agentmods.dev

context-and-tools: Instructions file for Claude Code

CLAUDE.md

context-and-tools CLAUDE.md is an instructions file for Claude Code from netlify/context-and-tools. It costs 1,720 tokens per session, scanned A, original, MIT.

Repository instructions for Netlify’s public context and tools, including platform guidance, skills, agent-plugin files, and generated rules for coding assistants.

In plain words
What is it for?
Use them when maintaining Netlify guidance, skills, plugin manifests, MCP configuration, or scripts that generate editor rules.
Why use it?
They help contributors keep platform references and generated outputs consistent across supported agent formats. They also identify which files are sources and which are generated.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

This is netlify/context-and-tools's own configuration. It tells Claude Code how to work on context-and-tools itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything context-and-tools configures →

not rated 51repo +1 changed 15d ago A scan 1,720 tokens original MIT
View source ↗ netlify/context-and-tools
Reuse

Borrowing it

Nothing to install: this file belongs to netlify/context-and-tools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/netlify/context-and-tools/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/netlify/context-and-tools

Made for: Claude Code.

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 context-and-tools CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/netlify/context-and-tools/claude-md/github.svg)](https://agentmods.dev/instructions/netlify/context-and-tools/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/netlify/context-and-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/netlify/context-and-tools/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for context-and-tools CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/netlify/context-and-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/netlify/context-and-tools/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,720 This file is loaded in full into every session.
When invoked 1,720 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.01720 $0.01720
Opus 5.5 $0.00688 $0.00688
Sonnet 5.5 $0.00344 $0.00344
Haiku 4.5 $0.00172 $0.00172

Measured 15d ago against content hash 24bbc95ec3da, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

context-and-tools CLAUDE.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 15d 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.

CLAUDE.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Netlify Context and Tools

This repository contains public Netlify skills — factual platform reference for AI agents working with Netlify projects.

Repository Structure

  • context/ — Steering guides (e.g., POWER.md for Kiro deployments)
  • .claude-plugin/ — Plugin marketplace config for Claude Code installation (VS Code agent plugins share this format and auto-detect .claude-plugin/plugin.json; no VS-Code-specific mirror is generated)
  • .grok-plugin/ — Plugin manifest for Grok Build (same plugin format as Claude Code; hand-authored, not generated)
  • .antigravity-plugin/plugin.json — Google Antigravity plugin manifest (hand-authored; version stamped by release-please). Only the manifest lives in the dot-folder: Antigravity resolves skills/, mcp_config.json, and the Marketplace logo assets/logo.svg relative to the repo root. Check with agy plugin validate . (needs agy ≥ 1.4). Don't use --strict: newer agy warns that .mcp.json is never loaded (expected — it's the Claude Code/Grok config), and strict fails on any warning
  • mcp_config.json — Netlify MCP server config for Antigravity (serverUrl format; mirrors .mcp.json)
  • .mcp.json — Netlify MCP server config bundled with the Claude Code and Grok Build plugins (hosted HTTP endpoint; OAuth at runtime)
  • gemini-extension.json — Gemini CLI extension manifest. name, version (stamped by release-please), and mcpServers are hand-authored; the skills array is auto-generated from skills/ (do NOT edit it directly). Gemini CLI itself auto-discovers skills from the skills/ directory, so the array is informational (gallery listing, readers)
  • skills/ — Netlify platform skills (source of truth for all agent formats)
  • agent-plugin/ — Agent Plugins spec-compliant package (plugin.json + mcp.json + skills/). Root manifests are hand-authored; agent-plugin/skills/ is auto-generated (do NOT edit directly)
  • cursor/rules/ — Auto-generated Cursor .mdc rule files (do NOT edit directly)
  • codex/ — Auto-generated Codex skills and AGENTS.md router (do NOT edit directly)
  • scripts/build-cursor-rules.sh — Converts skills/ → cursor/rules/
  • scripts/build-codex-skills.sh — Copies skills/ → codex/ and generates AGENTS.md
  • scripts/build-agent-plugin.sh — Mirrors skills/ → agent-plugin/skills/
  • scripts/build-gemini-extension.sh — Rewrites the skills array in gemini-extension.json from skills/*/SKILL.md (sorted; requires jq)
  • scripts/check-skills.mjs — CI check that every skills/netlify-*/ folder is listed in skills/CLAUDE.md and contains only files the build scripts carry (SKILL.md plus flat references/*.md)
  • scripts/build-manifest.mjs — Generates manifest.json (skill names, statuses, per-skill version and history derived from git tags, prior names, per-file hashes, tree_hash, docs provenance) from skills/, .ctx-gen/, and skill-registry.json
  • scripts/build-hosted.mjs — Materializes every release tag into dist/ (manifest.json, skills/, versions.json, v/<version>/…) for the hosted site
  • scripts/fetch-skill.mjs — Zero-dependency reference client: install skills (--skill/--all) from a release directory (--source) or the hosted site (--host) with hash verification; --check a local skills dir against the manifest; --update applies the sync rules (stale → replace, modified → keep unless --reset, renamed → migrate, deprecated → delete, edited copies kept unless --reset)
  • bin/netlify-skills.mjs — The netlify-skills command shipped in @netlify/skills (npx @netlify/skills@latest add|check|update); installs from the package's own bundled release by default, --host for the hosted manifest, into the agent directory found in the project or the one --agent/--dest names; thin wrapper over fetch-skill.mjs
  • skill-registry.json — Hand-maintained prior names and deprecations that the manifest cannot derive from skills/
  • netlify.toml — Hosted-site config (publish dir, cache headers); deployed by .github/workflows/release-please.yml, not by a Git-connected build
  • .github/workflows/release-please.yml — Cuts releases and publishes each tag to npm (@netlify/skills, Trusted Publishing tied to this filename) and then to the hosted Netlify site; also the manual re-publish entry point, guarded to real release tags on main
  • .github/workflows/ctx-pipeline-sync-closed.yml — Reports to context-hub when the rolling agent-context sync PR is merged or closed (EX-3352), via scripts/ctx-hub-ping.mjs sync-pr-closed; pull_request_target limited to the sync branch from this repo, never checks out PR code, telemetry only (continue-on-error)
  • .github/workflows/build-generated-outputs.yml — Rebuilds cursor/, codex/, agent-plugin/skills/, and the gemini-extension.json skill list from skills/ and commits them in a single step (on push to main and on PRs), so the generated outputs always stay in parity with skills/

Read the full file on GitHub · 56 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. 15d ago Changed · +2 lines · +154 tokens per session 24bbc95ec3da
  2. 23d ago Changed · +1 lines · +80 tokens per session bdbbb6188a2d
  3. 1mo ago Changed · +1 lines · +94 tokens per session 1aae3be3b77e
  4. 1mo ago Changed · +9 lines · +485 tokens per session 65ea14f5d6f1
  5. 1mo ago Changed · +2 lines · +147 tokens per session 69dcdd4f4cf5
  6. 1mo ago Changed · +2 lines · +93 tokens per session 14f1cdf20715
  7. 2mo ago First seen · 39 lines · 667 tokens per session scan A d6a0017dea78

Subscribe to this mod's changes

context-and-tools CLAUDE.md is an instructions file published in the GitHub repository netlify/context-and-tools (51 stars, last pushed yesterday), licensed MIT. It adds 1,720 tokens to every session, about $0.0069 per session on Opus 5.5. 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.

Related

context-and-tools CLAUDE.md compared with instructions from other repositories

context-and-tools CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
context-and-tools CLAUDE.mdnetlify/context-and-toolsInstructions file51yesterdayMITA1,720Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode