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 jordanhubbard/agentos --skill hermes-sessiongit clone --depth 1 https://github.com/jordanhubbard/agentosWrote 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/jordanhubbard/agentos/hermes-session)<a href="https://agentmods.dev/skills/jordanhubbard/agentos/hermes-session"><img src="https://agentmods.dev/badge/skills/jordanhubbard/agentos/hermes-session/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/jordanhubbard/agentos/hermes-session"><img src="https://agentmods.dev/badge/skills/jordanhubbard/agentos/hermes-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00000 | $0.01028 |
| Opus 5.5 | $0.00000 | $0.00411 |
| Sonnet 5.5 | $0.00000 | $0.00206 |
| Haiku 4.5 | $0.00000 | $0.00103 |
Grade A, and why
hermes-session 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 28d 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.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes operator session (agentOS)
This file is the session context an operator agent (Hermes or any other LLM CLI) loads when attached to agentOS. It is not a UI. It is not a PD.
What agentOS is
agentOS is a capability-secured OS on seL4. Guests (Linux, FreeBSD) and native agents consume virtualizers (serial, net, blk). seL4 is the only kernel-mode code. Native agents are not TCB.
What this session may do (now)
Read and report. Call the inspect snapshot ABI:
On the AArch64 target, make -C tools/agentctl builds the public consumer.
Run _build/tools/agentctl/agentctl --socket PATH inspect against the CC socket.
CC returns the immutable root boot observation with MSG_CC_INSPECT.
The report labels its observation as boot: listed PDs successfully started,
but current thread states are unknown. Guest RAM is the boot reservation;
untyped usage is an accounted-page lower bound, not a free-memory estimate.
No root endpoint or device capability is granted to the consumer.
agentctl --socket PATH session-inspect routes inspect.snapshot through
serial_virt to the native operator_session client. The client has its own
queue page and scoped attach/notification capabilities. This is one externally
serialized stream; callers must not interleave requests. The transport remains
privileged CC, and this protocol offers no PTY, shell, mutation or API-key storage.
- Header:
platform/include/platform/inspect.h - Fill:
aos_inspect_fill - Structured text:
aos_inspect_format(key=valuelines)
The snapshot covers:
- Memory: untyped pool total/used, guest RAM size, PD count
- Threads: PD index, name, priority, state (running/blocked/idle/unknown)
- Hardware: arch, UART PA, GIC distributor PA, emulated virtio-net IPA/IRQ
Host tests: tests/platform/test_inspect_snapshot.c (via make test-host).
Those tests are a pre-filter. They do not prove a live seL4 query.
make test-inspect verifies the real CC and CLI path, malformed request
rejection and repeat stability. make test-inspect-readonly separately
requires a root-verified CC write fault after a successful snapshot read.
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.
- 28d ago Changed 7db8a2472ecb
- 1mo ago Changed · +17 lines f1225f1007a1
- 1mo ago First seen · 76 lines · 0 tokens per session scan A 6cef0708c357
hermes-session is a skill published in the GitHub repository jordanhubbard/agentos (53 stars, last pushed 8d ago), licensed BSD-2-Clause. It costs nothing until one of its globs matches a file; then it loads 1,028 tokens. 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 2026-09-04.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
holoscan-install-wheel
Install Holoscan SDK 5.x CUDA 13 Python wheels in an isolated environment, choosing the full stack or version-matched components.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…