claude-plugin:update

A command for changing an existing Claude Code plugin by adding, modifying, or removing an agent, command, or skill.

In plain words
What is it for?
Use it to add new components, edit existing components, remove obsolete ones, or supply configuration such as an agent model and description.
Why use it?
It gives plugin updates a defined operation and checks that the target plugin and component are valid before changing them.

Command

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/geoffjay/claude-plugins/update
Clone the repo
git clone --depth 1 https://github.com/geoffjay/claude-plugins
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,562 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 $0.00019 $0.02562
Opus 5 $0.00010 $0.01281
Sonnet 5 $0.00004 $0.00512
Haiku 4.5 $0.00002 $0.00256

Measured 2d ago against content hash 9c5d350f4045, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-plugin:update 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.

plugins/claude-plugin/commands/update.md · 431 lines

How it starts

The opening of the file, as written. The whole thing — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Plugin Command

Update an existing Claude Code plugin by adding new components, modifying existing ones, or removing obsolete components.

Arguments

  • $1 - Plugin name (required, must exist in plugins/)
  • $2 - Update operation: add, modify, or remove (required)
  • $3 - Component type: agent, command, or skill (required)
  • $4 - Component name (required for modify/remove, optional for add)
  • $5 - Additional configuration as JSON (optional)

Usage

# Add a new agent to existing plugin
/claude-plugin:update golang-development add agent golang-testing

# Modify an existing command
/claude-plugin:update golang-development modify command golang-scaffold

# Remove a skill
/claude-plugin:update golang-development remove skill golang-patterns

# Add with configuration
/claude-plugin:update rust-development add agent rust-async '{"model":"claude-sonnet-4","description":"Async Rust expert"}'

Workflow

This command orchestrates plugin updates by:

  1. Validating Input

    • Verify plugin exists in plugins/ directory
    • Validate operation type (add/modify/remove)
    • Ensure component type is valid
    • Check component existence for modify/remove operations
  2. Gathering Requirements

    • For add: collect new component details
    • For modify: identify what needs to change
    • For remove: confirm removal and check dependencies
  3. Performing Update

    • Use Task tool with subagent_type="claude-plugin" to execute changes
    • Create, modify, or remove component files
    • Maintain spec compliance and naming conventions
  4. Updating Marketplace

    • Invoke marketplace-update skill to update plugin entry
    • Invoke documentation-update skill to regenerate docs

Implementation

Plugin Name: ${1:-"[REQUIRED]"} Operation: ${2:-"[REQUIRED: add|modify|remove]"} Component Type: ${3:-"[REQUIRED: agent|command|skill]"} Component Name: ${4:-"[REQUIRED for modify/remove]"} Configuration: ${5:-"{}"}

Read the full file on GitHub · 431 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 · 431 lines · 19 tokens per session scan A 9c5d350f4045

Subscribe to this mod's changes

claude-plugin:update is a command published in the GitHub repository geoffjay/claude-plugins (8 stars, last pushed 10mo ago), licensed MIT. It adds 19 tokens to every session and 2,562 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.