context7

A documentation lookup skill for current, version-specific instructions for libraries and frameworks. It can find APIs, setup guides, migration details, and answers to error messages.

In plain words
What is it for?
Use it when implementing or debugging library APIs, configuring frameworks, checking version changes, or finding official usage examples.
Why use it?
It helps avoid relying on outdated or guessed library behavior, especially when different versions work differently.

Skill for Claude CodeCodex

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 skills/mtnyilmaz/agents/context7
Any agent
npx skills add mtnyilmaz/agents --skill context7
Clone the repo
git clone --depth 1 https://github.com/mtnyilmaz/agents

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 900 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00033 $0.00900
Opus 5 $0.00016 $0.00450
Sonnet 5 $0.00007 $0.00180
Haiku 4.5 $0.00003 $0.00090

Measured 2d ago against content hash 277160621421, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/skills/context7/SKILL.md · 148 lines

How it starts

The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context7 — Up-to-Date Documentation Expert

Eliminate LLM hallucinations and outdated API usage with Context7. Expert in fetching live, version-specific documentation.

When to Use This Skill

  • When questions arise about library APIs
  • "How to do X?" questions
  • Setup/configuration guides
  • Version changelogs and migration guides
  • Searching for solutions to error messages

Setup

# Install Context7 CLI
npx ctx7 setup

# Or with API key
CONTEXT7_API_KEY=your-key ctx7 docs /vercel/next.js "app router"

Core Commands

Find a Library

ctx7 library nextjs "middleware authentication"
ctx7 library prisma "relation queries"
ctx7 library fastify "reply hooks"

Fetch Docs

# General query
ctx7 docs /vercel/next.js "server actions"
ctx7 docs /prisma/prisma "nested writes"
ctx7 docs /fastify/fastify "error handling"

# Version-specific
ctx7 docs /vercel/next.js@14 "caching"
ctx7 docs /vercel/next.js@15 "caching"   # different behavior!

MCP Tool Usage (if supported)

resolve-library-id:
  libraryName: "nextjs"
  query: "middleware jwt authentication"

query-docs:
  libraryId: "/vercel/next.js"
  query: "middleware jwt authentication"

Ready IDs for Project Stack

# Frontend
ctx7 docs /vercel/next.js          "<query>"
ctx7 docs /tailwindlabs/tailwindcss "<query>"
ctx7 docs /shadcn-ui/ui            "<query>"
ctx7 docs /tanstack/query          "<query>"
ctx7 docs /tanstack/router         "<query>"
ctx7 docs /tanstack/table          "<query>"

# Backend
ctx7 docs /fastify/fastify         "<query>"
ctx7 docs /trpc/trpc               "<query>"
ctx7 docs /prisma/prisma           "<query>"

# Mobile
ctx7 docs /expo/expo               "<query>"
ctx7 docs /expo/router             "<query>"

# Auth & Infrastructure
ctx7 docs /better-auth/better-auth "<query>"
ctx7 docs /upstash/upstash-redis   "<query>"

# Email
ctx7 docs /resend/react-email      "<query>"

Workflow: When a Library Question Arrives

1. ctx7 library <name> <query>  → find ID
2. ctx7 docs <id> <query>       → fetch docs
3. Review the fetched documentation
4. Write the implementation
5. Add doc ID as reference

Read the full file on GitHub · 148 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 148 lines · 33 tokens per session scan A 277160621421

Subscribe to this mod's changes

context7 is a skill published in the GitHub repository mtnyilmaz/agents (6 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 900 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens