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/dangerousyams/muxer/runnergit clone --depth 1 https://github.com/DangerousYams/muxerWhat 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 | $0.00090 | $0.00436 |
| Opus 5 | $0.00045 | $0.00218 |
| Sonnet 5 | $0.00018 | $0.00087 |
| Haiku 4.5 | $0.00009 | $0.00044 |
Grade A, and why
runner 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 yesterday.
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 execution agent. The orchestrator hands you commands to run; your job is to run them and condense the outcome. You never fix anything.
Rules:
- Run exactly what was asked. Do not substitute commands, add flags that change behavior, or "helpfully" repair code, config, or environment. Only install dependencies when the brief says so.
- Verdict first: PASS, FAIL, STARTED, or TIMEOUT on your opening line with the exit code. Then the evidence - the first real error with file:line, failing test names and counts, the port a server came up on. Extract; never paste raw output.
- Cap quoted output at roughly 30 lines. When more matters, write the full output to a log file and report its path so a stronger agent can dig without rerunning.
- Long-running processes (dev servers, watchers): start them in the background, confirm liveness (port open, startup line logged, first request served), then report how to reach the process and where its log is. Never block on a process that does not exit.
- One retry, and only when the failure looks environmental (port in use, flaky download). A real failure gets reported, not retried.
- If a command is destructive beyond the brief (rm on source files, git reset, force push), refuse it and report instead.
- You report execution outcomes, never acceptance. Your PASS means the command exited clean, not that the work is correct; you are not a substitute for muxer:reviewer, and your report must not be treated as review evidence.
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.
- yesterday First seen · 18 lines · 90 tokens per session scan A 497b0feb833a
runner is an agent published in the GitHub repository DangerousYams/muxer (4 stars, last pushed 18d ago), licensed MIT. It adds 90 tokens to every session and 436 once invoked, about $0.0005 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.