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/tzachbon/claude-model-router-hookWrote 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/tzachbon/claude-model-router-hook/routed-opus-max)<a href="https://agentmods.dev/agents/tzachbon/claude-model-router-hook/routed-opus-max"><img src="https://agentmods.dev/badge/agents/tzachbon/claude-model-router-hook/routed-opus-max/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/tzachbon/claude-model-router-hook/routed-opus-max"><img src="https://agentmods.dev/badge/agents/tzachbon/claude-model-router-hook/routed-opus-max.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 | $0.00026 | $0.00101 |
| Opus 5.5 | $0.00010 | $0.00040 |
| Sonnet 5.5 | $0.00005 | $0.00020 |
| Haiku 4.5 | $0.00003 | $0.00010 |
Grade A, and why
routed-opus-max 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 2mo 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.
This is a copy
86% identical to routed-opus-high — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Complete the delegated task exactly as prompted; return a concise report.
Work directly unless the task has independent, self-contained portions that need parallel investigation. Never delegate mechanical work merely to verify it; when delegation is justified, give each child a narrow scope and ask for a concise report.
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.
- 2mo ago First seen · 12 lines · 26 tokens per session scan A a8798320c26c
routed-opus-max is an agent published in the GitHub repository tzachbon/claude-model-router-hook (106 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 101 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 86% identical to routed-opus-high, differing in 6 lines, and is treated as a copy.
Other agents, from other repositories
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
skill-improver
Implements skill improvements based on observability data from LEARNINGS.md. Prioritizes by frequency × impact / ease, generates proposals, validates changes. Enhanced with Hyperagents patterns: consults PerformanceTracker for trend data and ImprovementMemory for causal hypotheses before proposing changes.
skill-evaluator
Records human qualitative feedback on recent skill executions. Use when a skill run needs a judgment the execution logs cannot capture.
continuation-agent
Lightweight agent designed to continue work from a session state checkpoint. Spawned when the parent agent exceeds context thresholds. This agent: 1. Reads the session state file 2. Re-establishes necessary context 3. Continues the task without interruption 4. Can spawn another continuation agent if needed.
unbloat-remediator
Orchestrate safe bloat remediation - execute deletions, refactorings, consolidations, and archiving with user approval. Creates backups, runs tests, provides rollback.
context-optimizer
Autonomous agent for context window optimization and MECW compliance. Use when full context audits needed, skills exceed token budgets, pre-release compliance verification, periodic health checks. Do not use when single skill optimization - use abstract:modular-skills. quick token counts - use skills-eval instead.…