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 agents/goondocks-co/open-agent-kit/skillsgit 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/agents/goondocks-co/open-agent-kit/skills)<a href="https://agentmods.dev/agents/goondocks-co/open-agent-kit/skills"><img src="https://agentmods.dev/badge/agents/goondocks-co/open-agent-kit/skills.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 | $0.00012 | $0.01620 |
| Opus 5 | $0.00006 | $0.00810 |
| Sonnet 5 | $0.00002 | $0.00324 |
| Haiku 4.5 | $0.00001 | $0.00162 |
Grade A, and why
skills 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills are the primary way OAK extends your AI agent's capabilities. They are deployed into each agent's skills directory during oak init and can be invoked directly from your agent's interface using slash commands (e.g., /project-governance), or they activate automatically when your request matches their description.
You don't need to memorize commands — just describe what you need:
"We need coding standards for this Python project" → /project-governance
"What did we discuss about auth last week?" → /oak
"I'm about to refactor the payment module — what breaks?" → /oak
"How do other projects handle auth?" → /swarm
"Propose an RFC for switching to PostgreSQL" → /project-governance
Skills use the team's semantic search and memory under the hood — no additional API keys required beyond what your agent already uses.
OAK (Team Intelligence)
/oak
Search, analyze, and query your codebase using semantic vector search, impact analysis, and direct SQL queries against the team intelligence database. Finds conceptually related code that grep would miss, assesses refactoring risk, and provides direct database access for session history, activity logs, and agent run data.
When to use:
- Finding similar implementations across the codebase
- Understanding how components connect to each other
- Assessing the impact of code changes before refactoring
- Recalling what was discussed or decided in previous sessions
- Looking up past conversations, outcomes, or decisions
- Querying session history or activity logs
- Looking up past memories or observations
- Checking agent run costs and performance
Examples:
# Find code by concept, not just text
/oak how does the authentication middleware work?
# Assess risk before refactoring
/oak I'm about to change the session model schema — what might be affected?
# Recall past conversations and decisions
/oak what did we discuss about the auth refactor last week?
# Look up what happened in previous sessions
/oak show me recent sessions and what was accomplished
# Search past learnings and gotchas
/oak are there any known gotchas with the payment module?
# Query raw data when you need specifics
/oak how many sessions have we had this week and what was the total cost?
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 · 189 lines · 12 tokens per session scan A 506bb921897b
skills is an agent published in the GitHub repository goondocks-co/open-agent-kit (10 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 1,620 once invoked, about $0.0001 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 agents, from other repositories
coordinator
A project coordinator subagent that plans work, creates tasks, and delegates to team agents. Use when you need to orchestrate a multi-agent workflow.
coordinator
A project coordinator subagent that plans work, creates tasks, and delegates to team agents. Use when you need to orchestrate a multi-agent workflow.
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…
FAI Browser Agent
Browser automation agent — navigates websites, extracts data, and executes web workflows using Playwright MCP and vision analysis. Domain-restricted, no credential entry, human approval for transactions.
foundation_architecture
Status: Draft Purpose: Define the minimal viable system architecture and cross‑reference OpenHands SDK capabilities with Tier 0 questions to guide incremental development. Related: ./openhandsinsightsandprioritization.md, ./implementationquestions.md, ./design/multiagentorchestration.md.
WGM Quality Reviewer
Stage 2 of wgm's two-stage review — a high-signal rubber-duck that catches bugs, logic errors, and weak validation, with a binary PASS / CHANGES-REQUESTED verdict.