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.
npx agentmods add commands/agentlas-ai/agentlas-os/hep-updategit 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-update)<a href="https://agentmods.dev/commands/agentlas-ai/agentlas-os/hep-update"><img src="https://agentmods.dev/badge/commands/agentlas-ai/agentlas-os/hep-update.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00485 |
| Opus 5 | $0.00007 | $0.00243 |
| Sonnet 5 | $0.00003 | $0.00097 |
| Haiku 4.5 | $0.00001 | $0.00049 |
Grade A, and why
hep-update 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- hep-update.body — 92% identical, 5 lines differ
What it actually says
Update fallback: 자동 업데이트가 안 되면 hephaestus update를 한 번 실행하세요. 업데이트하지 않아도 현재 버전 명령은 그대로 동작합니다.
Update the installed Agentlas runtime and every host adapter on this machine.
Raw request: $ARGUMENTS
Updates normally happen on their own. This command exists for the moment they did not: a host still loading an old bundle, a command that should exist and does not, an adapter that never got re-registered after a release.
Run it
hephaestus update
Report the runtime version it moved from and to, and the per-host result it
prints. Say already up to date plainly when nothing moved — that is a valid
outcome, not a failure to try.
Then check the host actually picked it up
A new runtime does not mean the host is using it. Each host caches its own copy of the adapter, and one host lagging behind is the usual reason a command is missing after an update that reported success.
- Codex, Gemini/Antigravity, Grok, OpenCode: the updater rewrites their adapter directly, so the printed result is the answer.
- Claude Code installs plugins through its own marketplace. The updater refreshes
the source it points at, but Claude Code decides when to re-copy it into
~/.claude/plugins/cache/. If a command is still missing there, the plugin needs reinstalling from the Agentlas marketplace inside Claude Code — the runtime cannot force that copy.
If the user asks why a command is missing, name the layer that is behind rather than reporting a general failure: runtime version, host adapter, or the host's own plugin cache. Those fail separately and the fix differs for each.
Boundaries
Never edit files under ~/.agentlas/runtime/ by hand to make a command appear.
Two programs write that tree — the installer and the updater — so a hand-placed
file survives until the next update and then vanishes, which reads as a
regression that nobody can reproduce. Fix the source and update again.
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 · 50 lines · 14 tokens per session scan A 7931a9cef678
hep-update is a command published in the GitHub repository agentlas-ai/Agentlas-OS (1,101 stars, last pushed 2d ago), licensed Apache-2.0. It adds 14 tokens to every session and 485 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 2026-09-03.
Other commands, from other repositories
dashboard-list-models
List reachable models from the dashboard registry. Usage /dashboard:list-models [annotated].
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-flow-auto
Toggle autonomous mode for a session's flow. Usage /dashboard:flow-auto.
dashboard-session-info
Show every field of a session by id-prefix. Usage /dashboard:session-info . Runs locally, no LLM.