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/agentlasgit 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)<a href="https://agentmods.dev/commands/agentlas-ai/agentlas-os/agentlas"><img src="https://agentmods.dev/badge/commands/agentlas-ai/agentlas-os/agentlas.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 | $0.00020 | $0.00487 |
| Opus 5 | $0.00010 | $0.00244 |
| Sonnet 5 | $0.00004 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
agentlas scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Update fallback: 자동 업데이트가 안 되면 hephaestus update를 한 번 실행하세요. 업데이트하지 않아도 현재 버전 명령은 그대로 동작합니다.
/agentlas
Single entry point for every Agentlas command. /agentlas <command> <request>
does exactly what /hep-<command> <request> does. Both names stay supported and
neither is deprecated — this command only spells the product name out loud.
Read the first whitespace-delimited token of the argument as COMMAND, and treat everything after it as REQUEST, verbatim.
COMMAND is one of:
network, build, storm, call, search, hub, local, cloud,
browser, connect, upload, graph, one, login, orch, update.
If COMMAND is missing, or is not in that list, print the list, ask which one the user meant, and stop. Never guess a command, and never improvise a workflow from memory.
Otherwise resolve the canonical workflow file for that command:
cmd="$COMMAND"
if [[ "$cmd" == "one" || "$cmd" == "agentlas-one" ]]; then
target="agentlas-one.md"
elif [[ "$cmd" == "graph" ]]; then
target="hep-graph.md"
else
target="hep-${cmd}.md"
fi
ls "$HOME/.agentlas/runtime/current/host_adapters"/*/prompts/"$target" "$HOME/.agentlas/runtime/current/host_adapters"/*/plugins/*/commands/"$target" 2>/dev/null | head -1
Read the file that resolves and follow its instructions exactly, using REQUEST as the request. That file is the authority. The table above only chooses which file to read; it adds no behaviour of its own, so the two spellings can never drift apart.
If nothing resolves, report that the Agentlas runtime is missing or incomplete
and suggest hephaestus update. Do not substitute a remembered version of the
workflow.
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.
- 3d ago First seen · 47 lines · 20 tokens per session scan A cb2660517f5e
agentlas is a command published in the GitHub repository agentlas-ai/Agentlas-OS (1,099 stars, last pushed yesterday), licensed Apache-2.0. It adds 20 tokens to every session and 487 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 2026-08-30.
Other commands, from other repositories
dashboard-flow-auto
Toggle autonomous mode for a session's flow. Usage /dashboard:flow-auto.
dashboard-git-branches
List git branches for the current dir (current marked ). Runs locally, no LLM.
setup
Full onboarding for a new project — runs /doctor diagnostics, then injects the CLAUDE.md template + nav-ref instrumentation + Zustand store exposure so the plugin works without the user having to read documentation.
run-action
Execute a learned Maestro flow ("action") by name with optional -e KEY=VALUE parameters. Looks the flow up via packages/rn-dev-agent-core/dist/learned-actions.js (same inventory as /rn-dev-agent:list-learned-actions), then replays it via cdprunaction — auto-repair-aware orchestration with structured RunRecords (GH.
send-feedback
Send feedback or report a bug for the rn-dev-agent plugin. Collects sanitized environment context and creates a GitHub issue. No sensitive data (paths, secrets, PII) is transmitted.
list-learned-actions
List persisted "learned actions" — feedback memories, Maestro flows, UI skeletons, and plugin commands that should be consulted before composing new device primitives. Wraps packages/rn-dev-agent-core/dist/learned-actions.js for programmatic discovery.