Borrowing it
Nothing to install: this file belongs to rhishi99/hermes-model-auto-switch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rhishi99/hermes-model-auto-switch/master/AGENTS.mdgit clone --depth 1 https://github.com/rhishi99/hermes-model-auto-switchWrote 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/instructions/rhishi99/hermes-model-auto-switch/agents-md)<a href="https://agentmods.dev/instructions/rhishi99/hermes-model-auto-switch/agents-md"><img src="https://agentmods.dev/badge/instructions/rhishi99/hermes-model-auto-switch/agents-md.svg" alt="Measured on agentmods" 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 | $0.00820 | $0.00820 |
| Opus 5 | $0.00410 | $0.00410 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
hermes-model-auto-switch AGENTS.md scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:19280/health How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unattended Installation Runbook for hermes-model-auto-switch
What this repo is: This repository provides a hybrid auto-switch system for Hermes to ensure you always have at least one working model with a SWE score > 71%. It combines an FCM router daemon, NVIDIA NIM health monitoring, and a learning database.
Install
Run the following commands in order:
python install.py
Expected output: A series of OK / SKIP steps completing the setup, followed by a success summary.
Verify
Run these checks to verify a successful installation:
- Verification Script:
python install.py --check
Pass condition: Script exits with 0 and prints no errors.
- Daemon Health:
curl http://localhost:19280/health
Pass condition: returns JSON containing "ok":true and "running":true. (There is no status field on this endpoint.)
- NIM Health Check:
python scripts/nvidia_nim_health_check.py
Pass condition: Outputs healthy NVIDIA models.
- Hybrid Auto-Switch Dry Run:
python scripts/hybrid_auto_switch.py --dry-run
Pass condition: exits without a traceback and prints a JSON object.
Note the switcher is disabled by default. With NIM_AUTO_SWITCH_ENABLED unset it short-circuits
and prints {"status": "disabled", ...} — that is expected, not a failure. To exercise the real path:
NIM_AUTO_SWITCH_ENABLED=true python scripts/hybrid_auto_switch.py --dry-run
Pass condition: prints JSON whose status is one of would_switch, no_change, or
no_eligible_models, and config.yaml is byte-identical before and after. The JSON always
carries fcm_resynced (always false under --dry-run — resync never runs in a rehearsal);
retired_models and throttled_models appear at the top level when status is
no_eligible_models, or nested as nim_health_summary.retired / nim_health_summary.throttled
otherwise. A status of no_eligible_models means no monitored model is currently healthy — an
unknown or sub-threshold SWE score no longer excludes a model by itself; the filter is
healthy AND (SWE >= 71% OR SWE unknown) — see Known limitations in RELEASE_NOTES.md. Set
NIM_AUTO_SWITCH_ENABLED=true permanently by adding it to the Hermes .env
(hermes config env-path).
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.
- 7d ago First seen · 87 lines · 820 tokens per session scan A 1dbc288db346
hermes-model-auto-switch AGENTS.md is an instructions file published in the GitHub repository rhishi99/hermes-model-auto-switch (2 stars, last pushed 15d ago), licensed MIT. It adds 820 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.