Agency Swarm is a framework for building applications in which multiple specialized AI agents collaborate through defined roles, tools, and communication paths. Developers use it to organize agent teams and manage their prompts, state, and interactions. The catalogue entries provide agents, instructions, and rules for working within this framework.
Borrowing it
Nothing to install: this file belongs to VRSEN/agency-swarm. 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/VRSEN/agency-swarm/main/.claude/skills/sdk-upgrade/SKILL.mdgit clone --depth 1 https://github.com/VRSEN/agency-swarmWrote 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/vrsen/agency-swarm/sdk-upgrade)<a href="https://agentmods.dev/skills/vrsen/agency-swarm/sdk-upgrade"><img src="https://agentmods.dev/badge/skills/vrsen/agency-swarm/sdk-upgrade/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/vrsen/agency-swarm/sdk-upgrade"><img src="https://agentmods.dev/badge/skills/vrsen/agency-swarm/sdk-upgrade.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 | $0.00034 | $0.00331 |
| Opus 5.5 | $0.00014 | $0.00132 |
| Sonnet 5.5 | $0.00007 | $0.00066 |
| Haiku 4.5 | $0.00003 | $0.00033 |
Grade A, and why
sdk-upgrade 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.
What it actually says
Upgrade the OpenAI Agents SDK or a provider SDK
The SDK moves fast and our wrappers can silently fall behind it. A custom session layer once missed the SDK's compaction capability for months because nobody compared the changelog with the wrapper. This procedure prevents that.
Steps
- Bump the pin in
pyproject.tomland update every affected lockfile in the same change. Check outreferences/openai-agents-pythonat the new tag (clone it there if missing). - Read the SDK changelog between the old and new tag.
- List every wrapper that mirrors an SDK abstraction (session, history items, streaming events, model settings, tracing, guardrails, handoffs; each names its SDK class in its docstring per AGENTS.md 1.3). For each new SDK feature, decide: the wrapper now supports it, the wrapper is deleted in favor of the SDK (AGENTS.md 1.4), or the gap is listed in the pull request with a GitHub issue drafted for the maintainer.
- Run
make ci. - Add or update an end-to-end test that makes a tool call or a delegation and then sends that history back to the model in the next turn. This catches history-format changes that unit tests miss.
- In the pull request, name the old and new versions and list each new SDK feature a wrapper does not yet support.
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.
- 15d ago First seen · 18 lines · 34 tokens per session scan A 5b96bfa698fa
sdk-upgrade is a skill published in the GitHub repository VRSEN/agency-swarm (4,617 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 331 once invoked, about $0.0001 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 2026-10-13.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.