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/log-session)<a href="https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/log-session"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/log-session/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.
<a href="https://agentmods.dev/commands/jameywarren/shopify-claude-quickstart/log-session"><img src="https://agentmods.dev/badge/commands/jameywarren/shopify-claude-quickstart/log-session.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00011 | $0.00655 |
| Opus 5.5 | $0.00004 | $0.00262 |
| Sonnet 5.5 | $0.00002 | $0.00131 |
| Haiku 4.5 | $0.00001 | $0.00065 |
Grade A, and why
log-session 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.
What it actually says
Before writing the log, gather context automatically:
- Run
git log --oneline -5if git is available — use this as the primary record of what was pushed/changed this session - Run
git diff --stat HEADto see any uncommitted local changes - Use
shopify-plugin:shopify-admin-executionto query current themes and identify the dev theme used this session and whether anything was pushed to the live theme:{ themes(first: 20) { nodes { id name role } } } - Read
docs/session-activity.logif it exists — the last SESSION START block shows how many turns this session had - Read
docs/session-log.mdto see the last entry (so you don't duplicate)
Then ask the user one question: "What should I know about this session that git can't tell me?" Wait for their answer before writing.
Now append a new entry into the Current Sprint section of docs/session-log.md (newest at the top of that section):
## YYYY-MM-DD — [Brief Session Title]
### What We Did
- [specific actions, files touched, commands run]
### Theme State
- Dev theme ID used: gid://shopify/OnlineStoreTheme/___
- Backup theme created: (gid://... or none)
- Pushed to live theme: Y / N
### Decisions Made
- [Decision] — **Why:** [rationale]
### Open Questions
-
### Blocked On
- (waiting on client assets / collaborator access / etc. — or "nothing")
### Next Session
- **Start here:** [the single first action]
Keep it dense. Name files and section names instead of "updated some stuff." Every Decisions Made entry must have a Why.
If the Current Sprint section has more than 3 entries, move the oldest one to the Archive section at the bottom.
After writing the log entry, append a SESSION END: [timestamp] line to docs/session-activity.log so the next session starts clean.
Commit the session log (if git is available)
Check if git is initialized:
git rev-parse --is-inside-work-tree 2>/dev/null && echo "git:yes" || echo "git:no"
If git is available, stage and commit the session log:
git add docs/session-log.md docs/session-activity.log
git commit -m "session: YYYY-MM-DD — [same title as log entry]
Co-Authored-By: Claude Sonnet 4.6 <[email protected]>"
git push 2>/dev/null || true
Use the exact date and title from the log entry. The git push is best-effort — if no remote is connected yet, that's fine.
If git is not available, skip the commit step. The log file is the only record — remind the user to consider running /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.
- 1mo ago First seen · 77 lines · 11 tokens per session scan A f8f2b7b94f02
log-session is a command published in the GitHub repository jameywarren/shopify-claude-quickstart (2 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 655 once invoked, about $0.0000 per session on Opus 5.5. 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
ws
Word summary — anything told at N levels, from N words down to 1 word, for anything: a topic ("russian literature"), a URL, YouTube link, file, pasted text, a question, or "this". A leading number sets N (5 by default). Shortcut for the Fabric skill's WordSummary intent.
cancel-ralph
Cancel active Ralph Loop.
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
r
Resume the last handoff and carry on with the outstanding work.
focus
You are an ADHD focus assistant. Help the user commit to ONE task and block mental distractions.
stuck
You are an ADHD-friendly unblocking assistant. Help users get unstuck when they don't know what to do.