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 xonovex/platform --skill command-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/command-guide)<a href="https://agentmods.dev/skills/xonovex/platform/command-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/command-guide/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/xonovex/platform/command-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/command-guide.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 | $0.00110 | $0.00946 |
| Opus 5.5 | $0.00044 | $0.00378 |
| Sonnet 5.5 | $0.00022 | $0.00189 |
| Haiku 4.5 | $0.00011 | $0.00095 |
Grade A, and why
command-guide 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 5d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command Guidelines
Author, merge, simplify, and distill reusable user-invocable prompt files (sometimes called slash commands, custom commands, or user prompts depending on the agent harness).
Core Principles
- Generic by Default: strip project-specific paths, domain terms, and tech names at author time so prompts reuse across projects
- Match Style and Voice: preserve the target's structure, voice, formatting when merging
- Structure Integrity: frontmatter, Arguments, and Delegation are the essential thin-command sections; the owning skill carries the procedure, output, and errors
- Safe Modifications: preview changes (
--dry-run) before applying - Deletion-first editing: a simplify or distill pass cuts at least as much as it adds, and reuses existing vocabulary rather than coining new terms; skill-guide owns this rule
- Bound the Body: target 15-40 lines for a delegating command and <150 lines for a harness that cannot delegate
- Delegate, Don't Duplicate: a command owns its argument contract and delegates the procedure to a guideline skill via the
Skilltool; the skill is the single source of truth, the command a thin, stable interface - Depend on Skills Two Ways: depend hard (name the exact skill, and add it to the plugin's
dependencieswhen the harness installs them) when one specific skill is always required, or soft (describe the capability and let the agent select an installed skill, degrading gracefully) when several interchangeable skills fit; if the harness distributes skills but not commands, publish and invoke the skill directly; either way load the selected skill at run time (install ≠ in-context), see references/distill.md - Validate the public contract: keep argument-hint and Arguments names identical; express optional supporting capabilities in delegation prose, not command metadata
Gotchas
- A prompt that hardcodes one repo's paths/domain terms isn't reusable: generalize at author time, not later
- Argument shape is the prompt's public contract: merging different argument styles silently breaks callers
- "Auto-generated name" + an existing file is a silent overwrite risk, always check before write
- Generalizing too aggressively destroys the example's instructional value: keep enough specificity to learn from
- A command-capable plugin that delegates to a skill but omits a supported dependency declaration can't guarantee the skill at run time: wire the dependency and load via the
Skilltool (install ≠ in-context)
What ships with it
9 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.
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.
- 5d ago Changed · -3 lines b17f82ede348
- 1mo ago First seen · 47 lines · 110 tokens per session scan A 4aaa560a5e06
command-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 2d ago), licensed MIT. It adds 110 tokens to every session and 946 once invoked, about $0.0004 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 2026-09-08.
Other skills, from other repositories
harbor-daytona
Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.
docker
Use when authoring or auditing a Dockerfile, shrinking a bloated image, hardening a container that runs as root, picking a base image, or wiring a Compose dev loop with hot reload. NOT CI builds or deploy-to-host (that is deployment), NOT k8s autoscaling (that is scaling), NOT app-level injection or secrets-in-code…
kastell
Server security auditing, hardening, and fleet management. 457 security checks across 30 categories (SSH, Firewall, Docker, TLS, HTTP Headers), CIS/PCI-DSS/HIPAA compliance mapping, 24-step production hardening, and 13 MCP tools. Supports Hetzner, DigitalOcean, Vultr, and Linode with Coolify, Dokploy, and bare VPS…
ilo
Run builds, tests, and other tooling inside a reproducible, containerized dev environment via the ilo CLI instead of on the host. Use this whenever a project relies on ilo, devcontainers, or container-based build environments — it has a .ilo.rc / .ilo/ilo.rc, dev/ argument files, a Containerfile/Dockerfile, a…
docker-compose-local-setup
Creates or updates local multi-service orchestration using docker compose. Covers compose.yaml design, service health checks, dependson readiness, env files, named volumes, migrations/seeds jobs, verification commands, and cleanup workflows for local development.
compose
A guide to Docker Compose, a tool for defining and running applications made of multiple containers, such as a web app, API, and database.