Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/desplega-ai/agent-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/plugins/desplega-ai/agent-swarm/gemini-extension)<a href="https://agentmods.dev/plugins/desplega-ai/agent-swarm/gemini-extension"><img src="https://agentmods.dev/badge/plugins/desplega-ai/agent-swarm/gemini-extension/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/plugins/desplega-ai/agent-swarm/gemini-extension"><img src="https://agentmods.dev/badge/plugins/desplega-ai/agent-swarm/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agent-swarm 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 today.
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
{
"name": "agent-swarm",
"description": "Install, deploy, and operate agent-swarm: Docker Compose, Kubernetes with Helm, HTTPS, agent-fs, integrations, and the API for coding agents",
"version": "1.173.0"
}
What ships with it
60 files beside gemini-extension.json 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.
- assets/agent-swarm-every-team.mp4 7927 KB
- assets/agent-swarm-logo-orange.png 1449 KB
- assets/agent-swarm-logo.png 1510 KB
- assets/agent-swarm-slack-to-pr.mp4 3474 KB
- assets/agent-swarm.mp4 2740 KB
- assets/agent-swarm.png 2578 KB
- assets/github-cancellation-flows.mmd 710 B
- assets/github-cancellation-flows.png 39 KB
- assets/github-followup-flows.mmd 1.3 KB
- assets/github-followup-flows.png 99 KB
- assets/github-task-creation-flow.mmd 1.4 KB
- assets/github-task-creation-flow.png 99 KB
- assets/operator-skill.md 476 B
- assets/operator-skill.png 232 KB
- assets/video-source/.gitignore 57 B
- assets/video-source/package.json 663 B
- assets/video-source/public/audio/bed.mp3 1559 KB
- assets/video-source/public/README.md 208 B
- assets/video-source/README.md 3.1 KB
- assets/video-source/remotion.config.ts 153 B runs code
- assets/video-source/src/compositions/DailyEvolution.tsx 1.5 KB
- assets/video-source/src/compositions/SlackToPR.tsx 1.5 KB
- assets/video-source/src/fonts.ts 472 B runs code
- assets/video-source/src/index.ts 93 B runs code
- assets/video-source/src/Root.tsx 759 B
- assets/video-source/src/scenes/daily-evolution/Scene1Opening.tsx 1.6 KB
- assets/video-source/src/scenes/daily-evolution/Scene2Scanning.tsx 2.9 KB
- assets/video-source/src/scenes/daily-evolution/Scene3Memories.tsx 3.3 KB
- assets/video-source/src/scenes/daily-evolution/Scene4Profile.tsx 3.1 KB
- assets/video-source/src/scenes/daily-evolution/Scene5Graph.tsx 4.1 KB
- assets/video-source/src/scenes/daily-evolution/Scene6Outro.tsx 1.6 KB
- assets/video-source/src/scenes/slack-to-pr/SceneBrainstorm.tsx 4.6 KB
- assets/video-source/src/scenes/slack-to-pr/SceneIntro.tsx 1.6 KB
- assets/video-source/src/scenes/slack-to-pr/SceneOutro.tsx 1.1 KB
- assets/video-source/src/scenes/slack-to-pr/ScenePR.tsx 4.7 KB
- assets/video-source/src/scenes/slack-to-pr/SceneRender.tsx 3.4 KB
- assets/video-source/src/scenes/slack-to-pr/SceneSpinUp.tsx 2.5 KB
- assets/video-source/src/scenes/slack-to-pr/SceneThread.tsx 5.0 KB
- assets/video-source/src/theme.ts 1.0 KB runs code
- assets/video-source/tsconfig.json 322 B
- examples/script-connections-playground.html 20 KB
- examples/sso/docker-compose.sso.yml 2.2 KB
- examples/sso/native-oidc.env.example 3.1 KB
- examples/sso/oauth2-proxy.cfg 3.9 KB
- scripts/.openapi-response-backlog 199 B
- scripts/agent-fs-version-utils.ts 5.0 KB runs code
- scripts/backfill-seed-users.sql 4.1 KB
- scripts/build-claude-mod.ts 2.2 KB runs code
- scripts/build-cli.ts 664 B runs code
- scripts/build-extension-catalog.ts 1.8 KB runs code
- scripts/build-extension-manifest-schema.ts 2.1 KB runs code
- scripts/build-realtime-browser.ts 706 B runs code
- scripts/build-seed-skill-files.ts 3.6 KB runs code
- scripts/build-skill-md.ts 3.0 KB runs code
- scripts/bump-agent-fs.ts 5.4 KB runs code
- scripts/bundle-extension-types.ts 3.6 KB runs code
- scripts/bundle-script-types.ts 2.5 KB runs code
- scripts/check-api-key-boundary.sh 1.8 KB runs code
- scripts/check-async-db-seam.sh 3.6 KB runs code
- scripts/check-audit-columns.sh 133 B runs code
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.
- today Changed 041211a69bde
- yesterday Changed 4d97092f8577
- 2d ago Changed 196499700cd6
- 3d ago Changed 4a2a82c9b740
- 4d ago Changed 3518b35d42be
- 5d ago Changed 011dfebf96d5
- 6d ago Changed 1541157ba2c8
- 7d ago Changed 5b8de01a271d
- 8d ago Changed 4105646a3e31
- 9d ago First seen · 6 lines scan A e66e65c69fdf
agent-swarm is a plugin published in the GitHub repository desplega-ai/agent-swarm (890 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-15.
Other plugins, from other repositories
agent-sandboxing
Agent sandboxing for AI coding agents: microVM and kernel-isolated execution environments. Index skill (sandbox) routes to substrate-specific paths. Currently covers the kubernetes-sigs/agent-sandbox path on kind, GKE, and kina (Kubernetes-in-Apple-Containers), with Kata, gVisor, and Apple Container microVM substrates.
ensemble-infrastructure
Infrastructure management for AWS, Kubernetes, Docker, Helm, Fly.io.
open-forge
Self-host open-source apps on your own cloud, your own VPS, your own Kubernetes cluster, a PaaS, or your own laptop. Chat-friendly interface to existing tools (aws, az, hcloud, doctl, gcloud, flyctl, kubectl, helm, podman, docker, lume, tailscale, terraform, cdk, ssh, gh) — Claude runs every command; you only answer…
agentic-workflows
Intelligent multi-agent swarms for automation - Ansible collections, Kubernetes operators, Terraform modules.
kubernetes-operations
Kubernetes manifest generation, networking configuration, security policies, observability setup, GitOps workflows, and auto-scaling.
datum-platform
Kubernetes platform engineering automation with aggregated API servers, controller patterns, GitOps deployment, and platform capabilities.