shopify-operations-mcp AGENTS.md

shopify-operations-mcp AGENTS.md is an instructions file for Codex, OpenCode from jpka/shopify-operations-mcp. It costs 565 tokens per session, scanned A, original, MIT.

A set of instructions for coding agents working on a Shopify operations server. It explains how to track work in GitHub Issues, make changes through pull requests, and handle Shopify writes with approval and audit steps.

In plain words
What is it for?
Use it when implementing or verifying tickets in the Shopify operations project, opening and merging pull requests, monitoring checks, and documenting completed work.
Why use it?
It gives the agent a defined process for making and reviewing repository changes safely. This helps prevent direct changes to the main code branch and records what was done.

Instructions file for CodexOpenCode

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 instructions/jpka/shopify-operations-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/jpka/shopify-operations-mcp

Made for: Codex, OpenCode.

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 shopify-operations-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jpka/shopify-operations-mcp/agents-md.svg)](https://agentmods.dev/instructions/jpka/shopify-operations-mcp/agents-md)
Your own site
<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>
Per session 565 This file is loaded in full into every session.
When invoked 565 The same file — it is already loaded in full.
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 $0.00565 $0.00565
Opus 5 $0.00282 $0.00282
Sonnet 5 $0.00113 $0.00113
Haiku 4.5 $0.00056 $0.00056

Measured 4d ago against content hash 596338fad0f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 21 lines

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 @me before 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, then gh pr merge --squash --delete-branch.
  • Put Closes #n in 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). Drop needs-triage when a ticket is ready.
  • Verify before opening a PR: npm run lint (tsc --noEmit) and npm 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-core is a file: 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 trackergh CLI 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.

Read the full file on GitHub · 21 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. 4d ago First seen · 21 lines · 565 tokens per session scan A 596338fad0f2

Subscribe to this mod's changes

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.