add-vendor

A command that adds a new skill provider to a plugin marketplace. A skill provider is a repository that supplies reusable instructions or tools for coding agents.

In plain words
What is it for?
Use it when onboarding a vendor from a GitHub repository and registering that vendor's skills in the marketplace.
Why use it?
It removes the need to update the marketplace files, repository link, submodule, plugin, and synchronised skills by hand.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/pleaseai/claude-code-plugins/add-vendor
Clone the repo
git clone --depth 1 https://github.com/pleaseai/claude-code-plugins

Made for: Claude Code.

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,836 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 $0.00041 $0.01836
Opus 5 $0.00020 $0.00918
Sonnet 5 $0.00008 $0.00367
Haiku 4.5 $0.00004 $0.00184

Measured 2d ago against content hash 1f08251d85d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

add-vendor 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.

.claude/commands/add-vendor.md · 229 lines

How it starts

The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Add a new Type 2 vendor to the marketplace.

Arguments: $ARGUMENTS (format: <vendor-name> <github-repo-url>)

Example: /add-vendor mastra https://github.com/mastra-ai/skills


Step 1 — Parse & Validate Input

Parse $ARGUMENTS to extract:

  • VENDOR_NAME: first token (e.g. oxc)
  • REPO_URL: second token (e.g. https://github.com/nicolo-ribaudo/oxc)

Validate:

  • Both tokens are present. If not, stop and show: Usage: /add-vendor <name> <github-repo-url>
  • REPO_URL matches pattern https://github.com/<owner>/<repo> (or [email protected]:<owner>/<repo>). Normalize to HTTPS form.
  • VENDOR_NAME contains only alphanumeric characters, hyphens, and underscores.

Check scripts/meta.ts — read the file and verify VENDOR_NAME is NOT already a key in the vendors object. If it already exists, stop and report: Vendor '<name>' already exists in scripts/meta.ts.

Step 2 — Explore Vendor Repository

Use the GitHub MCP tool or gh CLI to browse the vendor repository and find its skills/ directory:

gh api repos/<owner>/<repo>/contents/skills
  • If the API returns a 404 or the directory doesn't exist, stop and report:
    No skills/ directory found in <REPO_URL>.
    This repository is not a Type 2 vendor (it doesn't self-host skills).
    Consider using /generate-skill for Type 1 skill generation from docs.
    
  • If the directory exists, list all subdirectory names under skills/ — these are the available source skills.

Display the found skills to the user:

Found skills in <REPO_URL>/skills/:
  - <skill-1>
  - <skill-2>
  ...

Step 3 — Determine Skill → Plugin Mappings

For each skill found, determine:

  1. Output skill name — usually the same as the source skill name (identity mapping). Ask the user if they want to rename any skill.
  2. Target plugin — which plugins/<plugin>/ directory the skill should go into.

Read scripts/cli.ts to see existing SKILL_TO_PLUGIN entries and existing plugins in plugins/.

Read the full file on GitHub · 229 lines

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. 2d ago First seen · 229 lines · 0 tokens per session scan A 1f08251d85d5

Subscribe to this mod's changes

add-vendor is a command published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 7d ago), licensed MIT. It adds 41 tokens to every session and 1,836 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.