use-context7

A rule for using Context7, a documentation service that provides current library APIs, syntax, and examples. It tells the coding agent to check there when it is unsure or when a library version may have changed.

In plain words
What is it for?
Checking uncertain library behavior, version-specific syntax, configuration, or usage patterns when the project already provides the needed code or documentation.
Why use it?
It helps avoid guessing about APIs from possibly outdated knowledge. This is especially useful for newer library releases and exact code examples.

Cursor rule

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 rules/upstash/context7/use-context7
Clone the repo
git clone --depth 1 https://github.com/upstash/context7
Per session 199 This file is loaded in full into every session.
When invoked 199 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 $0.00199 $0.00199
Opus 5 $0.00100 $0.00100
Sonnet 5 $0.00040 $0.00040
Haiku 4.5 $0.00020 $0.00020

Measured yesterday against content hash c476645d52c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

use-context7 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 yesterday.

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.

plugins/cursor/context7/rules/use-context7.mdc · 19 lines

What it actually says

When you're unsure about a library's API, syntax, configuration, or behavior, use Context7 to fetch current documentation rather than guessing from training data that may be outdated.

Use Context7 when:

  • You're not confident about the exact API or syntax for a library
  • The user asks about a specific version (e.g., "Next.js 15", "React 19")
  • The library or framework has had recent major changes
  • You need accurate code examples for a specific use case

You don't need to use Context7 for:

  • Well-established language features (e.g., JavaScript array methods, Python builtins)
  • Conversations where the user has already provided the relevant code or docs

See the context7-docs-lookup skill for detailed instructions on how to resolve libraries and fetch documentation.

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. yesterday First seen · 19 lines · 199 tokens per session scan A c476645d52c7

Subscribe to this mod's changes

use-context7 is a cursor rule published in the GitHub repository upstash/context7 (61,442 stars, last pushed today), licensed MIT. It adds 199 tokens to every session, about $0.0010 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.