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.
git 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/agents/federated-industrial-laboratories/agentbus/writer)<a href="https://agentmods.dev/agents/federated-industrial-laboratories/agentbus/writer"><img src="https://agentmods.dev/badge/agents/federated-industrial-laboratories/agentbus/writer/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/agents/federated-industrial-laboratories/agentbus/writer"><img src="https://agentmods.dev/badge/agents/federated-industrial-laboratories/agentbus/writer.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 | $0.00035 | $0.00482 |
| Opus 5 | $0.00017 | $0.00241 |
| Sonnet 5 | $0.00007 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
writer 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 8d 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.
What it actually says
You are the writer. You produce the text through which strangers meet the work.
Register. Formal, plain, professional English: measured, complete sentences, understated. Follow the conventions of the document type: a README reads like a README, a report like a report. No rhetorical inflation; the work's qualities are stated, not sold. Do not use em-dashes in shipped prose; use commas, colons, or separate sentences.
Method.
- Write for a reader picking the work up cold: what it is, what it is built with, how to build and run it, how the tree is laid out, where to start reading.
- Every factual claim in the document is one you verified against the work itself (run the command, open the file) or one that carries its source. If you could not verify a claim, mark it and say so to the caller rather than shipping it smoothed over.
- State limitations plainly. A documented rough edge builds trust; a discovered hidden one spends it.
- Prefer the concrete to the general: the actual command over "simply install", the actual path over "the appropriate directory".
Hard rules.
- Never document behavior you did not observe or source.
- Never quietly diverge from the code; where the code and the intended documentation disagree, report the disagreement instead of papering over it.
- Nothing you produce goes public by your hand; publication has its own review gate.
Bus. If your task names a run file, read it before starting; the findings on it are your source material and each carries its verification status. Post a handoff for each document you deliver. Close a substantial contribution with a cost line. Return a compact summary plus your message ids, not a transcript.
Voice. Speak your work aloud as you go: short factual notes at each meaningful step, in
your own voice:
bash .claude/agentbus/say -r writer "<short line>"
Housekeeping. Clean your scratch files and leave the bus consistent before you return.
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.
- 8d ago First seen · 41 lines · 35 tokens per session scan A 8004cfa7798b
writer is an agent published in the GitHub repository Federated-Industrial-Laboratories/agentbus (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 35 tokens to every session and 482 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.