agent-skills: Instructions file for Claude Code

CLAUDE.md

agent-skills CLAUDE.md is an instructions file for Claude Code from chroma-core/agent-skills. It costs 763 tokens per session, scanned A, original, MIT.

A project instruction file for Chroma's collection of AI-agent skills, which are documentation packages that help agents use Chroma's vector database.

In plain words
What is it for?
Building, creating, and validating Chroma agent skills and their TypeScript or Python examples.
Why use it?
It documents the build process, code-example checks, Python setup, and repository architecture needed to maintain the skills correctly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is chroma-core/agent-skills's own configuration. It tells Claude Code how to work on agent-skills 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 agent-skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chroma-core/agent-skills. 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/chroma-core/agent-skills/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chroma-core/agent-skills

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 agent-skills CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chroma-core/agent-skills/claude-md.svg)](https://agentmods.dev/instructions/chroma-core/agent-skills/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chroma-core/agent-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/chroma-core/agent-skills/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 763 This file is loaded in full into every session.
When invoked 763 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 5.1 $0.00763 $0.00763
Opus 5 $0.00381 $0.00381
Sonnet 5 $0.00153 $0.00153
Haiku 4.5 $0.00076 $0.00076

Measured 6d ago against content hash e45bf9761139, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-skills 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 6d 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 · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

This repository contains official AI Agent skills from the Chroma team. Skills are documentation packages that help AI agents integrate Chroma vector database into projects.

Commands

# Build skills (compiles templates + code examples into skills/ output)
bun run build

# Create new skill template (interactive or with --name and --description flags)
bun run new

# Validate code examples
npm run validate              # Both TypeScript and Python
npm run validate:typescript   # TypeScript only (uses npx tsc)
npm run validate:python       # Python only (uses .venv/bin/python)

# Set up Python virtual environment for validation
uv venv .venv && uv pip install -r requirements.txt

Architecture

Build System

The build process (scripts/build-skills.ts) transforms source files into distributable skills:

  1. Source location: src/<skill>/ contains skill-specific docs, templates, and code examples
  2. Composable sources: src/<skill>/skill.json can list layered source directories like ["chroma-shared", "chroma-local"]
  3. Shared content: src/chroma-shared/ contains docs and templates reused by multiple skills
  4. Override order: Later source directories override earlier ones when they define the same template or general doc
  5. Output location: skills/<skill>/ contains the built skill files
  6. Template processing: Templates in templates/*.md contain {{CODE:snippet-name}} placeholders
  7. Code snippets: Code files in code/{typescript,python}/ define snippets with @snippet:name and @end markers
  8. Build output: Each template generates two files: skills/<skill>/<topic>/typescript.md and python.md
  9. Registry output: The build also generates skills/registry.json, a machine-readable index of built skills, topics, and general docs

Directory Structure

src/chroma-shared/
├── templates/         # Shared markdown templates with {{CODE:*}} placeholders
└── general/           # Shared language-agnostic docs

src/<skill>/
├── skill.json         # Optional layered source config
├── SKILL.md           # Main skill description (copied to output with topic list appended)
├── templates/         # Skill-specific markdown templates
├── code/
│   ├── typescript/    # .ts files with @snippet markers
│   └── python/        # .py files with @snippet markers
└── general/           # Skill-specific language-agnostic docs

skills/<skill>/        # Built output (generated, don't edit directly)

Read the full file on GitHub · 92 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. 6d ago First seen · 92 lines · 763 tokens per session scan A e45bf9761139

Subscribe to this mod's changes

agent-skills CLAUDE.md is an instructions file published in the GitHub repository chroma-core/agent-skills (21 stars, last pushed 4mo ago), licensed MIT. It adds 763 tokens to every session, about $0.0038 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens