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/release/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/release)<a href="https://agentmods.dev/skills/vrsen/agency-swarm/release"><img src="https://agentmods.dev/badge/skills/vrsen/agency-swarm/release/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/release"><img src="https://agentmods.dev/badge/skills/vrsen/agency-swarm/release.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 | $0.00027 | $0.00350 |
| Opus 5.5 | $0.00011 | $0.00140 |
| Sonnet 5.5 | $0.00005 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
release 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
Release
A release is a public action: the maintainer approves the version, the release notes and the publish step before any of them happen (AGENTS.md 2.2).
Steps
- Bump the version in
pyproject.toml. Backward compatibility is not a goal by itself (AGENTS.md 2.1): a breaking change gets a bigger version bump and a clear entry in the release notes anddocs/migration/guide.mdx, not a compatibility shim. - Run
make ci. The final run has no skipped test: tests that need real API keys run with real keys. One skipped test blocks the release. - Run a real example agency from this repository end to end against the release commit: send a first message and watch a non-empty streamed response. A launch, credential, dependency or interface failure blocks the release until its root cause is known.
- Get a review of the exact release commit (load the
reviewskill). The reviewer also checks each breaking-change entry in the release notes against the diff. Fix findings and repeat steps 2 and 3 if code changed. - Write the release notes: every user-visible change since the previous release, in plain language, following
.cursor/rules/writing-docs.mdc. Name each breaking change with what worked before and what changes now. - Draft the tag, the GitHub release and the package upload for the maintainer's approval, then publish.
Keep a bugfix release minimal: no policy edits and no tooling churn.
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 · 20 lines · 27 tokens per session scan A ad9e1d7a7e24
release is a skill published in the GitHub repository VRSEN/agency-swarm (4,617 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 350 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
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.
validate-release-green
Run or inspect the local Release-Green observer for an exact base or combined PR candidate, separating hard failures, advisory drift and incomplete evidence. Use for maintainer preflight; full CI acceptance remains a separate requirement.
ship
Pre-release gate. Run the full gate, responsive + render checks, then produce the release checklist (README badge/current/changelog). Use before tagging a release.
verify-and-ship
Choose proportionate validation, fix failures, update the changelog, commit, push, and create/update the pull request or merge request.
ship-workflow
Resumable shipping lifecycle: reconciles current Git and GitHub facts from any entry (dirty default or feature branch, local commits, published branch, open PR, existing manual or native stack, merged work), commits dirty work as lossless logical commits, publishes or reuses the PR, requires current CI and review…
mathodology-dev-test-release
Use when checking skill metadata, references or repository boundaries, or preparing an explicitly requested skills release.