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/grahamton/merchgent/command-creatornpx skills add grahamton/merchGent --skill command-creatorgit clone --depth 1 https://github.com/grahamton/merchGentWhat 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 | $0.00014 | $0.01825 |
| Opus 5 | $0.00007 | $0.00912 |
| Sonnet 5 | $0.00003 | $0.00365 |
| Haiku 4.5 | $0.00001 | $0.00183 |
Grade A, and why
command-creator 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 2d 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Usage (Already Configured)
Create a new command file
mkdir -p .opencode/commands
Create .opencode/commands/<name>.md with frontmatter and a prompt template.
Command file example
---
description: Run tests with coverage
agent: build
model: gpt-5.2-codex
---
Run the full test suite with coverage report and show any failures.
Focus on the failing tests and suggest fixes.
Prompt config essentials
- Use
$ARGUMENTSfor all arguments, or$1,$2,$3for positional args. - Use
!\command`` to inject shell output into the prompt. - Use
@path/to/fileto include file contents in the prompt.
Notes from OpenCode docs
- Command files live in
.opencode/commands/(project) or~/.config/opencode/commands/(global). - The markdown filename becomes the command name (e.g.,
test.md→/test). - JSON config also supports commands in
opencode.jsonundercommand. - Custom commands can override built-ins like
/init,/undo,/redo,/share,/help.
Reference
Follow the official OpenCode command docs: https://opencode.ai/docs/commands/ Use the docs as the escape hatch when unsure.
Docs snapshot
Skip to content OpenCode
Search ⌘ K Intro Config Providers Network Enterprise Troubleshooting Migrating to 1.0 TUI CLI Web IDE Zen Share GitHub GitLab Tools Rules Agents Models Themes Keybinds Commands Formatters Permissions LSP Servers MCP servers ACP Support Agent Skills Custom Tools SDK Server Plugins Ecosystem On this page Overview Create command files Configure JSON Markdown Prompt config Arguments Shell output File references Options Template Description Agent Subtask Model Built-in Commands Create custom commands for repetitive tasks.
Custom commands let you specify a prompt you want to run when that command is executed in the TUI.
/my-command
Custom commands are in addition to the built-in commands like /init, /undo, /redo, /share, /help. Learn more.
Create command files Create markdown files in the commands/ directory to define custom commands.
What ships with it
2 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.
- 2d ago First seen · 353 lines · 14 tokens per session scan A fa6325505859
command-creator is a skill published in the GitHub repository grahamton/merchGent (0 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 1,825 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
video-research
Teaches Claude how to effectively use the 28 video-research-mcp tools. Activates when working with video analysis, deep research, content extraction, web search, or knowledge store via the video-research MCP server.
ffmpeg-production
FFmpeg video/audio processing — conversion, scaling, compression, trimming, concatenation, AI post-processing. Not for audio ducking/voice mixing (tts-production) or Remotion rendering.
video-production
Orchestrate multi-clip AI video projects — style anchors, chaining patterns, frame-level QA, montage assembly. Not for video analysis, research, provider settings, or FFmpeg encoding.
mlflow-traces
Use when working with MLflow traces: debugging via MCP tools, analyzing performance, logging feedback, writing custom scorers/evaluations, or cleaning up trace data.
video-generation
Generate AI video with Veo or Sora. Triggers on text-to-video, image-to-video, video extension, style-consistent generation. Not for video analysis, research, or FFmpeg editing.
gemini-visualize
Generates interactive HTML visualizations (concept maps, evidence networks, knowledge graphs) from Gemini analysis results. Triggers automatically after /gr:video, /gr:research, /gr:analyze.