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/quangdang46/livekit_agent_simulator/agents-mdgit clone --depth 1 https://github.com/quangdang46/livekit_agent_simulatorWrote 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/quangdang46/livekit_agent_simulator/agents-md)<a href="https://agentmods.dev/instructions/quangdang46/livekit_agent_simulator/agents-md"><img src="https://agentmods.dev/badge/instructions/quangdang46/livekit_agent_simulator/agents-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 | $0.02396 | $0.02396 |
| Opus 5 | $0.01198 | $0.01198 |
| Sonnet 5 | $0.00479 | $0.00479 |
| Haiku 4.5 | $0.00240 | $0.00240 |
Grade A, and why
livekit_agent_simulator AGENTS.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 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — livekit-agent-simulator
Standalone Python package: MCP + lks CLI. Dials any LiveKit voice agent using
.agent-sim/ in a target repo (config, scenarios, reports). The agent under test is a
black box — we never import or edit target application code unless the user asks.
Boundary
| In scope | Out of scope |
|---|---|
src/livekit_agent_simulator/ |
Target agent source, consumer app code, DB, env |
| Scenario JSONL, Script timing, observer, reports | Parsing project-specific dispatch keys in core |
| LiveKit room + dispatch + sim caller | Agent model stack, tools, business rules |
Opaque dispatch: config.yaml → livekit.dispatch_metadata and scenario Dispatch.metadata
are passed through as JSON strings. Core Python must not interpret consumer-specific keys.
Target repo = path passed as project_root / --root. Consumer wiring examples live in
docs/portability.md — load that file only when the task is target .agent-sim/ setup, not
for package bugs or features.
Product rule: generic core, not fit-to-one-repo
This package ships tools + core capabilities that every LiveKit agent repo can use. It is not a glue layer for one consumer (worker, dashboard, language, brand).
| Do | Do not |
|---|---|
| Build features every target can enable via config / scenario / plugins | Hardcode language, timezone, agent IDs, data topics, or business strings in src/ |
Give extension points (opaque dispatch, observe.*, Script, verify plugins) so users customize |
Parse or special-case consumer keys in core Python |
Put project-specific wiring only in that target’s .agent-sim/ |
Change package defaults to match the last repo we smoked |
Prefer one clear API (record_audio, not aliases) |
Keep “legacy” flags, dual names, or compatibility shims “just in case” |
Customization belongs to the user. We ship knobs and contracts; the target fills
config.yaml, scenarios, plugins. If something only works for one monorepo, it is
wrong for core — fix the design or keep it out of src/.
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 · 197 lines · 2,396 tokens per session scan A 90382499381a
livekit_agent_simulator AGENTS.md is an instructions file published in the GitHub repository quangdang46/livekit_agent_simulator (5 stars, last pushed 13d ago), licensed MIT. It adds 2,396 tokens to every session, about $0.0120 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 2026-08-31.
Other instructions, from other repositories
AionUi AGENTS.md
AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
botmux CLAUDE.md
Claude Code instructions for deepcoldy/botmux, covering botmux, 构建 & 运行, bun 开发链路, worktree 的 nodemodules：共享还是独立（改前必读） and 编译态（单文件二进制）注意.
codedb AGENTS.md
AGENTS.md instructions for justrach/codedb, covering codedb agent guidelines, what codedb is (and isn't), review guidelines, pre-merge verification and security-sensitive areas.
SearChat CLAUDE.md
Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.
happier CLAUDE.md
Claude Code instructions for happier-dev/happier, covering claude code and typescript commands.