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 skills/0xranx/golembot/multi-botnpx skills add 0xranx/golembot --skill multi-botgit clone --depth 1 https://github.com/0xranx/golembotWrote 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/skills/0xranx/golembot/multi-bot)<a href="https://agentmods.dev/skills/0xranx/golembot/multi-bot"><img src="https://agentmods.dev/badge/skills/0xranx/golembot/multi-bot.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 | $0.00053 | $0.00811 |
| Opus 5 | $0.00026 | $0.00405 |
| Sonnet 5 | $0.00011 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
multi-bot scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST http://<peer-url>/chat \ How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Bot Collaboration
You may be one of several GolemBot instances running in the same fleet. The gateway injects [Peers: ...] into your group chat context so you know who else is present.
Peer Awareness
When you see [Peers: 小忆 (user research), 小舟 (content creation)] in the prompt:
- These are other GolemBot instances in the fleet
- Each has its own specialization (shown in parentheses)
- They may or may not be active in this specific group chat
When to Respond vs [PASS]
In group chats with peers, follow these rules:
- Respond if the message falls within your domain/role
- Respond if you are directly @mentioned
- [PASS] if the message clearly belongs to another peer's domain
- Respond if the topic spans multiple domains — focus on YOUR area of expertise only, don't duplicate what peers would cover
- Respond if no peer is better suited (don't let messages go unanswered)
Avoiding Redundancy
- Check the conversation history for
[bot:PeerName]entries - If a peer already covered a topic, don't repeat it — add new information or skip
- When a topic spans multiple domains, scope your response to your own expertise
Calling Peer Bots
You can call other GolemBot instances directly via their HTTP API when you need their capabilities:
# Ask a peer bot a question
curl -s -X POST http://<peer-url>/chat \
-H 'Content-Type: application/json' \
-d '{"message": "your question here", "sessionKey": "cross-bot-<context>"}'
# Check a peer's status
curl -s http://<peer-url>/health
Error Handling for Peer Calls
Peer bots may be temporarily unavailable. Always check the HTTP status code before using the response:
response=$(curl -s -w "\n%{http_code}" -X POST http://<peer-url>/chat \
-H 'Content-Type: application/json' \
-d '{"message": "your question", "sessionKey": "cross-bot-ctx"}')
status=$(echo "$response" | tail -1)
body=$(echo "$response" | sed '$d')
if [ "$status" -ne 200 ]; then
# Peer unavailable — answer with your own knowledge or inform the user
echo "Peer bot returned status $status; falling back to local knowledge."
fi
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.
- 5d ago First seen · 93 lines · 53 tokens per session scan A b51dc4553902
multi-bot is a skill published in the GitHub repository 0xranx/golembot (320 stars, last pushed 17d ago), licensed MIT. It adds 53 tokens to every session and 811 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
karpathy-guidelines
Tool-agnostic behavioral guidelines for AI coding assistants. Use when writing, reviewing, debugging, or refactoring code to reduce overengineering, surface ambiguity, make surgical changes, and define verifiable success criteria.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
ulw-execute
Executes a written Prometheus work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents. Use when the user says ulw-execute or asks to run a .omo/plans plan.
lcx-report-bug
Create a high-signal bug issue or PR in the repo that owns the defect. Use this whenever the user asks to report, file, open, or triage a LazyCodex, lazycodex-ai, omo-codex, Codex plugin, or upstream Codex CLI bug, especially when they need source-backed root cause, reproduction steps, fix guidance, and GitHub routing.
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…