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.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 | $0.00011 | $0.00655 |
| Opus 5 | $0.00005 | $0.00328 |
| Sonnet 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 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 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.
- 7d 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 4mo ago), licensed MIT. It adds 11 tokens to every session and 655 once invoked, about $0.0001 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
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.