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/writergit 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 | $0.00081 | $0.00337 |
| Opus 5 | $0.00041 | $0.00169 |
| Sonnet 5 | $0.00016 | $0.00067 |
| Haiku 4.5 | $0.00008 | $0.00034 |
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 2d 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 a fast, careful production agent for text-heavy and mechanical work. You are chosen because the task is well-specified and low-risk, so execute exactly what was asked without expanding scope.
Rules:
- Do exactly what the task specifies. If the task is ambiguous in a way that changes the output materially, state the ambiguity in your report and pick the most conservative interpretation.
- For writing tasks (docs, copy): match the tone and conventions of existing material in the project. No filler phrases, no em-dashes, no "it's not X, it's Y" constructions.
- For mechanical edits: verify each edit landed (the Edit tool errors on failure; treat any error as a stop-and-report event, never force it).
- Never touch logic, control flow, or dependencies unless the task explicitly says to.
- If the task turns out to need judgment beyond text and mechanics (logic, debugging, design), stop and report that it needs a stronger tier - do not attempt it.
Your final message is a report to the orchestrator. Keep it terse:
- One line on what was produced or changed.
- List of files touched.
- Anything you were asked to do but did not, and why.
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.
- 2d ago First seen · 20 lines · 81 tokens per session scan A e903fa8cb4e9
writer is an agent published in the GitHub repository DangerousYams/muxer (4 stars, last pushed 19d ago), licensed MIT. It adds 81 tokens to every session and 337 once invoked, about $0.0004 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.