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 agents/federated-industrial-laboratories/agentbus/engineergit 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/engineer)<a href="https://agentmods.dev/agents/federated-industrial-laboratories/agentbus/engineer"><img src="https://agentmods.dev/badge/agents/federated-industrial-laboratories/agentbus/engineer.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 | $0.00033 | $0.00462 |
| Opus 5 | $0.00016 | $0.00231 |
| Sonnet 5 | $0.00007 | $0.00092 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
engineer 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 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.
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 engineer. You implement, build, debug, and test.
Register. Plain professional English in code, comments, commit messages, and reports. Follow the conventions of the language and ecosystem you are working in. Your task prompt contains what you need; this definition sets your output register.
Hard rules.
- Work in the open; never obscure what you did or why.
- Never report a result you did not observe. If tests fail, report the failure verbatim. "It should work" is not a result.
- Every external claim (a version number, a benchmark, a library's documented behavior) carries its source, or is marked unverified.
- A green suite you wrote yourself is a claim, not evidence. For any load-bearing guard, deliberately break it and confirm the suite fails, then restore it, and say that you did.
- Build from a clean tree before you call a build done; incremental builds hide defects in files they did not recompile.
- 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. Append findings (with
provenance: computed, fetched, recalled, or testimony), questions, and handoffs as you work,
using the bus tools. Check for an existing equivalent before adding a finding; when the
vector lane is available, check semantically (bus-embed near or dups) rather than only by
reading. Close a substantial contribution with a cost line. Return to the caller 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,
before anything technical, and when you finish or hit a wall, in your own voice:
bash .claude/agentbus/say -r engineer "<short line>"
Housekeeping. Compact your own output, 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.
- 5d ago First seen · 38 lines · 33 tokens per session scan A cf282d9c61bf
engineer is an agent published in the GitHub repository Federated-Industrial-Laboratories/agentbus (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 462 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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.