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 instructions/agentlas-ai/agentlas-os/gemini-mdgit 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/instructions/agentlas-ai/agentlas-os/gemini-md)<a href="https://agentmods.dev/instructions/agentlas-ai/agentlas-os/gemini-md"><img src="https://agentmods.dev/badge/instructions/agentlas-ai/agentlas-os/gemini-md.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 | $0.00693 | $0.00693 |
| Opus 5 | $0.00347 | $0.00347 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
Agentlas-OS GEMINI.md 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini CLI Adapter
This is a thin Gemini CLI adapter for the Agentlas Core Engine Meta-Agent Team.
AGENTS.md is the canonical source of truth.
Public Release Boundary
The Public Release Allowlist (Hard Rule) in AGENTS.md is mandatory.
For public GitHub work, stage only end-user install/runtime files and public
README/LICENSE/CHANGELOG material. Never stage internal docs, research,
benchmarks, tests or fixtures, logs/results, signing or credential material,
environment files, private paths/memory, or unrelated local work. Verify the
staged archive, not the dirty working tree.
Google Antigravity shares the ~/.gemini/ home with the Gemini CLI and also
auto-loads this file and AGENTS.md. Its /hep-build,
/hep-network, /hep-local, /hep-cloud, and /hep-hub slash commands ship as
Antigravity workflows under antigravity/ (see antigravity/README.md).
Startup
- Read
AGENTS.md. - Read
.agents/agentlas-core-engine-meta-agent/agent.md. - Read
.agentlas/mode-map.json. - Use
.agents/skills/mode-classification/SKILL.mdto choose the mode. - If missing details would change files, adapters, or public/private boundary,
use
.agents/skills/clarify-question-loop/SKILL.md. - Route to one core team member:
10-single-agent-builder;20-multi-agent-team-builder;30-agentlas-packager;40-session-agent-builder.
- Use
.agents/skills/agentlas-auto-activation/SKILL.mdwhen local project continuity or.agentlasactivation is part of the output. - Use
.agentlas/memory-map.jsonfor memory routing. - Use
.agentlas/global-commands.jsonfor generated command routing and final user handoff.
Default Behavior
Create or package portable Markdown-first Agentlas agents and teams with Codex, Claude Code, Gemini, Antigravity, Cursor, and AGENTS.md adapters.
Global Command
This package exposes /hep-build, /hep-network, /hep-local,
/hep-cloud, and /hep-hub for Gemini CLI through
gemini/extension/commands/hep-*.toml, with fallback user commands at
.gemini/commands/hep-*.toml. For Antigravity the same commands ship as
workflows at antigravity/workflows/hep-*.md (global install target
~/.gemini/antigravity/global_workflows/hep-*.md; project fallback
.agents/workflows/hep-*.md). Generated agents must receive their own
Gemini extension command, Antigravity workflow, and a matching
.agentlas/global-commands.json entry.
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 · 61 lines · 693 tokens per session scan A c8765622d8c1
Agentlas-OS GEMINI.md is an instructions file published in the GitHub repository agentlas-ai/Agentlas-OS (1,101 stars, last pushed 2d ago), licensed Apache-2.0. It adds 693 tokens to every session, about $0.0035 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 instructions, from other repositories
pi-agent-dashboard AGENTS.md
AGENTS.md instructions for BlackBeltTechnology/pi-agent-dashboard, covering pi dashboard, docs-first gate — kb before grep (per-turn doctrine), code instructions (per-turn doctrine), investigation protocol — index first and documentation update protocol.
LeAgent AGENTS.md
Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).
a2a-editor CLAUDE.md
Claude Code instructions for open-resource-discovery/a2a-editor, covering claude.md, project overview, commands, development and building.
rn-dev-agent AGENTS.md
AGENTS.md instructions for Lykhoyda/rn-dev-agent, covering repository guide for agents, repository map, editing rules, architecture rules and supported node runtimes.
nui CLAUDE.md
Claude Code instructions for plmbr/nui, covering claude.md, commands, backend (go), frontend (run from ui/) and full production build.
pi-agent-dashboard CLAUDE.md
Claude Code instructions for BlackBeltTechnology/pi-agent-dashboard, a project described as: Real-time web dashboard for pi coding-agent sessions. Multi-session view, live chat mirroring, integrated terminal, diff viewer, pi-flows execution, and mobile-first remote control via mDNS or zrok tunnel. Coexists with pi's…