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 agentmods add skills/iranee/fnos-hermes-agent/trim-clinpx skills add iranee/fnos-hermes-agent --skill trim-cligit clone --depth 1 https://github.com/iranee/fnos-hermes-agentWrote 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/iranee/fnos-hermes-agent/trim-cli)<a href="https://agentmods.dev/skills/iranee/fnos-hermes-agent/trim-cli"><img src="https://agentmods.dev/badge/skills/iranee/fnos-hermes-agent/trim-cli.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 | $0.00037 | $0.12255 |
| Opus 5 | $0.00018 | $0.06128 |
| Sonnet 5 | $0.00007 | $0.02451 |
| Haiku 4.5 | $0.00004 | $0.01226 |
Grade A, and why
trim-cli 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 6d 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.
The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What ships with it
42 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- bin/trim-cli-darwin-arm64 8427 KB
- bin/trim-cli-darwin-x64 9133 KB
- bin/trim-cli-linux-arm64 7179 KB
- bin/trim-cli-linux-x64 8414 KB
- entries/trim-app.md 4.7 KB
- entries/trim-docker.md 1.1 KB
- entries/trim-download.md 1.9 KB
- entries/trim-file.md 1.2 KB
- entries/trim-log.md 2.0 KB
- entries/trim-media.md 1.4 KB
- entries/trim-monitor.md 1.9 KB
- entries/trim-network.md 800 B
- entries/trim-photos.md 1.3 KB
- entries/trim-shared.md 2.2 KB
- entries/trim-storage.md 1.5 KB
- entries/trim-system.md 2.6 KB
- entries/trim-user.md 990 B
- manifest.json 1.1 KB
- reference/_conventions.md 2.1 KB
- reference/_index.md 6.5 KB
- reference/app-center.md 19 KB
- reference/dockermgr.md 9.5 KB
- reference/download.md 14 KB
- reference/file.md 25 KB
- reference/log.md 9.0 KB
- reference/media.md 3.8 KB
- reference/network.md 1.1 KB
- reference/photos.md 6.5 KB
- reference/power.md 1.0 KB
- reference/resmon.md 6.6 KB
- reference/stor.md 18 KB
- reference/sysinfo.md 6.4 KB
- reference/user.md 52 KB
- reference/workflows/device-validation.md 2.2 KB
- reference/workflows/file-routing.md 3.0 KB
- reference/workflows/file-upload-validation.md 1.6 KB
- reference/workflows/media-routing.md 2.1 KB
- reference/workflows/photos-routing.md 3.2 KB
- reference/workflows/storage-dangerous-ops.md 2.9 KB
- scripts/trim-cli 641 B
- scripts/trim-cli.cmd 202 B runs code
- scripts/trim-cli.ps1 197 B runs code
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.
- 6d ago First seen · 1,244 lines · 37 tokens per session scan A 995bfe84cd5c
trim-cli is a skill published in the GitHub repository iranee/fnos-hermes-agent (100 stars, last pushed 17d ago), licensed GPL-3.0. It adds 37 tokens to every session and 12,255 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
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.
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…
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…
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…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.