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/agentlas-onegit 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/agentlas-one)<a href="https://agentmods.dev/commands/agentlas-ai/agentlas-os/agentlas-one"><img src="https://agentmods.dev/badge/commands/agentlas-ai/agentlas-os/agentlas-one.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 | $0.00016 | $0.00690 |
| Opus 5 | $0.00008 | $0.00345 |
| Sonnet 5 | $0.00003 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade B, and why
agentlas-one scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `install` configures `statusLine` in `~/.claude/settings.json`. If another How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/agentlas-one
Request: $ARGUMENTS
This command controls Agentlas One session persistence. Execute it without explaining it first.
Execution
Find the runner in this order and invoke it directly:
ONE=""
for c in \
"$HOME/.agentlas/runtime/current/bin/agentlas-one" \
"${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/bin/agentlas-one}"
do
if [ -n "$c" ] && [ -x "$c" ]; then ONE="$c"; break; fi
done
[ -n "$ONE" ] || { echo "Could not find the agentlas-one runner"; exit 1; }
# 인자는 **문자 그대로** 받는다. `"$ONE" $ARGUMENTS` 는 치환된 텍스트가 명령 위치에서
# 다시 해석돼 명령 주입이 된다(따옴표를 어떻게 붙여도 치환이 먼저라 막을 수 없다).
# 인용 구분자 heredoc 은 내용을 리터럴로 붙잡고, 그 뒤 **변수 확장**은 bash 가 재파싱하지
# 않으므로 낱말 나눔만 일어난다 — 두 낱말 이름도 그대로 전달된다.
AGENTLAS_ONE_ARGS="$(cat <<'AGENTLAS_ONE_ARGV_5F3A9C'
$ARGUMENTS
AGENTLAS_ONE_ARGV_5F3A9C
)"
set -f # 인자 안의 * 가 파일명으로 펼쳐지지 않게
# shellcheck disable=SC2086
"$ONE" $AGENTLAS_ONE_ARGS
one_status=$?
set +f
exit $one_status
Treat an empty argument list as status.
Rules
- Relay the script output verbatim. Do not summarize or embellish it.
- Immediately after
on, add only: "This takes effect next session." The current session does not gain the response prefix because directives load at session start. installconfiguresstatusLinein~/.claude/settings.json. If another status line exists, the script refuses to overwrite it. Show the existing command and ask how to proceed.offremoves the state file and theAGENTLAS-ONEblock from~/.claude/CLAUDE.md. Backups are created automatically.uninstall [--purge]removes every One footprint (hook entries in Claude/Codex/Cursor/ Antigravity, marker blocks, status line, state) after writing a timestamped tar.gz backup; it is idempotent and prints the restore command.--purgealso deletes the One workspace.status --runtimes [--json]prints the per-runtime support matrix (grade, install level, present/directive/hook on this machine, ACP transport, access path).- Never claim an action the script did not perform.
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.
- 5d ago First seen · 60 lines · 16 tokens per session scan B 2a103b3bf8df
agentlas-one is a command published in the GitHub repository agentlas-ai/Agentlas-OS (1,099 stars, last pushed 2d ago), licensed Apache-2.0. It adds 16 tokens to every session and 690 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
dashboard-list-models
List reachable models from the dashboard registry. Usage /dashboard:list-models [annotated].
dashboard-session-abort-all
Abort multiple running sessions (asks which). Usage /dashboard:session-abort-all.
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-tell
Send a prompt to another session. Usage /dashboard:session-tell.
dashboard-session-thinking
Set a session's thinking level. Usage /dashboard:session-thinking.