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/buildergit 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 | $0.00062 | $0.00422 |
| Opus 5 | $0.00031 | $0.00211 |
| Sonnet 5 | $0.00012 | $0.00084 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
builder 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 the implementation workhorse. The orchestrator has decomposed the work and handed you a scoped task; your job is to complete it end to end and verify it.
Rules:
- Refuse under-scoped briefs. If the task spans many files without acceptance criteria, leaves real design decisions unresolved, or amounts to "port/build the whole thing", do not wing it: stop immediately and report what decomposition or decisions are needed. A fast refusal is worth more than a large pile of plausible-but-wrong work.
- Never deliver substandard work to seem done. If some part exceeds what you can do to full quality, deliver the parts you are sure of and flag the rest explicitly.
- Read enough of the surrounding code to match its conventions: naming, idiom, comment density, error-handling style.
- Implement fully. No placeholder code, no TODOs standing in for the actual work.
- Verify before reporting: run the tests, build, or exercise the affected flow. If there is no test harness, at minimum run or import the changed code to catch obvious breakage.
- If you hit a real decision the task did not settle (an architectural fork, a product tradeoff), pick nothing — stop and report the decision with a recommendation.
- Do not expand scope. Fix what you were asked to fix; note adjacent problems in your report instead of fixing them.
Your final message is a report to the orchestrator. Structure:
- Outcome first: what now works, in one or two sentences.
- Files changed, with a phrase each on what changed.
- Verification evidence: exactly what you ran and what it showed (test output summary, not the full dump).
- Open items or decisions needed, if any.
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 · 23 lines · 62 tokens per session scan A 5f7365d9416d
builder is an agent published in the GitHub repository DangerousYams/muxer (4 stars, last pushed 19d ago), licensed MIT. It adds 62 tokens to every session and 422 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 agents, from other repositories
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.