merchGent: Skill for OpenCode

.opencode/skills/skill-creator/SKILL.md

skill-creator is a skill for OpenCode from grahamton/merchGent. It costs 14 tokens per session (653 once invoked), scanned A, original, MIT.

A scaffold for creating new OpenCode skills. A scaffold is a starting structure containing the files and guidance a new skill needs.

In plain words
What is it for?
It is for creating skill folders, example environment files, ignored credentials, reusable scripts, and clear trigger phrases.
Why use it?
It helps turn a completed workflow or requested task into a reusable skill with triggers, configuration guidance, and scripts where needed.

Skill for OpenCode

Written for OpenCode: installed under .opencode/. Also seen: mentions OpenCode.

This is grahamton/merchGent's own configuration. It tells OpenCode how to work on merchGent itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything merchGent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to grahamton/merchGent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/grahamton/merchGent/main/.opencode/skills/skill-creator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/grahamton/merchGent

Made for: OpenCode.

Wrote 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.

agentmods badge for skill-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/grahamton/merchgent/skill-creator.svg)](https://agentmods.dev/skills/grahamton/merchgent/skill-creator)
Your own site
<a href="https://agentmods.dev/skills/grahamton/merchgent/skill-creator"><img src="https://agentmods.dev/badge/skills/grahamton/merchgent/skill-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 653 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.00653
Opus 5 $0.00007 $0.00327
Sonnet 5 $0.00003 $0.00131
Haiku 4.5 $0.00001 $0.00065

Measured 5d ago against content hash 36378ea012f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-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.

.opencode/skills/skill-creator/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill creator helps create other skills that are self-buildable.

The best way to use it is after a user already executed a flow and says: create a skill for this. Alternatively, if the user asks for a skill to be created, suggest they do the task first and ask for skill creation at the end.

This should trigger this scaffold:

  • If the user needed to configure things, create a .env.example without credentials and include all required variables.
  • Ask the user if they want to store credentials. If yes, write them to a .env file in the skill, and suggest rotating keys later.
  • Always add a .gitignore in the skill that ignores .env, and verify .env is not tracked.
  • If the user needed to interact with an API and you created scripts, add reusable scripts under scripts/.
  • New skills should explain how to use the scripts/ and that .env.example defines the minimum config.
  • Skills should state that they infer what they can do from the available config.

Trigger phrases (critical)

The description field is how Claude decides when to use your skill. Include 2-3 specific phrases that should trigger it.

Bad example: "Use when working with content"

Good examples: "Use when user mentions 'content pipeline', 'add to content database', or 'schedule a post'" "Triggers on: 'rotate PDF', 'flip PDF pages', 'change PDF orientation'"

Quick validation:

  • Contains at least one quoted phrase
  • Uses "when" or "triggers"
  • Longer than ~50 characters

Frontmatter template

---
name: my-skill
description: |
  [What it does in one sentence]

  Triggers when user mentions:
  - "[specific phrase 1]"
  - "[specific phrase 2]"
  - "[specific phrase 3]"
---

Quick Usage (Already Configured)

Create a new skill folder

mkdir -p .opencode/skills/<skill-name>

Minimum scaffold files

  • SKILL.md
  • scripts/
  • .env
  • .env.example (use this to guide the minimum config)
  • .gitignore (ignore .env)

.env (credentials + config)

  • Use .env.example to document required credentials or external setup.
  • Do not include any real credentials in .env.example.

Read the full file on GitHub · 102 lines

Files

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.

Changes

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.

  1. 5d ago First seen · 102 lines · 14 tokens per session scan A 36378ea012f5

Subscribe to this mod's changes

skill-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 653 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.

Related

Other skills, from other repositories