skills apollo-client-skill.instructions.md

skills apollo-client-skill.instructions.md is an instructions file for GitHub Copilot from apollographql/skills. It costs 1,044 tokens per session, scanned A, original, MIT.

Writing guidance for creating Apollo Client skills, with specific rules for explaining GraphQL fragments and code examples. Apollo Client is a tool for connecting frontend applications to GraphQL APIs.

In plain words
What is it for?
Use it when writing or reviewing instructions about Apollo Client, GraphQL fragments, code examples, or external references.
Why use it?
It prevents documentation from presenting fragments as generic reusable pieces when their main purpose is to keep each component's data needs local. It also keeps explanations aligned with the project's stated conventions.

Instructions file for GitHub Copilot

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/apollographql/skills/apollo-client-skill
Clone the repo
git clone --depth 1 https://github.com/apollographql/skills

Made for: GitHub Copilot.

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 skills apollo-client-skill.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/apollographql/skills/apollo-client-skill.svg)](https://agentmods.dev/instructions/apollographql/skills/apollo-client-skill)
Your own site
<a href="https://agentmods.dev/instructions/apollographql/skills/apollo-client-skill"><img src="https://agentmods.dev/badge/instructions/apollographql/skills/apollo-client-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,044 This file is loaded in full into every session.
When invoked 1,044 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 $0.01044 $0.01044
Opus 5 $0.00522 $0.00522
Sonnet 5 $0.00209 $0.00209
Haiku 4.5 $0.00104 $0.00104

Measured 4d ago against content hash d159ad3853a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills apollo-client-skill.instructions.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.

.github/instructions/apollo-client-skill.instructions.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apollo Client Skill Writing Instructions

Follow these rules when working on the Apollo Client AI skill instructions.

General rules

  • Do not make time-relative statements about the library, like "now provides feature X". If the content is version-specific, refer to the minimal version instead. Generally assume the user uses Apollo Client v4.x unless otherwise specified.

Rules for discussing fragments

Fragments are for colocation, not reuse. When discussing fragments, follow these guidelines based on GraphQL spec PR #1193:

  • DO NOT describe fragments as being "for reuse" or "reusable units"
  • DO NOT suggest sharing fragments between components just because they currently need the same fields
  • DO emphasize that fragments are for component colocation - each component should have its own fragment
  • DO explain that fragments enable independent evolution of component data requirements
  • DO explain that sharing fragments creates artificial dependencies and leads to over-fetching when one component's needs change

Example of correct messaging:

  • ✅ "Each component should declare its data needs in a dedicated fragment"
  • ✅ "Fragments enable components to independently evolve their data requirements"
  • ❌ "Fragments allow for the reuse of common repeated selections"
  • ❌ "Create a shared fragment for fields used by multiple components"

Rules for code examples

  • always ensure correct imports
    • imports should be complete for the example
    • React hooks need to be imported from @apollo/client/react, NOT from @apollo/client
  • when an example needs a query, mutation, or fragment, use either of the following approaches:
    • in-example declaration
      • use the gql tag from @apollo/client to define queries/mutations/fragments
      • create a constant with an uppercase name (e.g., GET_USER, CREATE_POST)
      • declare types via TypedDocumentNode
    • import it from a generated file in the same directory as the example, treat it as a TypedDocumentNode with types defined:
      • queries.generated.ts for queries
      • mutations.generated.ts for mutations
      • fragments.generated.ts for fragments
  • always use TypeScript for code examples unless the context specifically calls for something else
  • React hooks should never be shown using explicit generics. Types should always be inferred from the typed query/mutation document.
    • do this: useQuery(GET_USER, { variables: { id: "1" } })
    • not this: useQuery<GetUserQuery, GetUserVariables>(GET_USER, { variables: { id: "1" } })
  • If both hooks appear in an example, ALWAYS call useQueryRefHandlers before useReadQuery. These two hooks interact with the same queryRef, and calling them in the wrong order could cause subtle bugs.

Read the full file on GitHub · 72 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 · 72 lines · 1,044 tokens per session scan A d159ad3853a8

Subscribe to this mod's changes

skills apollo-client-skill.instructions.md is an instructions file published in the GitHub repository apollographql/skills (110 stars, last pushed 1mo ago), licensed MIT. It adds 1,044 tokens to every session, about $0.0052 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 2026-08-30.