agent-update-distribution

agent-update-distribution is a skill for Claude Code from phazurlabs/install-labs. It costs 78 tokens per session (2,444 once invoked), scanned A, original, Apache-2.0.

Guidance for updating and distributing AI agents, automation tools, and MCP servers. MCP is a standard way for an AI client to connect to external tools and data.

In plain words
What is it for?
Use it to plan pinned or automatic updates, version agent and plugin releases, set minimum supported host versions, and handle migrations or rollbacks.
Why use it?
It helps developers choose how updates arrive, manage version compatibility, and reduce the risk that a breaking change reaches users unexpectedly.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; positional $N argument; mentions Claude Code.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python /app/migrations/run.py "$CURRENT" "$TARGET".

Part of the install-labs plugin — 12 skills, 10 commands shipped together

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/phazurlabs/install-labs
agentmods
npx agentmods add skills/phazurlabs/install-labs/agent-update-distribution

Made for: Claude Code.

Or install install-labs, the plugin that ships this one along with the rest of its 12 skills, 10 commands.

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 agent-update-distribution

README.md
[![agentmods](https://agentmods.dev/badge/skills/phazurlabs/install-labs/agent-update-distribution.svg)](https://agentmods.dev/skills/phazurlabs/install-labs/agent-update-distribution)
Your own site
<a href="https://agentmods.dev/skills/phazurlabs/install-labs/agent-update-distribution"><img src="https://agentmods.dev/badge/skills/phazurlabs/install-labs/agent-update-distribution.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,444 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00078 $0.02444
Opus 5 $0.00039 $0.01222
Sonnet 5 $0.00016 $0.00489
Haiku 4.5 $0.00008 $0.00244

Measured 6d ago against content hash 084f40fedddb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-update-distribution scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

resp = requests.get(UPDATE_CHECK_URL, timeout=3)
skills/agent-update-distribution/SKILL.md · 320 lines

How it starts

The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Update & Distribution

MCP Server Updates

npx Always-Latest Pattern

{ "mcpServers": { "my-agent": { "command": "npx", "args": ["-y", "@your-org/my-agent-mcp"] } } }

Pros: Users always get the latest. No update command needed. Cons: Breaking changes hit immediately. No offline support. Slower startup.

Pinned Install

npm install -g @your-org/[email protected]   # exact version
npm update -g @your-org/my-agent-mcp           # update explicitly

Version Pinning in MCP Config

  • @2.1.0 -- exact version, never auto-updates
  • @^2.0.0 -- allows minor/patch within major 2
  • @latest or omitted -- always fetches newest

Claude Code Plugin Updates

Git-Based Plugins

cd ~/.claude/plugins/my-agent-plugin
git pull origin main
./install.sh                   # if plugin has install script
npm install                    # if it has JS dependencies

Versioning in plugin.json

{ "name": "my-agent-plugin", "version": "2.3.1", "minClaudeCodeVersion": "1.5.0" }

Bump version on every release. Set minClaudeCodeVersion to block incompatible hosts. Tag in git: git tag v2.3.1 && git push --tags.

Self-Updating Plugin Pattern

#!/bin/bash
# commands/update/run.sh
PLUGIN_DIR="$(dirname "$(dirname "$(realpath "$0")")")"
cd "$PLUGIN_DIR"
echo "Current: $(jq -r .version plugin.json)"
git fetch origin main
LOCAL=$(git rev-parse HEAD); REMOTE=$(git rev-parse origin/main)
if [ "$LOCAL" = "$REMOTE" ]; then echo "Up to date."
else git pull origin main; echo "Updated to: $(jq -r .version plugin.json)"; fi

Docker Agent Updates

Image Tagging Strategy

docker build -t my-agent:2.3.1 -t my-agent:2.3 -t my-agent:2 -t my-agent:latest .
  • 2.3.1 -- immutable, never changes after push
  • 2.3 / 2 -- mutable, points to latest in that range
  • latest -- newest release

Docker Compose Update Flow

docker compose pull && docker compose up -d
docker compose logs --tail 20 my-agent   # verify

Read the full file on GitHub · 320 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. 6d ago First seen · 320 lines · 78 tokens per session scan A 084f40fedddb

Subscribe to this mod's changes

agent-update-distribution is a skill published in the GitHub repository phazurlabs/install-labs (3 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 2,444 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.