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/apollographql/skills/apollo-client-skillgit clone --depth 1 https://github.com/apollographql/skillsWrote 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/apollographql/skills/apollo-client-skill)<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>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 | $0.01044 | $0.01044 |
| Opus 5 | $0.00522 | $0.00522 |
| Sonnet 5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00104 | $0.00104 |
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.
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
gqltag from@apollo/clientto define queries/mutations/fragments - create a constant with an uppercase name (e.g.,
GET_USER,CREATE_POST) - declare types via
TypedDocumentNode
- use the
- import it from a generated file in the same directory as the example, treat it as a
TypedDocumentNodewith types defined:queries.generated.tsfor queriesmutations.generated.tsfor mutationsfragments.generated.tsfor fragments
- in-example declaration
- 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" } })
- do this:
- If both hooks appear in an example, ALWAYS call
useQueryRefHandlersbeforeuseReadQuery. These two hooks interact with the samequeryRef, and calling them in the wrong order could cause subtle bugs.
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 · 72 lines · 1,044 tokens per session scan A d159ad3853a8
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.
Other instructions, from other repositories
sdks AGENTS.md
AGENTS.md instructions for morpho-org/sdks, covering engineering rules, 1. architecture, layering: one direction, no exceptions, modularity: one reason to exist and testability: pure cores, i/o at the edge.
sdks CLAUDE.md
Claude Code instructions for morpho-org/sdks, a project described as: Typescript SDKs to interact with the Morpho protocols.
graphjin AGENTS.md
AGENTS.md instructions for dosco/graphjin, covering graphjin agent guide, architectural overview, directory structure & responsibilities, build commands and coding guidelines.
NornicDB AGENTS.md
Instructions for orneryd/NornicDB, covering nornicdb development guide for ai agents, core philosophy, 🎯 golden rules, 1. prove value before merging and 2. test-driven bug fixes.
api-gateway CLAUDE.md
Claude Code instructions for membrane/api-gateway, covering claude.md, git & commit policy, working principles, 1. think before coding and 2. simplicity first.
apollo-mcp-server AGENTS.md
AGENTS.md instructions for apollographql/apollo-mcp-server, covering claude.md, project overview, build & test commands, build and run all tests.