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/agent-creatornpx skills add grahamton/merchGent --skill agent-creatorgit clone --depth 1 https://github.com/grahamton/merchGentWrote 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/grahamton/merchgent/agent-creator)<a href="https://agentmods.dev/skills/grahamton/merchgent/agent-creator"><img src="https://agentmods.dev/badge/skills/grahamton/merchgent/agent-creator.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 | $0.00022 | $0.00317 |
| Opus 5 | $0.00011 | $0.00159 |
| Sonnet 5 | $0.00004 | $0.00063 |
| Haiku 4.5 | $0.00002 | $0.00032 |
Grade A, and why
agent-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 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.
What it actually says
Quick Usage (Already Configured)
Create a project agent
opencode agent create
Agent file locations
- Project agents:
.opencode/agents/<name>.md - Global agents:
~/.config/opencode/agents/<name>.md
Default model
Use gpt-5.2-codex as the default model for new agents unless a workflow needs a different model.
Minimal agent template
---
description: One-line description of what the agent does
mode: subagent
model: gpt-5.2-codex
tools:
write: false
edit: false
bash: false
---
You are a specialized agent. Describe your task, boundaries, and expected output.
Notes from OpenCode docs
- Agent files are markdown with YAML frontmatter.
- The markdown filename becomes the agent name.
- Set
modetoprimary,subagent, orall. - If no model is specified, subagents inherit the caller model.
toolscontrols per-agent tool access.
Reference
Follow the official OpenCode agent docs: https://opencode.ai/docs/agents/
First-Time Setup (If Not Configured)
- Run
opencode agent createand choose project scope. - Paste in the default template above and adjust tools as needed.
What ships with it
4 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 First seen · 52 lines · 22 tokens per session scan A 2ea9ec52ac55
agent-creator is a skill published in the GitHub repository grahamton/merchGent (0 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 317 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.
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.
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.
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.
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-explainer
Teaches Claude how to use the 15 video explainer tools to create explainer videos from research content. Activates when working with video synthesis, explainer creation, or the video-explainer MCP server.