Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Veightor/chutes-agent-toolkitnpx agentmods add skills/veightor/chutes-agent-toolkit/chutes-routingWrote 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/veightor/chutes-agent-toolkit/chutes-routing)<a href="https://agentmods.dev/skills/veightor/chutes-agent-toolkit/chutes-routing"><img src="https://agentmods.dev/badge/skills/veightor/chutes-agent-toolkit/chutes-routing/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/veightor/chutes-agent-toolkit/chutes-routing"><img src="https://agentmods.dev/badge/skills/veightor/chutes-agent-toolkit/chutes-routing.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 | $0.00080 | $0.00591 |
| Opus 5.5 | $0.00032 | $0.00236 |
| Sonnet 5.5 | $0.00016 | $0.00118 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
chutes-routing 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 1mo 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
Chutes Routing for Hermes
Status: VERIFIED LIVE 2026-04-13. This is the Hermes entry point for the full skill at
plugins/chutes-ai/skills/chutes-routing/. Scripts and references stay single-sourced in the plugin tree.
When to use this skill
Use when a Hermes user wants to:
- Pick the best Chutes model pool for an intent such as
interactive-fast,agent-coder,private-reasoning, ortee-chat. - Generate inline routing strings using
:latencyor:throughput. - Create or audit stable Chutes aliases backed by
chute_ids. - Re-check a routing pool against live
/v1/modelsso stale static model choices do not rot.
Hermes-facing workflow
Run from the repo root:
python plugins/chutes-ai/skills/chutes-routing/scripts/build_pool.py \
--intent interactive-fast --size 4 --dry-run
python plugins/chutes-ai/skills/chutes-routing/scripts/audit_pool.py \
--routing-string "modelA,modelB,modelC:latency"
For a named alias, require the user to choose the alias string explicitly:
python plugins/chutes-ai/skills/chutes-routing/scripts/build_pool.py \
--intent private-reasoning --size 4 --tee-only --alias tee-chat
Deep references
plugins/chutes-ai/skills/chutes-routing/SKILL.mdplugins/chutes-ai/skills/chutes-routing/references/alias-packs.mdplugins/chutes-ai/skills/chutes-routing/references/routing-strings-spec.mdplugins/chutes-ai/skills/chutes-routing/references/tee-only-routing.mdplugins/chutes-ai/skills/chutes-routing/references/cost-aware-routing.md
Safety rules
- Always use
https://llm.chutes.ai/v1/modelsas the live source of truth. - Do not create or delete aliases without explicit user intent; aliases mutate routing policy.
- Cost filters are advisory, not hard caps. For spend controls, load
chutes-usage-and-billing.
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.
- 1mo ago First seen · 57 lines · 80 tokens per session scan A dd20812a9533
chutes-routing is a skill published in the GitHub repository Veightor/chutes-agent-toolkit (7 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 591 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
bittensor
Use when a developer asks what a Bittensor subnet does, whether it's up right now, how to call/integrate its API, or what mining/validating one costs and earns — e.g. "which subnet does image generation", "is subnet 7 healthy", "call the Beam API for me", "does mining subnet 3 need a GPU", "what does the median miner…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.