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 commands/khadinakbarlabs/shopify-app-builder/graphqlgit clone --depth 1 https://github.com/khadinakbarlabs/shopify-app-builderWrote 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/khadinakbarlabs/shopify-app-builder/graphql)<a href="https://agentmods.dev/commands/khadinakbarlabs/shopify-app-builder/graphql"><img src="https://agentmods.dev/badge/commands/khadinakbarlabs/shopify-app-builder/graphql.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 | $0.00019 | $0.00645 |
| Opus 5 | $0.00010 | $0.00322 |
| Sonnet 5 | $0.00004 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
graphql 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 5d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Admin GraphQL Operations
You are constructing Admin GraphQL queries and mutations with cost optimization. Confirm the latest stable API version before generating the endpoint.
Query Planning
-
Select operation type and resources
- Query operations: products, orders, customers, inventory, fulfillments
- Mutation operations: updateProduct, createOrder, updateInventory, addFulfillment
- Confirm the latest stable API version and the store plan's cost restore rate (standard: 100 points/second)
- Reference skill: GraphQL operations (02_apis.md)
-
Design query structure
- Request only necessary fields (don't use fragments initially for clarity)
- Use pagination with first:25, after: "[cursor]" for large result sets
- Add filters for specific resource lookups (e.g., query: "status:active")
- Minimize nested relationships to reduce query cost
- Reference skill: query optimization (02_apis.md)
-
Calculate query cost
- Use query complexity algorithm: each field has cost value
- Simple fields (id, title) = 1 point; connections (products) = depends on requested count
- Example: products(first:25) with 5 fields per product ≈ 75 points
- Keep queries under 800 points for safety margin
- Reference skill: cost calculation (02_apis.md)
Implementation
-
Build GraphQL request
- Use GraphQL client library (Apollo Client or @shopify/graphql-request)
- Construct operation string with query/mutation definition
- Add variables object for dynamic parameters (e.g., productId, input data)
- Include error handling for rate limit responses (HTTP 429)
-
Execute and handle responses
- Send POST request to
https://[store-domain]/admin/api/2026-07/graphql.json, after confirming2026-07is still supported - Include X-Shopify-Access-Token header with session token
- Parse response.data for successful operations
- Log response.extensions.cost for monitoring (track cumulative daily cost)
- Reference skill: API versioning (02_apis.md)
- Send POST request to
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.
- 5d ago First seen · 65 lines · 19 tokens per session scan A 5fc9d8115d88
graphql is a command published in the GitHub repository khadinakbarlabs/shopify-app-builder (1 stars, last pushed 26d ago), licensed MIT. It adds 19 tokens to every session and 645 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
tray-referencia-api
Referência rápida de todos os endpoints da API da Tray, aceita nome do recurso como filtro.
sm-search
Ad-hoc semantic search over the supamem dual-memory collection.
project_init
이 프로젝트를 ocul-pm 추적 대상으로 초기화 (.oculpm/ + 기록 규칙 생성) — 사용자가 직접 실행하는 명시적 시작.
analysis-next
Advance the current analysis to the next ALIVE stage.
analysis-retro
Generate an automatic retrospective report from archived analyses.
analysis-search
Deep search across all analyses — full-text, context display, and pattern analysis.