Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/yuanchuan/aivonpx agentmods add commands/yuanchuan/aivo/aivo_guideWrote 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/yuanchuan/aivo/aivo_guide)<a href="https://agentmods.dev/commands/yuanchuan/aivo/aivo_guide"><img src="https://agentmods.dev/badge/commands/yuanchuan/aivo/aivo_guide/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/yuanchuan/aivo/aivo_guide"><img src="https://agentmods.dev/badge/commands/yuanchuan/aivo/aivo_guide.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 | $0.00000 | $0.05374 |
| Opus 5.5 | $0.00000 | $0.02150 |
| Sonnet 5.5 | $0.00000 | $0.01075 |
| Haiku 4.5 | $0.00000 | $0.00537 |
Grade A, and why
aivo_guide 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 16d 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 — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aivo — complete usage guide
aivo is a CLI that connects your existing coding agents (and its own built-in agent) to whatever
model you want, with local encrypted API-key management. Config lives in ~/.config/aivo/ — API
keys are AES-256-GCM encrypted in config.json.
Machine-readable command structure: aivo --help-json. Per-command help: aivo <command> --help.
Global usage
aivo <command> [options]
Global options: -h/--help, --help-json (full command tree as JSON), -v/--version.
Get started:
aivo code # built-in agent
aivo claude # launch Claude Code (same for codex/gemini/…)
aivo run # pick a tool
Shortcuts (bare forms that expand to a subcommand):
| Shortcut | Expands to | Notes |
|---|---|---|
aivo <tool> |
aivo run <tool> |
claude, codex, gemini, opencode, pi, grok, … |
aivo <prompt> |
aivo code -p <prompt> |
quoted text with a space, or piped stdin; a single lowercase word is a command (aivo hello → aivo -p hello / aivo code). TUI: aivo code "<prompt>" |
aivo hf:… / aivo https://… |
aivo code <ref> |
open code on a local HuggingFace GGUF |
aivo use |
aivo keys use |
switch active key |
aivo ping |
aivo keys ping |
health-check keys |
Providers & keys — aivo keys
A key is a saved provider credential (id, name, base URL, secret). The active key is what
commands use by default. Any OpenAI-compatible base URL works; native Anthropic/Gemini, GitHub
Copilot, and Ollama are also supported (the sentinel base URLs copilot and ollama select those
provider types).
aivo keys # list all keys (active marked) — same as `aivo keys list`
aivo keys use <id|name> # activate a key
aivo keys add [name] # add a key (interactive picker for provider type)
aivo keys cat <id|name> # show a key's details
aivo keys edit <id|name> # edit a key
aivo keys rm <id|name> # remove a key
aivo keys reauth <id|name> # OAuth re-login or rotate an API key
aivo keys ping [id|name] # health-check keys (also `aivo ping`)
aivo keys reset-route <id|name> # clear cached provider routing for a key
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.
- 16d ago Changed · -20 lines 66dac977ad65
- 2mo ago Changed · +2 lines 470131643af0
- 2mo ago First seen · 430 lines · 0 tokens per session scan A 455348bf7d64
aivo_guide is a command published in the GitHub repository yuanchuan/aivo (192 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,374 tokens. 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.
aivo_guide compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| aivo_guideyuanchuan/aivo | Command | 192 | 16d ago | MIT | A | 0 | Claude Code |
| 5_gofer_implementeai-support/eai-gofer | Command | 1 | 5d ago | Apache-2.0 | A | 22 | Claude Code |
| 3_gofer_planeai-support/eai-gofer | Command | 1 | 5d ago | Apache-2.0 | A | 20 | Claude Code |
| 0a_problem_validationeai-support/eai-gofer | Command | 1 | 5d ago | Apache-2.0 | A | 22 | Claude Code |
| 9_gofer_testseai-support/eai-gofer | Command | 1 | 5d ago | Apache-2.0 | A | 18 | Claude Code |
| gofer:eai-first-runeai-support/eai-gofer | Command | 1 | 5d ago | Apache-2.0 | A | 23 | Claude Code |
| gofer_hydrateeai-support/eai-gofer | Command | 1 | 5d ago | Apache-2.0 | A | 17 | Claude Code |