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 skills add Federated-Industrial-Laboratories/agentbus --skill busgit clone --depth 1 https://github.com/Federated-Industrial-Laboratories/agentbusWrote 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/federated-industrial-laboratories/agentbus/bus)<a href="https://agentmods.dev/skills/federated-industrial-laboratories/agentbus/bus"><img src="https://agentmods.dev/badge/skills/federated-industrial-laboratories/agentbus/bus/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/skills/federated-industrial-laboratories/agentbus/bus"><img src="https://agentmods.dev/badge/skills/federated-industrial-laboratories/agentbus/bus.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 | $0.00064 | $0.01866 |
| Opus 5 | $0.00032 | $0.00933 |
| Sonnet 5 | $0.00013 | $0.00373 |
| Haiku 4.5 | $0.00006 | $0.00187 |
Grade A, and why
bus 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 11d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The agent bus
Parallel agents are blind to one another by default. They duplicate findings, rank the same result differently with no channel to reconcile, and return transcripts instead of claims. The bus is the correction: one shared, append-only JSONL file per run, which every agent and the orchestrator write to as they work.
The tools are bus-new, bus-append, bus-lint, bus-embed and bus-model. They must be on
PATH, or invoked by path from the agentbus checkout. SCHEMA.md in that checkout is the
codebook and is the authority on anything below.
All five are yours to run. bus-embed and bus-model in particular are part of normal work,
not setup performed by a human beforehand: you run bus-embed near and bus-embed dups to
check whether a finding already exists, and you run bus-model status and bus-model fetch
to make sure the vector lane is available in the first place.
When to open a run
Open a run when a session is about to dispatch work to two or more agents, or when it will run several substantial phases whose findings must survive compaction.
bus-model status # is the embedding model installed and ready?
bus-new <run-name> # prints the path it created
If bus-model status reports that the active model is not installed, install it yourself with
bus-model fetch all-MiniLM-L6-v2 before dispatching. It is an 87 MiB download that takes a
few seconds, and without it the duplicate check below falls back to reading the file by hand.
The run file lands in $AGENTBUS_DIR, or in ./bus/runs if that variable is unset, named
<YYYY-MM-DD>-<run-name>.jsonl. Pass that path to every agent you dispatch, and tell each one
to read it before starting.
Do not open a run for single-agent work. A bus with one writer is overhead with no reader.
Appending
Every agent appends as it works, and so does the orchestrator. An orchestrator that reads the bus without writing to it leaves the record one-sided.
bus-append <file> --agent <name> --type <type> --body '<json object>'
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.
- 11d ago First seen · 168 lines · 64 tokens per session scan A 1e659bfa04c7
bus is a skill published in the GitHub repository Federated-Industrial-Laboratories/agentbus (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,866 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…