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 KxSystems/kx-skills --skill kdbie-devgit clone --depth 1 https://github.com/KxSystems/kx-skillsWrote 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/kxsystems/kx-skills/kdbie-dev)<a href="https://agentmods.dev/skills/kxsystems/kx-skills/kdbie-dev"><img src="https://agentmods.dev/badge/skills/kxsystems/kx-skills/kdbie-dev/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/kxsystems/kx-skills/kdbie-dev"><img src="https://agentmods.dev/badge/skills/kxsystems/kx-skills/kdbie-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 30 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 233 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 255 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00045 | $0.02943 |
| Opus 5 | $0.00023 | $0.01471 |
| Sonnet 5 | $0.00009 | $0.00589 |
| Haiku 4.5 | $0.00005 | $0.00294 |
Grade A, and why
kdbie-dev 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 8d 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating KX Insights Enterprise via kxi
kxi is a Python CLI (location varies — often a venv) that drives a live Insights Enterprise
deployment. Every command runs against a specific profile (~/.insights/config.toml) and a
Kubernetes namespace, and several actions (pm deploy/teardown, install delete) are
destructive. So before running anything: resolve the active profile and namespace, and never
operate on a namespace the user didn't explicitly name.
The core workflow is packages. Two command groups, easy to confuse:
kxi package — build/validate/pack a package locally (init → validate → packit),
producing a .kxi file. Nothing touches a running instance.
kxi pm — the package manager on a running IE instance: push (upload), deploy (activate),
list/info, teardown. push does not deploy — they're deliberately separate steps.
(kxi install handles the Helm/K8s lifecycle; kxi obs retrieves logs.)
Configuration
KXI_BIN=kxi
The binary is a python executable kxi, which may be available on the main path, but allow the user to define a different location as it is a common pattern to install the kxi binary in a virtual environment.
Profile Config File Location
IMPORTANT: The kxi CLI stores all profile configuration in
~/.insights/config.toml(TOML format, kxi ≥ 1.12). There is no~/.kxidirectory — do not reference or attempt to create it.
- Active profile:
current_profile = "default"field at the top of the file- Per-profile settings (hostname, namespace, realm, etc.) under
[profiles.<name>]- Legacy installs (kxi < 1.12) use
~/.insights/cli-config(INI format) as a fallbackTo read the active profile's hostname programmatically:
python3 -c "import tomllib; c=tomllib.load(open('$HOME/.insights/config.toml','rb')); p=c.get('current_profile','default'); print(c['profiles'][p]['hostname'])"
The kxi binary allows for the user to create and utilise different profiles by appending --profile <profile> to the kxi command. For example kxi --profile uat would issue kxi commands against that uat profile. Profiles are created via the kxi configure --profile <profile> command and configuration stored in ~/.insights/config.toml. To permanently switch the CLI default: $KXI_BIN workon <profile>.
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.
- 8d ago First seen · 258 lines · 45 tokens per session scan A 702d679ad35d
kdbie-dev is a skill published in the GitHub repository KxSystems/kx-skills (16 stars, last pushed 6d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,943 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
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.
google-cloud-solution-guided-gke-ai-migration
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI inference workload (on Cloud Run, the Gemini API, Gemini Enterprise Agent Platform, or a custom VM) and wants to move it to…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
agent-platform-endpoint-management
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoint permission, quota, or resource busy errors. Don't use for deploying models to endpoints or for running model…
gke-inference
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on GKE. Don't use for generic batch jobs or HPC task queues (use gke-batch-hpc instead).
modal
Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.