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.
git 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-goal)<a href="https://agentmods.dev/commands/agentlas-ai/agentlas-os/hep-goal"><img src="https://agentmods.dev/badge/commands/agentlas-ai/agentlas-os/hep-goal/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/agentlas-ai/agentlas-os/hep-goal"><img src="https://agentmods.dev/badge/commands/agentlas-ai/agentlas-os/hep-goal.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00018 | $0.00675 |
| Opus 5.5 | $0.00007 | $0.00270 |
| Sonnet 5.5 | $0.00004 | $0.00135 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
hep-goal 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-goal.body — 86% identical, 5 lines differ
How it starts
The opening of the file, as written. The whole thing — 36 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.
/hep-goal
Adds a plan tree to the host's own /goal: a shape for the goal, strategies and tactics, and a KPI reading that says whether the plan is working. The host goal still decides when the work is done; this only keeps the plan and the numbers honest.
Pick the shape first
Run hep-goal schema once and follow the field lists it prints. Then choose:
- single_tactic (short work with one clear check: a bug, a test, a file): store it with
hep-goal startand stop using this command. From here it is exactly the host/goal. - tactic_list (several known steps): store the steps with
done_whenfor each. - mission_tree (long work with a number the owner named: followers, revenue, signups): store the objective, the diagnosis of the biggest obstacle, the key results, strategies and tactics.
A target is only a number the owner wrote in the goal text, and an owner boundary needs a quote from it. The store refuses anything else, so do not invent them.
Run it
hep-goal start --goal-text "<the owner's exact text>" --json <draft>stores the plan and prints the goal id.- Before each turn,
hep-goal context --goal-id <id>prints a short block (empty means say nothing about the plan). Work the tactics it names. - When you read a KPI, record it:
hep-goal kpi-sample --goal-id <id>with the value, the time, the source and a short evidence quote. A second reading from a different tool (reobserved) makes it verified. Without a source and evidence it is refused. - When the context says a review is due,
hep-goal review --goal-id <id>shows the table and the strategies. Answer with oneshift(hold,pivot,double_downorescalate_owner) that cites sample ids. - If it reports an owner hold, tell the owner the three numbers it names (current, needed per day, observed per day) and wait. Do not re-plan until they answer; then
hep-goal owner-answer.
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 · 36 lines · 18 tokens per session scan A 9fb1715a3b40
hep-goal is a command published in the GitHub repository agentlas-ai/Agentlas-OS (1,602 stars, last pushed yesterday), licensed Apache-2.0. It adds 18 tokens to every session and 675 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-17.
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-diff
Show file changes (git diff) for a session by id-prefix. Usage /dashboard:session-diff . Runs locally, no LLM.
dashboard-session-rename
Rename a session. Usage /dashboard:session-rename.