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.
git clone --depth 1 https://github.com/jameywarren/shopify-claude-quickstartWrote 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.
[](https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/safe-push)<a href="https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/safe-push"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/safe-push.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00009 | $0.00643 |
| Opus 5 | $0.00005 | $0.00321 |
| Sonnet 5 | $0.00002 | $0.00129 |
| Haiku 4.5 | $0.00001 | $0.00064 |
Grade A, and why
safe-push 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 7d 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.
What it actually says
Before pushing any theme changes to the live theme, run through:
- Were changes tested on a dev theme first? (find recent
shopify theme push --themecommands indocs/session-log.md) - Are there console errors in any changed sections?
- Does the Liquid validate cleanly via
shopify-plugin:shopify-liquid? - Hardcoded strings that should be settings or translations?
- Missing schema translations for any new settings?
- Any in-flight metafield/metaobject changes that haven't been applied yet?
Report all issues. If all clear, confirm "ready to push" and output the exact push command for the live theme.
Push ordering — if pushing a section and a template that references it together:
Push in two steps. Shopify validates template JSON before resolving new section schemas, so pushing both at once can fail with a block-key error even when the files are correct.
# Step 1: section Liquid first
shopify theme push --path store-data/theme --store {STORE}.myshopify.com --theme LIVE_THEME_ID --force \
--only sections/changed.liquid
# Step 2: template JSON after
shopify theme push --path store-data/theme --store {STORE}.myshopify.com --theme LIVE_THEME_ID --force \
--only templates/changed.json
For unrelated files (no section/template dependency), a single push is fine:
shopify theme push --path store-data/theme --store {STORE}.myshopify.com --theme LIVE_THEME_ID --force \
--only sections/a.liquid sections/b.liquid
--forceis required for live theme pushes. Claude Code runs non-interactively — the Shopify CLI prompt "Push theme files to the live theme?" has no TTY to answer and exits with code 1.--forcebypasses it. Dev theme pushes don't need it.
The --path store-data/theme flag is required — omitting it causes "not in a theme directory" errors.
Do not push yourself — I push.
After the user confirms the push succeeded
Check if this project has a git remote:
git remote -v 2>/dev/null
If a remote exists — commit the pushed files automatically:
git add store-data/theme/
git status
Show the staged files, then commit with a message derived from what was pushed (use the filenames from the --only list):
git commit -m "theme: {brief description of what changed}
Co-Authored-By: Claude Sonnet 4.6 <[email protected]>"
git push
Example messages: theme: update hero subheading and CTA copy, theme: add ski landing page template, theme: fix product grid spacing on mobile.
If no remote exists — ask: "No GitHub repo connected yet. Want to run /github-setup to enable version history?"
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.
- 7d ago First seen · 71 lines · 9 tokens per session scan A aef53bb33fe8
safe-push is a command published in the GitHub repository jameywarren/shopify-claude-quickstart (2 stars, last pushed 4mo ago), licensed MIT. It adds 9 tokens to every session and 643 once invoked, about $0.0000 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.
Other commands, from other repositories
create_worktree_prompt
Create a git worktree with isolated configuration for parallel development.
list_worktrees_prompt
List all git worktrees with their configuration and status.
remove_worktree_prompt
Remove a git worktree, delete its branch, and stop its running services.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.