Skip to content

guanyang/open-agent-hub / skills/claude-api

claude-api

Unverified

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

FileKindSize
LICENSE.txtmarkdown11.1 KB
SKILL.mdskill md102.7 KB
csharp/claude-api.mdmarkdown15.3 KB
csharp/claude-api/README.mdmarkdown18.5 KB
csharp/claude-api/batches.mdmarkdown413 B
csharp/claude-api/files-api.mdmarkdown900 B
csharp/claude-api/streaming.mdmarkdown787 B
csharp/claude-api/tool-use.mdmarkdown7.4 KB
curl/examples.mdmarkdown9.5 KB
curl/managed-agents.mdmarkdown10.5 KB
go/claude-api.mdmarkdown14.4 KB
go/claude-api/README.mdmarkdown8.3 KB
go/claude-api/files-api.mdmarkdown936 B
go/claude-api/streaming.mdmarkdown1.0 KB
go/claude-api/tool-use.mdmarkdown9.8 KB
go/managed-agents/README.mdmarkdown21.9 KB
java/claude-api.mdmarkdown15.5 KB
java/claude-api/README.mdmarkdown11.7 KB
java/claude-api/files-api.mdmarkdown1.2 KB
java/claude-api/streaming.mdmarkdown655 B
java/claude-api/tool-use.mdmarkdown10.9 KB
java/managed-agents/README.mdmarkdown20.0 KB
php/claude-api.mdmarkdown11.5 KB
php/claude-api/README.mdmarkdown6.4 KB
php/claude-api/batches.mdmarkdown447 B
php/claude-api/files-api.mdmarkdown476 B
php/claude-api/streaming.mdmarkdown682 B
php/claude-api/tool-use.mdmarkdown9.5 KB
php/managed-agents/README.mdmarkdown16.2 KB
python/agent-sdk/README.mdmarkdown12.4 KB
python/agent-sdk/patterns.mdmarkdown9.0 KB
python/claude-api/README.mdmarkdown20.1 KB
python/claude-api/batches.mdmarkdown5.6 KB
python/claude-api/files-api.mdmarkdown4.4 KB
python/claude-api/sdk-upgrade.mdmarkdown28.1 KB
python/claude-api/streaming.mdmarkdown11.7 KB
python/claude-api/tool-use.mdmarkdown20.9 KB
python/managed-agents/README.mdmarkdown14.5 KB
ruby/claude-api.mdmarkdown3.4 KB
ruby/claude-api/README.mdmarkdown4.7 KB
ruby/claude-api/streaming.mdmarkdown235 B
ruby/claude-api/tool-use.mdmarkdown2.6 KB
ruby/managed-agents/README.mdmarkdown11.9 KB
shared/admin-api.mdmarkdown11.3 KB
shared/agent-design.mdmarkdown8.5 KB
shared/anthropic-cli.mdmarkdown23.4 KB
shared/claude-platform-on-aws.mdmarkdown4.3 KB
shared/cost-optimization.mdmarkdown57.1 KB
shared/error-codes.mdmarkdown20.3 KB
shared/evals/build-eval.mdmarkdown53.5 KB
shared/evals/cost-hillclimb.mdmarkdown31.0 KB
shared/evals/eval-audit.mdmarkdown27.2 KB
shared/evals/eval-hillclimb.mdmarkdown67.5 KB
shared/evals/report/SCHEMA.mdmarkdown15.7 KB
shared/evals/report/build-report-lite.mjsscript26.7 KB
shared/evals/report/runner-scaffold.mjsscript32.4 KB
shared/live-sources.mdmarkdown17.3 KB
shared/managed-agents-api-reference.mdmarkdown34.5 KB
shared/managed-agents-client-patterns.mdmarkdown11.8 KB
shared/managed-agents-core.mdmarkdown32.7 KB
shared/managed-agents-environments.mdmarkdown13.9 KB
shared/managed-agents-events.mdmarkdown25.4 KB
shared/managed-agents-memory.mdmarkdown11.1 KB
shared/managed-agents-multiagent.mdmarkdown65.1 KB
shared/managed-agents-onboarding-from-quickstart.mdmarkdown19.3 KB
shared/managed-agents-onboarding-from-url.mdmarkdown31.9 KB
shared/managed-agents-onboarding.mdmarkdown16.4 KB
shared/managed-agents-outcomes.mdmarkdown8.8 KB
shared/managed-agents-overview.mdmarkdown14.2 KB
shared/managed-agents-quickstarts/bug-hunter.mdmarkdown7.9 KB
shared/managed-agents-quickstarts/contract-tracker.mdmarkdown1.8 KB
shared/managed-agents-quickstarts/data-analyst.mdmarkdown1.5 KB
shared/managed-agents-quickstarts/deep-researcher.mdmarkdown2.4 KB
shared/managed-agents-quickstarts/explainer-video-maker.mdmarkdown4.8 KB
shared/managed-agents-quickstarts/field-monitor.mdmarkdown2.1 KB
shared/managed-agents-quickstarts/incident-commander.mdmarkdown1.7 KB
shared/managed-agents-quickstarts/performance-tuner.mdmarkdown11.1 KB
shared/managed-agents-quickstarts/sprint-retro-facilitator.mdmarkdown2.0 KB
shared/managed-agents-quickstarts/structured-extractor.mdmarkdown1.5 KB
shared/managed-agents-quickstarts/support-agent.mdmarkdown1.4 KB
shared/managed-agents-quickstarts/support-to-eng-escalator.mdmarkdown1.8 KB
shared/managed-agents-quickstarts/watchlist-scanner.mdmarkdown5.5 KB
shared/managed-agents-scheduled-deployments.mdmarkdown9.3 KB
shared/managed-agents-self-hosted-sandboxes.mdmarkdown27.3 KB
shared/managed-agents-tools.mdmarkdown37.0 KB
shared/managed-agents-webhooks.mdmarkdown11.1 KB
shared/model-migration.mdmarkdown338.1 KB
shared/models.mdmarkdown17.1 KB
shared/platform-availability.mdmarkdown7.2 KB
shared/preserved-thinking-migration.mdmarkdown62.5 KB
shared/preserved-thinking-migration/causes.mdmarkdown38.8 KB
shared/preserved-thinking-migration/drop_block_probe.pyscript65.0 KB
shared/preserved-thinking-migration/prefix_diff.pyscript91.8 KB
shared/prompt-audit.mdmarkdown48.2 KB
shared/prompt-caching.mdmarkdown32.3 KB
shared/token-counting.mdmarkdown1.6 KB
shared/tool-use-concepts.mdmarkdown43.3 KB
typescript/agent-sdk/README.mdmarkdown10.6 KB
typescript/agent-sdk/patterns.mdmarkdown4.6 KB
typescript/claude-api/README.mdmarkdown15.5 KB
typescript/claude-api/batches.mdmarkdown2.5 KB
typescript/claude-api/files-api.mdmarkdown2.3 KB
typescript/claude-api/streaming.mdmarkdown9.3 KB
typescript/claude-api/tool-use.mdmarkdown23.7 KB
typescript/managed-agents/README.mdmarkdown13.7 KB

shared/claude-platform-on-aws.md

View on GitHub
# Claude Platform on AWS

**Anthropic-operated** access to the Claude Developer Platform through AWS infrastructure - SigV4 authentication, AWS IAM access control, and AWS Marketplace billing. Because Anthropic operates it, **the API surface matches first-party with same-day parity** - for per-feature exceptions, see `shared/platform-availability.md` (the single source of truth; do not rely on an inline exception list here). Model IDs are the bare first-party strings (`claude-opus-5-5`, `claude-sonnet-5-5`) - **no provider prefix**.

> **Not the same as Amazon Bedrock.** Bedrock is partner-operated (AWS runs the service; release schedules vary, feature subset, `anthropic.`-prefixed model IDs). Claude Platform on AWS and Bedrock coexist; pick by whether you need AWS-native IAM/billing with full Anthropic API parity (this page) vs. Bedrock's own ecosystem.

---

## Client & install

| Language | Install | Client |
|---|---|---|
| Python | `pip install -U "anthropic[aws]"` | `from anthropic import AnthropicAWS` -> `AnthropicAWS()` |
| TypeScript | `npm install @anthropic-ai/aws-sdk` | `import AnthropicAws from "@anthropic-ai/aws-sdk"` -> `new AnthropicAws()` |
| Go | `go get github.com/anthropics/anthropic-sdk-go` | `import anthropicaws "github.com/anthropics/anthropic-sdk-go/aws"` -> `anthropicaws.NewClient(ctx, anthropicaws.ClientConfig{})` |
| C# | `dotnet add package Anthropic.Aws` | `new AnthropicAwsClient()` |
| Java | See SDK repo in `shared/live-sources.md` | See SDK repo in `shared/live-sources.md` |
| Ruby | `gem install anthropic aws-sdk-core` | See SDK repo in `shared/live-sources.md` |
| PHP | `composer require anthropic-ai/sdk aws/aws-sdk-php` | See SDK repo in `shared/live-sources.md` |

After construction, **use the client exactly as you would `Anthropic()`** - `client.messages.create(...)`, `client.beta.sessions.*`, etc., with bare model IDs.

```python
from anthropic import AnthropicAWS

client = AnthropicAWS()  # region + workspace_id from env; see below
client.messages.create(
    model="claude-opus-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
```

---

## Required configuration

Two values must be available (constructor args or environment) - **there is no default fallback** for either:

| Value | Env var | Notes |
|---|---|---|
| AWS region | `AWS_REGION` | Required. Unlike `AnthropicBedrock`, there is no `us-east-1` fallback. |
| Workspace ID | `ANTHROPIC_AWS_WORKSPACE_ID` | Required. Routes requests to your Claude workspace. |

Endpoint pattern: `https://aws-external-anthropic.{region}.api.aws/v1/...`. Requests are SigV4-signed with service name `aws-external-anthropic`.

## Authentication

The client resolves AWS credentials via the standard precedence chain: explicit constructor args -> environment (`AWS_ACCESS_KEY_ID`/`AWS_SECRET_ACCESS_KEY`/`AWS_SESSION_TOKEN`) -> shared profile -> assumed role / instance metadata.

**Short-term API keys** are also supported for cases where SigV4 isn't practical (e.g., browser, simple scripts). Mint one with the per-language token-generator package; pass it as `api_key` on the client. Lifetime is the **lesser of** the requested duration, the underlying credential's expiry, and **12 hours**. For package names and IAM details, WebFetch the Claude Platform on AWS page in `shared/live-sources.md`.

---

## What to tell users

- Treat it as first-party: every section of this skill applies unchanged. Do **not** apply Bedrock's feature-availability mask. Three Managed Agents differences only: (1) a session can run autonomously (no user events) for at most **6 hours** before it needs reauthentication - send any user-role event to continue; (2) sessions on **self-hosted** environments **cannot attach memory stores** (rejected at session create) - cloud environments attach them as usual; (3) self-hosted workers authenticate with IAM/SigV4 or an AWS-Console API key plus the `AnthropicSelfHostedEnvironmentAccess` managed policy - Console-generated environment keys don't work against the AWS endpoint.
- Model IDs are bare (`claude-opus-5-5`). Do **not** add an `anthropic.` prefix.
- A missing region or `workspace_id` throws at client-construction time (no request is sent). A **403** means the request reached the server - check for a **wrong** `workspace_id` or a missing IAM action on the principal. See the IAM actions reference in `shared/live-sources.md`.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall