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.
npx agentmods add instructions/jpka/shopify-operations-mcp/agents-mdgit clone --depth 1 https://github.com/jpka/shopify-operations-mcpWrote 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/instructions/jpka/shopify-operations-mcp/agents-md)<a href="https://agentmods.dev/instructions/jpka/shopify-operations-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jpka/shopify-operations-mcp/agents-md.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 | $0.00565 | $0.00565 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
shopify-operations-mcp AGENTS.md 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 21 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
shopify-operations-mcp: a safe-write MCP server for Shopify operations, built on safe-write-mcp-core — plan-before-execute writes, out-of-band localhost approval, and audit hooks. Work is tracked as tickets in GitHub Issues (see the build map).
Working conventions
- Tickets live in GitHub Issues; claim one with
gh issue edit <n> --add-assignee @mebefore starting. - PR-first: any ticket that involves file edits is developed on a branch and merged via a GitHub PR — never push to main directly. Open the PR with
gh pr create, then babysit it: watch CI (gh pr checks <n> --watch --interval 10), address failures in new commits on the branch, re-watch until green, thengh pr merge --squash --delete-branch. - Put
Closes #nin the PR body so the ticket closes on merge; then post a resolution comment summarizing what was delivered and verified. - Triage labels:
needs-triage(maintainer must evaluate),needs-info(waiting on reporter),ready-for-agent(fully specified, ready for an AFK agent),ready-for-human(requires human implementation),wayfinder:map(parent tracking issue). Dropneeds-triagewhen a ticket is ready. - Verify before opening a PR:
npm run lint(tsc --noEmit) andnpm test(vitest) locally — CI runs the same on Node 24. - Delegate when it makes sense: break work into independent parallel tracks and hand each to a subagent (e.g. static lint/test/grep on one side, a live-store verification on another). Delegate when the tracks don't touch the same files or state; keep edits that depend on one another in the same hand.
safe-write-mcp-coreis afile:dependency until jpka/safe-write-mcp-core#7 publishes to npm; the registry dependency replaces it afterward.- Architectural decisions are recorded in
DECISIONS.md(newest first), in the style of sw-postgres-mcp.
Agent docs
- Issue tracker —
ghCLI conventions, the PR-first workflow, and the build map:docs/agents/issue-tracker.md. - Triage labels — the five canonical labels and when to apply them:
docs/agents/triage-labels.md. - Domain docs — what to read before exploring, and the codebase's vocabulary:
docs/agents/domain.md.
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.
- 4d ago First seen · 21 lines · 565 tokens per session scan A 596338fad0f2
shopify-operations-mcp AGENTS.md is an instructions file published in the GitHub repository jpka/shopify-operations-mcp (0 stars, last pushed 19d ago), licensed MIT. It adds 565 tokens to every session, about $0.0028 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 instructions, from other repositories
vibetags com-example-service-OrderService.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for orderservice, rules for method calculatetax, rules for method processpayment, rules for method validateorder and context & focus.
rubydex AGENTS.md
AGENTS.md instructions for Shopify/rubydex, covering instructions, project overview, documentation, ruby gem and structure.
hw-mcp CLAUDE.md
Instructions for Hertwill/hw-mcp, covering project, constraints, technology stack, executive recommendation and recommended stack.
VectorCart copilot-instructions.md
Copilot instructions for Rounit-1st/VectorCart, covering vectorcart shopping assistant — llm instructions, role, 1. understand the customer, 2. convert the request into search inputs and visual search query.
gengeo-agent-registry AGENTS.md
Instructions for warwickwood-cell/gengeo-agent-registry: GenGEO provides machine-readable merchant verification infrastructure for AI agents.
kronan-mcp CLAUDE.md
Instructions for sandsower/kronan-mcp, covering kronan-mcp, build, configure, usage in claude code and api reference.