Borrowing it
Nothing to install: this file belongs to goondocks-co/open-agent-kit. 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/goondocks-co/open-agent-kit/main/.agents/skills/swarm/SKILL.mdgit clone --depth 1 https://github.com/goondocks-co/open-agent-kitWrote 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/goondocks-co/open-agent-kit/swarm)<a href="https://agentmods.dev/skills/goondocks-co/open-agent-kit/swarm"><img src="https://agentmods.dev/badge/skills/goondocks-co/open-agent-kit/swarm/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/goondocks-co/open-agent-kit/swarm"><img src="https://agentmods.dev/badge/skills/goondocks-co/open-agent-kit/swarm.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 | $0.00095 | $0.01302 |
| Opus 5.5 | $0.00038 | $0.00521 |
| Sonnet 5.5 | $0.00019 | $0.00260 |
| Haiku 4.5 | $0.00010 | $0.00130 |
Grade A, and why
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 1mo 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Swarm
The swarm is a federation of teams across your organization. Each team is a project with its own machine and developer nodes — its own memories, sessions, plans, and codebase knowledge. The swarm connects these teams so you can search and retrieve knowledge from all of them at once.
Use MCP tools (swarm_search, swarm_fetch, swarm_nodes, swarm_status)
to access collective knowledge. If MCP tools are not available, fall back to
the CLI commands shown below.
Architecture at a Glance
Organization Swarm
├── Team A (this project)
│ ├── Node: developer laptop
│ └── Node: CI server
├── Team B (api-service)
│ └── Node: developer laptop
└── Team C (mobile-app)
├── Node: developer laptop
└── Node: staging server
- Swarm = organization-level federation of teams
- Team = a single project (has its own
.oak/ci/activities.db) - Node = a machine running the team daemon within a project
The swarm aggregates knowledge across teams. The team federates tool calls across nodes within one project. This skill is for the swarm layer.
When to Use Swarm vs Team
| Question | Use Team (oak) |
Use Swarm |
|---|---|---|
| How does auth work in this project? | oak_search |
|
| How do we handle auth across projects? | swarm_search |
|
| What patterns exist org-wide for error handling? | swarm_search |
|
| What was decided about our API design? | oak_search |
|
| What API conventions do other teams follow? | swarm_search |
|
| What depends on this module locally? | oak_context |
|
| Which other projects depend on our shared library? | swarm_search |
Rule of thumb: Team = "this project", Swarm = "the organization".
Quick Start
Search then Fetch (primary workflow)
The two-step pattern keeps responses focused — search returns summaries with IDs, fetch returns full content for the items you care about.
# 1. Search across all connected teams
swarm_search(query="retry with exponential backoff", search_type="memory")
# 2. Get full details for specific results
swarm_fetch(ids=["chunk-id-from-search"], project_slug="api-service")
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.
- 1mo ago First seen · 172 lines · 95 tokens per session scan A 06d500cc6f98
swarm is a skill published in the GitHub repository goondocks-co/open-agent-kit (10 stars, last pushed 3mo ago), licensed MIT. It adds 95 tokens to every session and 1,302 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
fetch-url
Fetch a single URL and print its content as Markdown. Use when you need to read a web page, documentation page, or API reference without indexing it. Accepts http(s):// and file:// URLs and writes the result to stdout.
gsap-scrolltrigger
Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…
gsap-core
Official GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap.matchMedia() (responsive, prefers-reduced-motion). Use when the user asks for a JavaScript animation library, animation in React/Vue/vanilla, GSAP tweens, easing, basic animation, responsive or reduced-motion…
playwright-recording
Record browser interactions as video using Playwright. Use for capturing demo videos, app walkthroughs, and UI flows for Remotion videos. Triggers include recording a demo, capturing browser video, screen recording a website, or creating walkthrough footage.
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…
threejs-geometry
Three.js geometry creation - built-in shapes, BufferGeometry, custom geometry, instancing. Use when creating 3D shapes, working with vertices, building custom meshes, or optimizing with instanced rendering.