Claude Agent SDK for Python is a Python interface for querying and interacting with Claude Code, an AI coding agent that can read, edit, and run commands in a project. Developers use it to build interactive Claude-powered applications with custom tools and hooks. The catalogue add-ons provide commands, agents, hooks, instructions, skills, plugins, and settings for Claude Code workflows.
Borrowing it
Nothing to install: this file belongs to anthropics/claude-agent-sdk-python. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/anthropics/claude-agent-sdk-python/main/CLAUDE.mdgit clone --depth 1 https://github.com/anthropics/claude-agent-sdk-pythonWrote 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.
[](https://agentmods.dev/instructions/anthropics/claude-agent-sdk-python/claude-md)<a href="https://agentmods.dev/instructions/anthropics/claude-agent-sdk-python/claude-md"><img src="https://agentmods.dev/badge/instructions/anthropics/claude-agent-sdk-python/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.
<a href="https://agentmods.dev/instructions/anthropics/claude-agent-sdk-python/claude-md"><img src="https://agentmods.dev/badge/instructions/anthropics/claude-agent-sdk-python/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00995 | $0.00995 |
| Opus 5.5 | $0.00398 | $0.00398 |
| Sonnet 5.5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
claude-agent-sdk-python 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 19d 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow
# Lint and style
# Check for issues and fix automatically
python -m ruff check src/ tests/ scripts/ --fix
python -m ruff format src/ tests/ scripts/
# Typecheck
python -m mypy src/ scripts/
# Run all tests
python -m pytest tests/
# Run specific test file
python -m pytest tests/test_client.py
Codebase Structure
src/claude_agent_sdk/- Main packageclient.py- ClaudeSDKClient for interactive sessionsquery.py- One-shot query functiontypes.py- Type definitions_internal/- Internal implementation detailstransport/subprocess_cli.py- CLI subprocess managementmessage_parser.py- Message parsing logic
Security hardening for GitHub Actions
Workflow jobs in this repository that call Claude run with three protections. Keep them when you add or edit a workflow.
- Egress-firewall runner. The job has
runs-on: ubuntu-24.04-firewall, a GitHub-hosted runner that filters the job's outbound network traffic. Do not move a job that calls Claude to another runner. - Network allow list.
.github/egress-firewall.yamllists the hosts those jobs may reach, besides any that GitHub's firewall allows by default. Keepmode: enforce, which is what makes the firewall block the rest. Follow that file's header when you add a host. - Auto permission mode. Every step that runs the Claude Code action
(
uses: anthropics/claude-code-action, or a local action with aclaude_argsinput) passes--permission-mode autoinclaude_args. A tool call that needs permission and that the allowed tools do not cover then runs only if Claude Code's safety review passes it. Allow only the tools the job needs, and keep any--disallowedToolslist a step has. Useclaude-opus-4-6or a newer model: on an older one Claude Code falls back to its default permission mode.
claude.yml answers @claude mentions. The Claude Code action sets
--permission-mode acceptEdits for those, and the --permission-mode auto in
the workflow's claude_args, which comes after it, replaces it.
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.
- 19d ago Changed · +55 lines · +815 tokens per session 3e7b306e9e96
- 1mo ago First seen · 28 lines · 180 tokens per session scan A 7aaff076c597
claude-agent-sdk-python CLAUDE.md is an instructions file published in the GitHub repository anthropics/claude-agent-sdk-python (8,301 stars, last pushed today), licensed MIT. It adds 995 tokens to every session, about $0.0040 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.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.