original, Apache-2.0.

A command for finding and preparing agents from the public Agentlas Hub, a shared catalogue of agents. It validates the selection and pins the exact package and release for execution.

In plain words
What is it for?
Use it to search the public Hub, select suitable agents, and prepare them for a project task.
Why use it?
It lets you use public agents while keeping their source, version, package contents, and permissions explicit.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to search the public Hub, select suitable agents, and prepare them for a project task.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/agentlas-ai/agentlas-os/hep-hub
About the project

Agentlas OS is a local-first system for creating, storing, borrowing, and running specialist AI agents and temporary agent teams through supported hosts and models. It serves people who want reusable agents that remain available across computers and model workspaces, and the catalogue contains its skills, commands, hooks, agents, instructions, plugin, and rule.

agentlas-ai/Agentlas-OS · 1,602 stars · on GitHub · agentlas.cloud

Install

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.

Clone the repo
git clone --depth 1 https://github.com/agentlas-ai/Agentlas-OS

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for hep-hub

README.md
[![agentmods](https://agentmods.dev/badge/commands/agentlas-ai/agentlas-os/hep-hub/github.svg)](https://agentmods.dev/commands/agentlas-ai/agentlas-os/hep-hub)
Your own site
<a href="https://agentmods.dev/commands/agentlas-ai/agentlas-os/hep-hub"><img src="https://agentmods.dev/badge/commands/agentlas-ai/agentlas-os/hep-hub/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for hep-hub

Your own site · 80×15
<a href="https://agentmods.dev/commands/agentlas-ai/agentlas-os/hep-hub"><img src="https://agentmods.dev/badge/commands/agentlas-ai/agentlas-os/hep-hub.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,021 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00011 $0.01021
Opus 5.5 $0.00004 $0.00408
Sonnet 5.5 $0.00002 $0.00204
Haiku 4.5 $0.00001 $0.00102

Measured 2d ago against content hash 47055c529b2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

hep-hub 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/commands/hep-hub.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update fallback: 자동 업데이트가 안 되면 hephaestus update를 한 번 실행하세요. 업데이트하지 않아도 현재 버전 명령은 그대로 동작합니다.

/hep-hub

Use the local Agentlas OS MCP server hephaestus-network and call the Workforce tools with exact sourceScope: "hub". This is public Hub only; it must not add registered Local or owner Cloud candidates.

First decide which of the two shapes this is

One named agent. The argument names a single agent — a slug, or an unmistakable name with no task described around it (ktx-book, use ktx-book). The user is asking to use that agent, not to have a team staffed, so do not make them sit through a staffing ceremony to get there:

  1. Find that exact agent with hephaestus_search. If nothing matches the name, say so and stop — never substitute a different agent for the one they asked for.
  2. Before preparing anything, tell them in plain words:
    • what the agent does, from its own card;
    • what it will need from them. Read prerequisites, envRequirements and mcpServers off the card. If all three are empty, say that the card declares nothing rather than implying it needs nothing — plenty of agents want a login they never wrote down, and the user should hear that before they start, not when the run stops to ask;
  3. Ask for whatever it needs, then prepare and run it, keeping the exact release pins below.

Skip the ceremony, never the pins: the prepared release must still carry source hub, the exact release, package hash, content digest, runtime bundle, permission policy, and context digest.

A job to be done. The argument describes work rather than naming an agent. Staff it:

  1. Author a redacted agentlas.workforce-work-order.v1; private project grounding stays on-host.
  2. Call workforce.search_candidates with {workOrder, sourceScope: "hub"} and keep the complete response as federationResult, including the Hub source receipt and the projected menu's selectionSessionId. Do not echo the projected menu back as federationResult — Core resolves the complete federation state locally from that session.
  3. Author the final agentlas.workforce-selection.v1 as the active host LLM, then call workforce.validate_selection with {workOrder, selection} and keep the response as federatedSelection. Revise on rejection; do not accept a deterministic picker or unrelated fallback.
  4. Call workforce.prepare_execution with {workOrder, selection, federatedSelection, projectDir}. Require every selected row to remain pinned to source hub, exact release, package hash, content digest, runtime bundle, permission policy, and context digest.
  5. Execute distinct planner/manager, worker, synthesis, and verifier calls with explicit artifact handoffs. Preserve packaged Team graphs.

Read the full file on GitHub · 88 lines

Changes

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.

  1. 2d ago Changed · +9 lines 47055c529b2e
  2. 23d ago Changed · -48 lines 382a619b4f3b
  3. 1mo ago Changed · +65 lines 0f67238caebf
  4. 1mo ago First seen · 62 lines · 11 tokens per session scan A f6aaa6389996

Subscribe to this mod's changes

hep-hub is a command published in the GitHub repository agentlas-ai/Agentlas-OS (1,602 stars, last pushed yesterday), licensed Apache-2.0. It adds 11 tokens to every session and 1,021 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-03.