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 skills add BlockRunAI/ClawRouter-Hermes --skill clawroutergit clone --depth 1 https://github.com/BlockRunAI/ClawRouter-HermesWrote 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/skills/blockrunai/clawrouter-hermes/clawrouter)<a href="https://agentmods.dev/skills/blockrunai/clawrouter-hermes/clawrouter"><img src="https://agentmods.dev/badge/skills/blockrunai/clawrouter-hermes/clawrouter/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/skills/blockrunai/clawrouter-hermes/clawrouter"><img src="https://agentmods.dev/badge/skills/blockrunai/clawrouter-hermes/clawrouter.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 | $0.00170 | $0.04353 |
| Opus 5 | $0.00085 | $0.02176 |
| Sonnet 5 | $0.00034 | $0.00871 |
| Haiku 4.5 | $0.00017 | $0.00435 |
Grade C, and why
clawrouter scanned grade C with 2 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 3d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/BlockRunAI/ClawRouter-Hermes/main/scripts/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/BlockRunAI/ClawRouter-Hermes/main/scripts/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawRouter (Hermes)
Quick Start (Hermes plugin)
Recommended:
curl -fsSL https://raw.githubusercontent.com/BlockRunAI/ClawRouter-Hermes/main/scripts/install.sh | bash
Manual install, if you know Hermes' Python venv path:
~/.hermes/hermes-agent/venv/bin/python -m pip install -U hermes-plugin-clawrouter
hermes plugins enable clawrouter
hermes clawrouter setup # installs the model-provider plugin + verifies your rail (wallet or API key)
hermes clawrouter doctor # green = ready
If plain pip install hermes-plugin-clawrouter fails with Debian/Ubuntu's
externally-managed-environment, do not use --break-system-packages; install
into Hermes' venv or use the one-command installer. The installer also checks
for Python, pip/venv support, pipx, and Node/npm/npx, and installs missing
basics through common OS package managers when available.
Then in a Hermes chat session:
- Pick model
blockrun/autofor smart routing across 76 models. /clawrouter account— which rail you're paying on (wallet or API key)/clawrouter wallet— show address + USDC balance (Solana and Base)/clawrouter stats— proxy usage/clawrouter status— proxy health/clawrouter route <eco|auto|premium>— switch routing profile/clawrouter logout— drop the API key, go back to the wallet- Tools:
clawrouter_image_generate,clawrouter_video_generate,clawrouter_web_search
Two ways to pay
Same catalog and same model ids either way — what differs is the credential and the host.
| Wallet (x402) | API key (account credit) | |
|---|---|---|
| Set up | npx @blockrun/clawrouter setup |
Sign in at https://user.blockrun.ai, mint a key |
| Funding | USDC on Solana or Base | Card top-up at /dashboard/credits |
| Gateway | sol.blockrun.ai/api · blockrun.ai/api |
api.blockrun.ai |
| Turn on | the default | hermes-clawrouter login brk_live_… |
hermes-clawrouter login brk_live_... # bill account credit
hermes-clawrouter account # what's live right now
hermes-clawrouter logout # back to the x402 wallet
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.
- 3d ago Changed · +28 lines a6ef7c8d8e9f
- 5d ago Changed · -1 tokens per session 7af2e75c0bc5
- 9d ago First seen · 223 lines · 171 tokens per session scan C 0ebd858108e2
clawrouter is a skill published in the GitHub repository BlockRunAI/ClawRouter-Hermes (20 stars, last pushed 2d ago), licensed MIT. It adds 170 tokens to every session and 4,353 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
rag-local-lancedb
Build, query, and manage local vector embeddings and semantic search pipelines using LanceDB and HuggingFace/SentenceTransformers embeddings without cloud dependencies.
optimizing-attention-flash
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding…
chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source…
pytorch-lightning
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
peft-fine-tuning
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.