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 skills add agentlas-ai/Agentlas-OS --skill hephaestus-uploadgit 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/skills/agentlas-ai/agentlas-os/hephaestus-upload)<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-os/hephaestus-upload"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-os/hephaestus-upload.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 73 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00067 | $0.01671 |
| Opus 5 | $0.00034 | $0.00835 |
| Sonnet 5 | $0.00013 | $0.00334 |
| Haiku 4.5 | $0.00007 | $0.00167 |
Grade A, and why
hephaestus-upload 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 8d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hephaestus Upload (Cloud or Agentlas Hub)
Publish a finished Agentlas package. This is a WRITE surface: a Hub upload is public and other people can borrow it, so the destination question comes before any packaging or API call.
Upload is deliberately NOT folded into /hep-network. Network staffs a roster
(a read), upload publishes an artifact (a write that is hard to take back);
merging them would let "find me an agent" end in an accidental publish.
1. Ask the destination first — always
Ask this before anything else, even when the arguments already say upload, publish, add, Cloud, Hub, or name a target folder:
Cloud에 업로드 할까요? 다른사람들이 볼 수 없어요.
Upload to Cloud? Other people cannot see it.
Agentlas Hub에 업로드 할까요? 다른 사람들이 빌려 쓸 수 있어요.
Upload to Agentlas Hub? Other people can borrow it.
Do not package, publish, register, add-source, reindex, or call any upload API until the user answers Cloud or Agentlas Hub. If the destination is answered but the target folder is ambiguous, ask for the exact agent folder before running anything.
2. Ask the price — Agentlas Hub only
Ask this only when the destination was Agentlas Hub. Skip it entirely for Cloud/private-link: a private save is not listed and nobody can hire it, so there is nothing for a price to apply to.
값을 정하시겠어요? 비워 두면 그 항목은 팔지 않습니다.
Set a price? Leave one out and that kind is simply not sold.
빌리기 / Rent 워크오더 1건 · 24시간 1-100 크레딧
인제스트 / Ingest 프로젝트 1개 · 하루 1-2000 크레딧
포크 / Fork 사본 1개 · 1회 1 크레딧 이상
전부 비워 두면 무료로 불립니다. 나중에 agentlas.cloud 수익 페이지에서도 정할 수 있습니다.
Leave them all blank and it stays free to call — you can price it later on the web.
Why the three ceilings differ: a rental is a 24-hour lease a buyer opens many of, so the same job must not cost more for being split into more pieces; ingest is a day of a whole project, worth twenty times that; a fork is a copy sold once, with no repeat for a ceiling to protect against.
Rules:
- Blank is not zero. An unanswered kind is left out of the command, meaning
"not sold". Never pass
0— the server refuses it, and a stored 0 cannot be told apart from a field nobody filled in. - All three blank is a valid answer. Publish with no price flag at all. The agent is callable for free, which is where every agent published before pricing existed already lives. Do not push and do not re-ask.
- Do not invent a number. No answer means the flag is omitted.
- The server enforces the ceilings and returns the bound when it refuses. Report the actual limit, never a bare "it failed".
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.
- 8d ago First seen · 145 lines · 67 tokens per session scan A 40993f04de5f
hephaestus-upload is a skill published in the GitHub repository agentlas-ai/Agentlas-OS (1,103 stars, last pushed yesterday), licensed Apache-2.0. It adds 67 tokens to every session and 1,671 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
agentfield-use
Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …
agent-optimization
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
quality-loop
Use this workflow recipe when a draft, plan, proposal, or other deliverable should be independently reviewed and revised until it satisfies explicit quality criteria.
cli-skill-design
Design a co CLI surface and its SKILL.md together so an agent can drive it without guessing — every command ends by naming the next one, --help lists everything, and every failure says what to run instead. Use when adding a new CLI command group, writing or rewriting a SKILL.md for one, or auditing an existing one.
plan_route
Plan a route and return distance + ETA (schema + deterministic result).
update-setup
A one-time setup wizard for creating a personalised upgrade guide for a workspace. It checks for an existing guide, identifies the current version and installation clues, and requires confirmation of the installation method before writing a new guide.