Borrowing it
Nothing to install: this file belongs to carrotly-ai/gluon-agent. 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/carrotly-ai/gluon-agent/main/.claude/skills/upgrade-claude-agent-sdk/SKILL.mdgit clone --depth 1 https://github.com/carrotly-ai/gluon-agentWrote 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/skills/carrotly-ai/gluon-agent/upgrade-claude-agent-sdk)<a href="https://agentmods.dev/skills/carrotly-ai/gluon-agent/upgrade-claude-agent-sdk"><img src="https://agentmods.dev/badge/skills/carrotly-ai/gluon-agent/upgrade-claude-agent-sdk/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/skills/carrotly-ai/gluon-agent/upgrade-claude-agent-sdk"><img src="https://agentmods.dev/badge/skills/carrotly-ai/gluon-agent/upgrade-claude-agent-sdk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00077 | $0.01573 |
| Opus 5 | $0.00039 | $0.00787 |
| Sonnet 5 | $0.00015 | $0.00315 |
| Haiku 4.5 | $0.00008 | $0.00157 |
Grade A, and why
upgrade-claude-agent-sdk 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 11d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upgrade Claude Agent SDK
Overview
Perform a structured upgrade of the claude-agent-sdk Python package in this project. Review upstream changes, assess integration impact, expose new features to users where appropriate, update documentation, and ship the result on a clean feature branch.
Workflow
Execute these phases in order. Do not skip phases — each validates the previous.
Phase 1: Discover SDK Changes
-
Check current version
uv run python -c "import claude_agent_sdk; print(claude_agent_sdk.__version__)" grep 'claude-agent-sdk' pyproject.toml -
Fetch latest SDK release info from
https://github.com/anthropics/claude-agent-sdk-pythonUse
ghCLI or web tools to review:- Release notes / changelog
- New/changed exports in
claude_agent_sdkandclaude_agent_sdk.types - New fields on
ClaudeAgentOptions(the primary integration surface)
-
Inspect SDK types programmatically
# After installing the new version uv run python -c " import dataclasses, claude_agent_sdk for f in dataclasses.fields(claude_agent_sdk.ClaudeAgentOptions): print(f'{f.name}: {f.type}') " -
Produce a change summary listing:
- New
ClaudeAgentOptionsfields (type, default, purpose) - Deprecated or removed fields
- New exported types/classes
- Breaking changes to existing APIs
- CLI flag changes (run
CLAUDECODE= claude --helpto check)
- New
Phase 2: Assess Integration Impact
Read the integration map at references/integration-map.md for the full data flow.
For each SDK change, determine:
-
Does it affect existing integration? Check if any current code in
agent.pyuses deprecated/changed APIs. Fix these first. -
Is it a new feature? Classify it:
- Global preference → Settings page +
store.get_setting() - Per-task option → TASK_PROFILES +
resolve_task_options()+ Advanced Options UI - SDK-only internal →
agent.pyonly - Informational → README/docs only
- Global preference → Settings page +
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 179 lines · 77 tokens per session scan A a4ed602eed98
upgrade-claude-agent-sdk is a skill published in the GitHub repository carrotly-ai/gluon-agent (11 stars, last pushed 12d ago), licensed MIT. It adds 77 tokens to every session and 1,573 once invoked, about $0.0004 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.
Other skills, from other repositories
python-package-management
Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.
python-testing
Guidelines for writing and running tests in the Agent Framework Python codebase. Use this when creating, modifying, or running tests.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
python-development
Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.
claude-api
Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.