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-report/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-report)<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.
<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>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 | $0.00082 | $0.00969 |
| Opus 5.5 | $0.00033 | $0.00388 |
| Sonnet 5.5 | $0.00016 | $0.00194 |
| Haiku 4.5 | $0.00008 | $0.00097 |
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 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 — 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
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.
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 · 143 lines · 82 tokens per session scan A fd22df852c4b
swarm-report is a skill published in the GitHub repository goondocks-co/open-agent-kit (10 stars, last pushed 3mo ago), licensed MIT. It adds 82 tokens to every session and 969 once invoked, about $0.0003 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
github-fix-issue
Investigate or fix a GitHub issue by number or URL. Keep investigation-only requests read-only.
apex-workflow-start
Start or resume APEX work in VS Code Copilot. Select the interactive Orchestrator or domain owner, recover current project evidence, collect missing decisions and use native tasks without UI handoff or readiness rituals.
studio-goal-progress
Use when a KIT-managed Codex or Hermes Goal needs evidence-backed percentage, ETA range, live read-only progress views, or portable append-only progress recovery.
kanban-board
Manage the kanban board. List, read, and close GitHub issues.
core-holistic-planning-and-tracking
Create a plan and Beads tasks with dependencies and acceptance criteria.
strategic-alignment
Cascades strategy from boardroom to individual contributor. Detects and fixes misalignment between company goals and team execution. Covers strategy articulation, cascade mapping, orphan goal detection, silo identification, communication gap analysis, and realignment protocols. Use when teams are pulling in different…