What is upgrade-automation?

An automation review skill that checks new Claude Code and Anthropic features and assesses whether they could improve a company's automation. It considers effort, stability, compatibility, and potential value before recommending action.

Use it for periodic reviews of Claude Code releases, documentation, and related announcements, followed by adoption recommendations or upgrades.

It provides a recurring way to find relevant platform changes instead of relying on occasional manual checks or adopting features without evaluating their fit.

upgrade-automation — Skill for Claude Code and Codex by JOINCLASS

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.

Any agent

npx skills add JOINCLASS/ai-ceo-framework --skill upgrade-automation

Clone the repo

git clone --depth 1 https://github.com/JOINCLASS/ai-ceo-framework

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/joinclass/ai-ceo-framework/upgrade-automation/github.svg)](https://agentmods.dev/skills/joinclass/ai-ceo-framework/upgrade-automation)

Your own site

<a href="https://agentmods.dev/skills/joinclass/ai-ceo-framework/upgrade-automation"><img src="https://agentmods.dev/badge/skills/joinclass/ai-ceo-framework/upgrade-automation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/joinclass/ai-ceo-framework/upgrade-automation"><img src="https://agentmods.dev/badge/skills/joinclass/ai-ceo-framework/upgrade-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 565 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00565
Opus 5.5	$0.00000	$0.00226
Sonnet 5.5	$0.00000	$0.00113
Haiku 4.5	$0.00000	$0.00056

Measured 1mo ago against content hash 62a92d3458c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

upgrade-automation 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 1mo 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.

skills/upgrade-automation/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/upgrade-automation -- Automation Upgrade Skill

Periodically check for new Claude Code and Anthropic features, identify those applicable to your automation, and propose/implement upgrades.

Information Sources

Anthropic Blog: https://www.anthropic.com/news
Claude Code Documentation: https://docs.anthropic.com/en/docs/claude-code
Claude Code Release Notes: Check claude --version
GitHub: https://github.com/anthropics
Community articles: Claude Code tags on dev platforms
Social media: @AnthropicAI official posts

Evaluation Criteria

Rate each new feature on 5 dimensions (10 points each, 50 total):

Dimension	What to Evaluate
Automation impact	How much manual work does this eliminate?
Adoption cost	Implementation time and complexity
Stability	Preview/beta vs. stable release
System compatibility	How easily does it integrate with current AI-CEO Framework?
Content value	Could this become an article or book topic?

30+ points -> Recommend adoption 20-29 points -> Consider 19 or below -> Skip

Workflow

Periodic Check (weekly)

1. Run `claude --version` to check current version
2. Compare with last checked version
3. If new features found:
   a. Research feature details
   b. Score on 5 dimensions
   c. Create adoption proposal for features scoring 30+
   d. Notify CEO
4. Record results in .company/departments/dev/upgrade-log.md

Adoption Execution

1. After proposal is approved (or auto-approve policy applies)
2. Update existing scripts, agents, and skills
3. Run tests
4. Report completion (update STATE.md)

Features to Watch

Category	Current Usage	Upgrade Opportunity
Hooks	Basic event-driven	New hook event types
Skills	Defined skills	New skill capabilities (args, chaining)
MCP	External tool integration	New MCP servers, protocol extensions
Agent Teams	Not yet used	Multi-agent coordination
Dispatch	Not yet used	Mobile task delegation
Remote Control	Not yet used	Remote operations
Model updates	Current model	Performance improvements

Read the full file on GitHub · 75 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.

1mo ago First seen · 75 lines · 0 tokens per session scan A 62a92d3458c1

Subscribe to this mod's changes

upgrade-automation is a skill published in the GitHub repository JOINCLASS/ai-ceo-framework (61 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 565 tokens. 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 2026-09-26.

Building agents

upgrade-automation next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
upgrade-automationJOINCLASS/ai-ceo-framework	Skill	61	yesterday	MIT	A	0	Claude Code, Codex
imagegenopenai/codex	Skill	135k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	100k	today	Apache-2.0	A	19	Claude Code
browser-automationopenclaw/openclaw	Skill	394k	today	MIT	A	36	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	5d ago	MIT	A	200	Claude Code, Codex
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
systematic-debuggingobra/superpowers	Skill	316k	8d ago	MIT	A	21	Claude Code