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/indexgit clone --depth 1 https://github.com/goondocks-co/open-agent-kitWhat 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 | $0.00014 | $0.00919 |
| Opus 5 | $0.00007 | $0.00460 |
| Sonnet 5 | $0.00003 | $0.00184 |
| Haiku 4.5 | $0.00001 | $0.00092 |
Grade A, and why
index 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 yesterday.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
These are the AI coding agents your team uses to build software — Claude Code, Cursor, Gemini, and others. OAK integrates with each of them through hooks (to capture activity and inject context), MCP tools (for semantic search and memory), and skills (to extend what agents can do). No matter which agent your engineers prefer, OAK ensures every session contributes to and benefits from your project's shared intelligence.
:::note[Looking for OAK's built-in agents?] OAK also runs its own autonomous agents that turn captured intelligence into action — documentation, analysis, and insights. See OAK Agents. :::
Supported Agents
| Agent | Directory | Hooks | MCP | Skills |
|---|---|---|---|---|
| Claude Code | .claude/ |
Yes | Yes | Yes |
| Codex CLI | .codex/ |
Yes (OTel) | Yes | Yes |
| Cursor | .cursor/ |
Yes | Yes | Yes |
| Gemini CLI | .gemini/ |
Yes | Yes | Yes |
| OpenCode | .opencode/ |
Yes (Plugin) | Yes | Yes |
| VS Code Copilot | .github/ |
Yes | Yes | Yes |
| Windsurf | .windsurf/ |
Yes | No | Yes |
For details on what each agent's hooks actually provide (context injection, activity capture, summarization), see the Team overview.
Skills & Commands
OAK deploys skills and commands into each agent's native directories. Skills are the primary way OAK extends your agent — invoke them with slash commands like /project-governance or /oak.
After oak init, 4 skills are available:
- OAK —
/oak(semantic search, impact analysis, memory, database queries) - Rules Management —
/project-governance(constitutions, agent files, RFCs) - Context Engineering —
/context-engineering(prompt design, context optimization, the four strategies) - Swarm —
/swarm(cross-project search for collective knowledge and patterns)
See the Skills page for full details on each skill.
Agent Instruction Files
OAK creates and manages instruction files that reference your project constitution:
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.
- yesterday First seen · 76 lines · 14 tokens per session scan A f3077fcd0f17
index is an agent published in the GitHub repository goondocks-co/open-agent-kit (10 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 919 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
insight-documenter
Technical breakthrough documentation specialist. Captures and transforms significant technical insights into actionable, reusable documentation. Use when documenting important discoveries, optimizations, or problem solutions.
instruction-reflector
Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.
builder
Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…
finalize
Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.
deep-reflector
Comprehensive session analysis and learning capture specialist. Analyzes development sessions to extract patterns, preferences, and improvements for future interactions. Use after significant work sessions to capture learnings.
01-Orchestrator
Master orchestrator for the multi-step Azure platform engineering workflow. Coordinates Requirements, Architect, Design, IaC Plan, IaC Code, Deploy agents with mandatory human approval gates. Routes Bicep or Terraform tracks via decisions.iactool.