Copilot-Skills context7.instructions.md

Copilot-Skills context7.instructions.md is an instructions file for GitHub Copilot from TheSethRose/Copilot-Skills. It costs 2,321 tokens per session, scanned A, original, MIT.

Instructions for retrieving current documentation for software libraries through Context7. Library documentation explains how to install and use a programming library.

In plain words
What is it for?
Use it when you need documentation for a library, want to find the right library entry, or need version-specific usage details.
Why use it?
It reduces the risk of relying on outdated documentation when libraries change between versions.

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/thesethrose/copilot-skills/context7
Clone the repo
git clone --depth 1 https://github.com/TheSethRose/Copilot-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 Copilot-Skills context7.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/thesethrose/copilot-skills/context7.svg)](https://agentmods.dev/instructions/thesethrose/copilot-skills/context7)
Your own site
<a href="https://agentmods.dev/instructions/thesethrose/copilot-skills/context7"><img src="https://agentmods.dev/badge/instructions/thesethrose/copilot-skills/context7.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,321 This file is loaded in full into every session.
When invoked 2,321 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 $0.02321 $0.02321
Opus 5 $0.01161 $0.01161
Sonnet 5 $0.00464 $0.00464
Haiku 4.5 $0.00232 $0.00232

Measured 3d ago against content hash 73d6a2364ed0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Copilot-Skills context7.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 3d 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/context7.instructions.md · 352 lines

How it starts

The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context7 - Automatic Context Instructions

Related Prompt: /context7
Related Skill: .github/copilot-skills/documentation/context7/

Triggers: context7, up-to-date docs, latest documentation, library documentation, resolve library, get docs

Context: Up-to-Date Library Documentation

When working with library documentation or when user queries mention getting current docs, this context is automatically activated.

Core Principles

Always Use Current Documentation

  • Never rely on outdated docs from training data
  • Always check Context7 first for library information
  • Verify versions - libraries change rapidly
  • Trust scores matter - prefer 7-10 range

Progressive Documentation Retrieval

  1. Start broad - Resolve library ID first
  2. Get specific - Request docs with focused topics
  3. Iterate - Refine topic if results aren't helpful
  4. Cache - Remember frequently used patterns

Default Behaviors

When user mentions "need docs for {library}"

  1. Suggest /context7 skill prompt
  2. Call resolve-library-id with library name
  3. Show top 3-5 matches with trust scores
  4. Ask user to confirm which library
  5. Fetch docs with relevant topic

When user mentions "latest {library} features"

  1. Resolve library ID
  2. Check for version information
  3. Get docs with topic "new features" or "changelog"
  4. Highlight recent updates
  5. Compare with older versions if available

When enhancing a skill

  1. Identify which libraries the skill covers
  2. Resolve IDs for each library
  3. Fetch current documentation
  4. Update patterns.md with latest examples
  5. Refresh reference.md with current APIs
  6. Note the update date and Context7 source

When user asks "which library should I use"

  1. Resolve multiple candidate libraries
  2. Compare trust scores
  3. Compare snippet counts (coverage indicator)
  4. Fetch brief docs for top candidates
  5. Present comparison table
  6. Recommend based on use case + trust + coverage

Quality Guidelines

Read the full file on GitHub · 352 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. 3d ago First seen · 352 lines · 2,321 tokens per session scan A 73d6a2364ed0

Subscribe to this mod's changes

Copilot-Skills context7.instructions.md is an instructions file published in the GitHub repository TheSethRose/Copilot-Skills (3 stars, last pushed 8mo ago), licensed MIT. It adds 2,321 tokens to every session, about $0.0116 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.