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.
npx agentmods add skills/goondocks-co/open-agent-kit/pattern-findernpx skills add goondocks-co/open-agent-kit --skill pattern-findergit 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/pattern-finder)<a href="https://agentmods.dev/skills/goondocks-co/open-agent-kit/pattern-finder"><img src="https://agentmods.dev/badge/skills/goondocks-co/open-agent-kit/pattern-finder.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.01201 |
| Opus 5 | $0.00044 | $0.00600 |
| Sonnet 5 | $0.00018 | $0.00240 |
| Haiku 4.5 | $0.00009 | $0.00120 |
Grade A, and why
pattern-finder 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 4d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern Finder
Search across swarm nodes for recurring code patterns, architectural decisions, and shared conventions that could be standardized or extracted into shared libraries.
Workflow
1. Verify Connectivity
swarm_status()
swarm_nodes()
Note the connected projects — each represents a search target.
2. Search for Patterns
Run searches across several dimensions:
# Shared utility patterns
swarm_search(query="utility functions helpers common patterns", search_type="all", limit=20)
# Architectural patterns
swarm_search(query="service layer architecture middleware patterns", search_type="memory", limit=20)
# Error handling and resilience
swarm_search(query="error handling retry logic resilience patterns", search_type="memory", limit=15)
# Testing approaches
swarm_search(query="testing conventions test patterns integration tests", search_type="memory", limit=15)
# Configuration and deployment
swarm_search(query="configuration management deployment patterns CI/CD", search_type="memory", limit=15)
Adjust queries based on the user's focus area. If they asked about a specific domain (e.g., "how do other teams handle auth?"), prioritize targeted searches.
3. Drill into Interesting Findings
swarm_fetch(ids=["<chunk-id>"], project_slug="<project>")
Fetch details for patterns that appear across multiple projects or that represent particularly clean solutions worth adopting.
4. Compare with Local Patterns
Search the current project to see how local patterns relate:
# Use grep/glob to find local implementations of discovered patterns
Grep(pattern="relevant pattern", path="src/")
This comparison makes recommendations concrete — "Team B does X, we do Y, here's why aligning makes sense."
5. Write the Report
Write to oak/insights/pattern-finder-report.md:
# Pattern Finder Report
> Generated: YYYY-MM-DD | Projects analyzed: N
## Executive Summary
Overview of key findings — what patterns are widely shared, where approaches
diverge, and the top extraction/standardization opportunities.
## Shared Patterns
Patterns that appear across multiple projects:
### [Pattern Name]
- **Where:** Projects A, B, C
- **What:** Brief description of the pattern
- **Variation:** How implementations differ across projects
- **Assessment:** Is convergence desirable? Which version is best?
(Repeat for each significant pattern found)
## Divergences Worth Examining
Areas where projects take notably different approaches to the same problem:
| Problem Domain | Project A Approach | Project B Approach | Notes |
|---------------|-------------------|-------------------|-------|
| ... | ... | ... | ... |
## Extraction Candidates
Code that could be extracted into shared packages:
| Candidate | Found In | Description | Effort |
|-----------|----------|-------------|--------|
| Retry utility | A, B, C | Exponential backoff with jitter | Low |
| ... | ... | ... | ... |
Include:
- Utility functions duplicated across projects
- Common middleware or service patterns
- Shared type definitions or schemas
## Convention Alignment
| Convention | Projects Aligned | Projects Diverging | Recommendation |
|-----------|-----------------|-------------------|----------------|
| Naming style | A, C (snake_case) | B (camelCase) | Align to snake_case |
| ... | ... | ... | ... |
## Recommendations
Prioritized list of actions:
1. Quick wins — patterns already nearly aligned, just need coordination
2. High-value extractions — widely duplicated code worth packaging
3. Convention decisions — divergences that need a team decision
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.
- 4d ago First seen · 169 lines · 88 tokens per session scan A b7fbdef50ca9
pattern-finder is a skill published in the GitHub repository goondocks-co/open-agent-kit (10 stars, last pushed 1mo ago), licensed MIT. It adds 88 tokens to every session and 1,201 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.
Other skills, from other repositories
taiwanese-mandarin-translate
Translate English into Traditional Chinese for Taiwan audiences, using natural Taiwanese Mandarin by default and a neutral ROC Mandarin register when the context is formal or public-facing.
neohive-coordinator
Runs Neohive multi-agent coordination from MCP or the dashboard without wasting tokens rediscovering ports, CSRF headers, task rules, or listen/checkmessages patterns. Use when acting as Coordinator, Manager, or Lead; when assigning Neohive work; when using dashboard REST APIs from curl/scripts; or when the user…
neohive-developer-agent
Implements Neohive-assigned work as a Coder, Frontend, or specialist agent using MCP tools correctly—register, listen, lockfile, tasks, Node/Volta-safe MCP configs, and dashboard API headers. Use when working in a Neohive-enabled repo, when the user asks to register/listen, or when integrating with .neohive/ and the…
conventions
Neohive multi-agent collaboration conventions. Automatically loaded when working in a multi-agent team to ensure proper tool usage, communication patterns, and workflow management.
launch-team
Launch a multi-agent team from a template. Lists available templates and generates prompts for each agent. Use when starting a new multi-agent collaboration, team session, or when the user says "launch team" or "start agents".
plan
Create a multi-agent workflow plan from a natural language description. Breaks down the task into steps, assigns to agents, and creates the workflow. Use when the user describes a feature or task they want the team to build.