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.
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.
git clone --depth 1 https://github.com/agentlas-ai/Agentlas-OSWrote 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.
[](https://agentmods.dev/commands/agentlas-ai/agentlas-os/hep-orch)<a href="https://agentmods.dev/commands/agentlas-ai/agentlas-os/hep-orch"><img src="https://agentmods.dev/badge/commands/agentlas-ai/agentlas-os/hep-orch/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.
<a href="https://agentmods.dev/commands/agentlas-ai/agentlas-os/hep-orch"><img src="https://agentmods.dev/badge/commands/agentlas-ai/agentlas-os/hep-orch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.01038 |
| Opus 5.5 | $0.00006 | $0.00415 |
| Sonnet 5.5 | $0.00003 | $0.00208 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
hep-orch 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 13d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- hep-orch.body — 94% identical, 7 lines differ
How it starts
The opening of the file, as written. The whole thing — 93 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.
Set or show which model runs the orchestrator and which runs the workers.
A role split only saves anything when the roles actually run on different models. Before this policy existed the allocator had nothing to read, so every worker inherited the orchestrator's frontier model and a five-worker fan-out billed five frontier runs to do work a cheap model finishes.
Read the request
- No arguments, or
show/status→ report the current policy and stop. - A request refused with
tier_clamped_by_cost_policyorrequested_exact_model_exceeds_cost_policyis this policy working: show the current policy, name the role whose ceiling refused it, and offer the exacthep-orchline that would allow the request. Change the policy only when the user says so, never to get a refused request through. clear/reset→ remove the policy and stop.- Otherwise the request is one or more
role=valuepairs.
role.effort=<level> sets the reasoning-effort ceiling for that role
(none, minimal, low, medium, high, xhigh, max); an empty value
removes it. Model and effort are independent, so
worker=<exact-model-id> worker.effort=xhigh pins a model and lets it think
as hard as that model supports.
role is orchestrator or worker. value is either a tier
(economy, balanced, frontier) — read as a ceiling — or an exact model id
from the live host inventory, read as a pin. An empty value drops that role
back to inherited.
Apply it
Run the host command and report exactly what it prints:
hep-orch <role=value> [<role=value>...]
Do not edit ~/.agentlas/one/model-policy.json by hand and do not export
AGENTLAS_MODEL_ALLOCATION_POLICY_JSON on the user's behalf. The environment
variable is the operator override and outranks this file; say so if it is set,
because the policy the user just wrote will not be the one in force.
Which hosts can actually act on it
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.
- 13d ago Changed · +11 lines 45ef18f13749
- 1mo ago First seen · 82 lines · 15 tokens per session scan A 6ce00ed6c90b
hep-orch is a command published in the GitHub repository agentlas-ai/Agentlas-OS (1,589 stars, last pushed 2d ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,038 once invoked, about $0.0001 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.
Other commands, from other repositories
dashboard-list-models
List reachable models from the dashboard registry. Usage /dashboard:list-models [annotated].
dashboard-flow-auto
Toggle autonomous mode for a session's flow. Usage /dashboard:flow-auto.
dashboard-server-tunnel-off
Disconnect the public tunnel. Usage /dashboard:server-tunnel-off.
dashboard-session-abort-all
Abort multiple running sessions (asks which). Usage /dashboard:session-abort-all.
dashboard-session-diff
Show file changes (git diff) for a session by id-prefix. Usage /dashboard:session-diff . Runs locally, no LLM.
dashboard-session-tell
Send a prompt to another session. Usage /dashboard:session-tell.