open-agent-kit: Skill for Claude Code

.agents/skills/swarm-report/SKILL.md

swarm-report is a skill for Claude Code from goondocks-co/open-agent-kit. It costs 82 tokens per session (969 once invoked), scanned A, original, MIT.

A cross-project reporting tool for an organization’s connected teams. It checks which projects are online, gathers information about activity, dependencies, coding patterns, and decisions, then compares the results.

In plain words
What is it for?
Use it to review project activity, find shared practices, compare technical choices, and identify possible collaboration opportunities.
Why use it?
It brings information from separate projects into one overview instead of requiring manual comparison.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is goondocks-co/open-agent-kit's own configuration. It tells Claude Code how to work on open-agent-kit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything open-agent-kit configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/goondocks-co/open-agent-kit/main/.agents/skills/swarm-report/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/goondocks-co/open-agent-kit

Made for: Claude Code.

Wrote 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.

agentmods badge for swarm-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/goondocks-co/open-agent-kit/swarm-report/github.svg)](https://agentmods.dev/skills/goondocks-co/open-agent-kit/swarm-report)
Your own site
<a href="https://agentmods.dev/skills/goondocks-co/open-agent-kit/swarm-report"><img src="https://agentmods.dev/badge/skills/goondocks-co/open-agent-kit/swarm-report/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.

agentmods 80×15 button for swarm-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/goondocks-co/open-agent-kit/swarm-report"><img src="https://agentmods.dev/badge/skills/goondocks-co/open-agent-kit/swarm-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 969 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.00969
Opus 5 $0.00041 $0.00485
Sonnet 5 $0.00016 $0.00194
Haiku 4.5 $0.00008 $0.00097

Measured 8d ago against content hash fd22df852c4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

swarm-report 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 8d 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.

.agents/skills/swarm-report/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Swarm Report

Generate a structured cross-project report from connected swarm nodes. The report compares projects, surfaces shared patterns, and recommends collaboration opportunities.

Workflow

1. Verify Connectivity

swarm_status()

If disconnected, inform the user and stop. The swarm must be online to generate a meaningful report.

2. Inventory Nodes

swarm_nodes()

Record each team's project slug, connection status, and capabilities. This becomes the Node Inventory section of the report.

3. Gather Cross-Project Data

Run multiple searches to build a picture of the organization:

# Activity and recent work
swarm_search(query="recent changes and refactoring", search_type="all", limit=20)

# Shared dependencies and libraries
swarm_search(query="shared dependencies and common libraries", search_type="memory", limit=20)

# Coding conventions and patterns
swarm_search(query="coding conventions and architectural patterns", search_type="memory", limit=20)

# Decisions and trade-offs
swarm_search(query="architectural decisions and trade-offs", search_type="memory", limit=15)

Adapt queries based on what comes back — if a topic yields interesting results, drill deeper with swarm_fetch:

swarm_fetch(ids=["<chunk-id>"], project_slug="<project>")

4. Write the Report

Write the report to oak/insights/cross-project-report.md using this structure:

# Cross-Project Report

> Generated: YYYY-MM-DD | Nodes: N connected

## Executive Summary

2-3 paragraph overview of the organization's current state — what's active,
what themes emerge, and the top recommendations.

## Node Inventory

| Project | Status | Capabilities | Notable Activity |
|---------|--------|--------------|------------------|
| ...     | ...    | ...          | ...              |

## Activity Comparison

Compare what each project has been working on recently. Highlight:
- Projects with high activity vs quiet ones
- Overlapping work across teams
- Blocked or stalled efforts

## Shared Patterns

Patterns that appear across multiple projects:
- Common dependencies (same libraries, frameworks, versions)
- Similar architectural approaches (service layers, error handling)
- Shared conventions (naming, testing, deployment)

## Divergences

Where projects have made different choices:
- Conflicting dependency versions
- Different approaches to the same problem
- Inconsistent conventions that could cause friction

## Recommendations

Concrete, actionable suggestions:
- Opportunities for code sharing or extraction into shared libraries
- Projects that should coordinate on version alignment
- Teams that would benefit from knowledge sharing on specific topics

Read the full file on GitHub · 143 lines

Files

What ships with it

2 files 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.

Changes

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.

  1. 8d ago First seen · 143 lines · 82 tokens per session scan A fd22df852c4b

Subscribe to this mod's changes

swarm-report is a skill published in the GitHub repository goondocks-co/open-agent-kit (10 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 969 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 2026-08-31.