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 hep-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/hep-upload)<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-os/hep-upload"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-os/hep-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 52 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 | $0.00015 | $0.01065 |
| Opus 5 | $0.00008 | $0.00532 |
| Sonnet 5 | $0.00003 | $0.00213 |
| Haiku 4.5 | $0.00002 | $0.00106 |
Grade A, and why
hep-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 4d 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 — 92 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.
Hephaestus Upload
Legacy compatibility only: this custom prompt applies to Codex 0.116 and
earlier. Codex 0.117 and later use the installed $hephaestus-upload skill.
Raw arguments: everything the user typed after /skill:hep-upload.
Always ask the destination question before doing anything else, even if the arguments already say upload, publish, add, Cloud, Hub, or a target folder:
Cloud에 업로드 할까요? 다른사람들이 볼 수 없어요.
Upload to Cloud? Other people cannot see it.
Agentlas Hub에 업로드 할까요? 다른 사람들이 빌려 쓸 수 있어요.
Upload to Agentlas Hub? Other people can borrow it.
Do not package, publish, register, add-source, reindex, or call an upload API until the user answers Cloud or Agentlas Hub.
If the destination is Agentlas Hub, ask what it should charge before uploading. Skip this for Cloud/private-link — a private save is not listed and nobody can hire it.
값을 정하시겠어요? 비워 두면 그 항목은 팔지 않습니다.
Set a price? Leave one out and that kind is simply not sold.
빌리기 / Rent 워크오더 1건 · 24시간 1-100 크레딧
인제스트 / Ingest 프로젝트 1개 · 하루 1-2000 크레딧
포크 / Fork 사본 1개 · 1회 1 크레딧 이상
전부 비워 두면 무료로 불립니다. 나중에 agentlas.cloud 수익 페이지에서도 정할 수 있습니다.
Leave them all blank and it stays free to call — you can price it later on the web.
Blank is NOT zero: leave the flag out entirely. Never pass 0, never invent a
number, and treat "all three blank" as a complete answer — the agent is then
callable for free, which is a supported state. Pass what they answered as
--rent-credits N, --ingest-credits N, --fork-credits N.
After the user chooses a destination, run the app-host auto-update preflight
from the hephaestus-network skill inside Codex, then resolve RUNNER at
~/.agentlas/runtime/current/bin/hephaestus or ./bin/hephaestus. Do not ask
the user to open a separate terminal. Use that resolved Hephaestus runtime gate;
it must work for any local package folder and must not assume any private
checkout.
Use one explicit hep-upload command. Never run package and then publish,
because that packages twice and can submit bytes different from the review:
- Cloud:
"$RUNNER" hep-upload <agent-folder> --visibility private-link - Agentlas Hub:
"$RUNNER" hep-upload <agent-folder> --visibility marketplace [--rent-credits N] [--ingest-credits N] [--fork-credits N]
All security and content findings are advisory. Never instruct the user to
block, abort, or postpone upload because of a finding. Continue with safe bytes:
omit affected source items with omission receipts, or attach an engine-gap
receipt when the engine cannot safely represent or repair an item, then upload
the remaining package. Keep the findings and receipts visible.
For a preview, add --dry-run, retain manifest.packageHash and
uploadReceipt.receipt, then append --expected-package-hash <manifest.packageHash> --expected-upload-receipt <uploadReceipt.receipt> to the
later one-shot publish. Stop on any hash or receipt mismatch. On
overwrite_confirmation_required, show the
exact Cloud ID and ask for approval before appending
--overwrite-cloud-id <exact-cloud-id>. Preserve exact auth/credit/ownership
errors and never switch destinations. Report success only when the response
attests slug, visibility, package hash, release ID/version, and content digest.
If the destination is answered but the target folder is ambiguous, ask for the exact agent folder before running any upload.
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.
- 4d ago First seen · 92 lines · 15 tokens per session scan A ff387989f3cc
hep-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 15 tokens to every session and 1,065 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 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.