rombot-cli

A command-line tool that asks the AI Agents community for answers based on members' tips, repositories, discussions, and known problems. It returns answers with citations.

In plain words
What is it for?
Checking community practices, finding commonly used repositories, and learning about tips or problems in AI-agent development.
Why use it?
It gives coding and agent questions community-based context, so you do not have to search through scattered discussions yourself.

Skill for Claude CodeCodex

Part of the rombot-community-skill plugin — 1 skill shipped together

Install

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.

agentmods
npx agentmods add skills/romiluz13/rombot-community-skill/rombot-cli
Any agent
npx skills add romiluz13/rombot-community-skill --skill rombot-cli
Clone the repo
git clone --depth 1 https://github.com/romiluz13/rombot-community-skill

Made for: Claude Code, Codex.

Or install rombot-community-skill, the plugin that ships this one along with the rest of its 1 skill.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 867 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.00867
Opus 5 $0.00019 $0.00434
Sonnet 5 $0.00008 $0.00173
Haiku 4.5 $0.00004 $0.00087

Measured 3d ago against content hash bf61c58db5f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rombot-cli 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/rombot-ask.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/rombot-cli/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RomBot CLI

Ask the AI Agents community brain a question from inside your coding agent. Get grounded, cited answers from ~4,000 members' tips, repos, discussions, and gotchas.

When to use

Use when you want community-grounded knowledge on a coding/agent topic: best practices, repos people use, gotchas, discussions, tips. Don't use for general web search or questions unrelated to the AI Agents community.

Setup

You — the coding agent — drive setup. The human never opens a terminal for the skill.

  1. Install the skill (if not already installed): npx skills add romiluz13/rombot-community-skill.
  2. Check whether the skill is configured. Run python3 scripts/rombot-ask.py "test". If it exits 4 ("Not configured"), the skill is not set up — proceed to step 3. If it runs, skip to Asking a question.
  3. Get a token from the human. Ask the human: "Send /rombot-cli to RomBot on WhatsApp to get a token, then paste it here." The token is tied to the human's phone number — the agent cannot get it; the human is the only one who can. Wait for the human to paste the token into the chat.
  4. Configure the skill yourself. With the token the human pasted, run setup so the token is in the environment (the CLI reads it from there and writes the config non-interactively, no prompts):
    ROMBOT_CLI_TOKEN=<the token> python3 scripts/rombot-ask.py setup
    
    This writes ~/.config/rombot-cli/.env with the token and the default endpoint URL.
  5. Verify the skill is configured. Re-run step 2 (python3 scripts/rombot-ask.py "test"). If it now runs (exit 0), setup succeeded — proceed to Asking a question. If it still exits 4 ("Not configured"), setup failed — re-run step 4.
  6. Ask. You're now configured — proceed to Asking a question.

Asking a question

With the skill configured (above), run the CLI via Bash:

python3 scripts/rombot-ask.py "<question>"
  • Pass the answer through verbatim to the human. Do NOT reword, summarize, or translate RomBot's answer.
  • You may rephrase the human's question into a crisp query before calling the CLI.
  • RomBot's answer includes inline citations (who said it, which group, when, repo links). Do not strip them.
  • If the CLI exits non-zero, report the error to the human.

Read the full file on GitHub · 78 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 3d ago First seen · 78 lines · 38 tokens per session scan A bf61c58db5f9

Subscribe to this mod's changes

rombot-cli is a skill published in the GitHub repository romiluz13/rombot-community-skill (11 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 867 once invoked, about $0.0002 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.