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/oak/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/oak)<a href="https://agentmods.dev/skills/goondocks-co/open-agent-kit/oak"><img src="https://agentmods.dev/badge/skills/goondocks-co/open-agent-kit/oak/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/oak"><img src="https://agentmods.dev/badge/skills/goondocks-co/open-agent-kit/oak.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 | $0.00167 | $0.03403 |
| Opus 5.5 | $0.00067 | $0.01361 |
| Sonnet 5.5 | $0.00033 | $0.00681 |
| Haiku 4.5 | $0.00017 | $0.00340 |
Grade A, and why
oak 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 — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OAK
Prefer MCP tools (oak_search, oak_context, oak_remember, oak_resolve_memory) over CLI when available. Fall back to CLI or direct SQL for queries not covered by MCP tools. If .oak/ci/activities.db does not exist, inform the user to run oak-dev team start first.
Quick Start
MCP tools (preferred when available)
# Search knowledge — memories, plans, and sessions (default)
oak_search(query="authentication refactor decision")
# Narrow by category
oak_search(query="form validation logic", search_type="code")
oak_search(query="backup directory decision", search_type="memory")
oak_search(query="migration plan", search_type="plans")
# Impact analysis — get context for a specific file
oak_context(task="impact of changes to executor", files=["src/features/agent_runtime/executor.py"])
# Store an observation
oak_remember(observation="The backup dir uses a 3-tier priority", memory_type="decision")
# Mark a resolved gotcha
oak_resolve_memory(id="<uuid from oak_search>")
CLI fallback
# Semantic search
oak-dev ci search "retry with exponential backoff" --type code
# Browse memories by type
oak-dev ci memories --type decision
# Get impact context for a specific file
oak-dev ci context "impact of changes" -f src/services/auth.py
Direct SQL (for aggregations, history, custom queries)
# Recent sessions
sqlite3 -readonly -header -column .oak/ci/activities.db \
"SELECT id, agent, title, status, datetime(created_at_epoch, 'unixepoch', 'localtime') as started FROM sessions ORDER BY created_at_epoch DESC LIMIT 5;"
# Query anything
sqlite3 -readonly -header -column .oak/ci/activities.db "SELECT count(*) FROM sessions;"
Commands Reference
CLI commands
| Command | Purpose |
|---|---|
oak-dev ci search "query" --type code |
Semantic vector search for code |
oak-dev ci search "query" --type memory |
Semantic search for memories |
oak-dev ci search "query" -n 20 |
Broader search with more results |
oak-dev ci context "task" -f <file> |
Get context for current work |
oak-dev ci remember "observation" |
Store a memory (NOT via SQL) |
oak-dev ci memories --type gotcha |
Browse memories by type |
oak-dev ci memories --status active |
Browse memories by lifecycle status |
oak-dev ci resolve <id> |
Mark observation as resolved |
oak-dev ci resolve --session <id> |
Bulk-resolve all observations from a session |
oak-dev ci sessions |
List session summaries |
oak-dev team status |
Check daemon status |
What ships with it
6 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 · 328 lines · 167 tokens per session scan A 06b89b04918e
oak is a skill published in the GitHub repository goondocks-co/open-agent-kit (10 stars, last pushed 3mo ago), licensed MIT. It adds 167 tokens to every session and 3,403 once invoked, about $0.0007 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
apex-context-management
UTILITY SKILL — Two-mode context-window management. RUNTIME: artifact compression (full/summarized/minimal) for orchestrator and codegen agents. AUDIT: post-mortem analysis of Copilot debug logs (token profiling, redundancy, hand-off gaps) for 11-Context Optimizer. WHEN: "context optimization", "token budget"…
inspect-history
Investigate prior AI coding activity, commands, tool outcomes, files, sessions, and tests for an active continuity task without changing project files.
resume-task
Resume an in-progress coding task previously worked on by this or another AI agent using captured local context, Git state, test history, and checkpoints.
session-end
Close a session — summarize changes, suggest commits, write a journal entry (episodic trace), append a NEXT.md handoff block. Chains to dream for substantive sessions. Also writes the PreCompact checkpoint block when invoked by that cue.
dream
Sleep-consolidation pass — replay journal entries and the harness-memory inbox to distill them into garden/essential/USER.md, garden/essential/SOUL.md, garden/ .md, and new procedures in forge/ (T1, within capacity). Reconsolidate T1 items found wrong in use. Propose T2 graduations for Owner ratification (in-session…
session-start
Load the hot read order at every session begin. Full mode on startup (drift check via detect-runtime, consume + clear NEXT.md, brief Owner); re-entry mode after compaction / resume / fork (hot load only). Not the one-time bootstrap (use init).