drupal-update

drupal-update is a skill for Claude Code, Codex from trebormc/drupal-ai-agents. It costs 53 tokens per session (1,077 once invoked), scanned A, original, Apache-2.0.

A controlled workflow for updating Drupal core, contributed modules, and security fixes. It covers checks, backups, Composer package updates, database updates, configuration syncing, and rollback preparation.

In plain words
What is it for?
Use it for routine Drupal maintenance, security patches, Composer updates, database updates, and configuration deployment.
Why use it?
It places safety checks and a verified database backup before package or site changes. The workflow stops when the working tree, environment, or database is not ready.

Skill for Claude CodeCodex

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 skills/trebormc/drupal-ai-agents/drupal-update
Any agent
npx skills add trebormc/drupal-ai-agents --skill drupal-update
Clone the repo
git clone --depth 1 https://github.com/trebormc/drupal-ai-agents

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.

agentmods badge for drupal-update

README.md
[![agentmods](https://agentmods.dev/badge/skills/trebormc/drupal-ai-agents/drupal-update.svg)](https://agentmods.dev/skills/trebormc/drupal-ai-agents/drupal-update)
Your own site
<a href="https://agentmods.dev/skills/trebormc/drupal-ai-agents/drupal-update"><img src="https://agentmods.dev/badge/skills/trebormc/drupal-ai-agents/drupal-update.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,077 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 $0.00053 $0.01077
Opus 5 $0.00026 $0.00539
Sonnet 5 $0.00011 $0.00215
Haiku 4.5 $0.00005 $0.00108

Measured 3d ago against content hash f29d62cc7f9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

drupal-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 3d 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/skills/drupal-update/SKILL.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drupal Update Workflow

Execute updates following this EXACT sequence.

Phase 1: Pre-flight Checks

# Verify DDEV and Drupal version
ssh web drush status --field=drupal-version

# Check for uncommitted changes (STOP if dirty)
git status --porcelain

# Check available updates
ssh web composer outdated --direct --format=json

# Check for pending database updates (should be clean)
ssh web drush updatedb:status

STOP if: Git working directory is dirty, DDEV not responding, or pending DB updates exist.

Phase 2: Backup

ssh web drush sql:dump --result-file=/tmp/pre-update-backup.sql --gzip
git rev-parse HEAD  # Note for rollback

# VERIFY the backup before continuing (file exists and is non-empty):
ssh web test -s /tmp/pre-update-backup.sql.gz && echo "BACKUP OK" || echo "STOP: backup failed"

If the output is not "BACKUP OK": STOP. Tell the user the backup failed. Do NOT continue the update.

Phase 3: Composer Updates

Pick ONE variant:

# Update everything — routine maintenance window, full regression test planned
ssh web composer update --with-all-dependencies

# Core only — when you only want the Drupal core release (safest scope)
ssh web composer update "drupal/core-*" --with-all-dependencies

# Specific package — targeted fix or single contrib update
ssh web composer update drupal/package_name --with-all-dependencies

# Security only — when the goal is just to patch advisories
ssh web composer audit
ssh web composer update --with-all-dependencies $(ssh web composer audit --format=json | jq -r '.advisories | keys | .[]')

Phase 4: Database Updates

ssh web drush updatedb -y
ssh web drush cache:rebuild

Phase 5: Configuration Sync

ssh web drush config:status
ssh web drush config:export -y

Phase 6: Verification

ssh web drush core:status
ssh web drush watchdog:show --severity=error --count=10
ssh web drush core:requirements

# Run custom module tests if any exist (Form ROOT shown; if no project phpunit.xml,
# use the canonical Form CORE pattern from the drupal-testing skill):
ssh web ./vendor/bin/phpunit $DDEV_DOCROOT/modules/custom --testdox 2>/dev/null || echo "No tests"

Read the full file on GitHub · 144 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. 3d ago First seen · 144 lines · 53 tokens per session scan A f29d62cc7f9e

Subscribe to this mod's changes

drupal-update is a skill published in the GitHub repository trebormc/drupal-ai-agents (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,077 once invoked, about $0.0003 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens