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 skills add OXI-717/ai-native-toolkit --skill agent-teamsgit clone --depth 1 https://github.com/OXI-717/ai-native-toolkitWrote 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/oxi-717/ai-native-toolkit/agent-teams)<a href="https://agentmods.dev/skills/oxi-717/ai-native-toolkit/agent-teams"><img src="https://agentmods.dev/badge/skills/oxi-717/ai-native-toolkit/agent-teams/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/oxi-717/ai-native-toolkit/agent-teams"><img src="https://agentmods.dev/badge/skills/oxi-717/ai-native-toolkit/agent-teams.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 | $0.00055 | $0.02184 |
| Opus 5.5 | $0.00022 | $0.00874 |
| Sonnet 5.5 | $0.00011 | $0.00437 |
| Haiku 4.5 | $0.00006 | $0.00218 |
Grade A, and why
agent-teams 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Teams
Coordinate multiple autonomous agents working on a shared task list with direct messaging.
Core principle: Teams for collaboration with shared state. Subagents for focused tasks returning results. Don't use teams when subagents suffice.
When to Use
digraph when_to_use {
"Complex task?" [shape=diamond];
"Independent subtasks?" [shape=diamond];
"Need agents to communicate?" [shape=diamond];
"Need shared task tracking?" [shape=diamond];
"Single agent" [shape=box];
"Subagents (Agent tool)" [shape=box];
"Agent Teams" [shape=box];
"Complex task?" -> "Single agent" [label="no"];
"Complex task?" -> "Independent subtasks?" [label="yes"];
"Independent subtasks?" -> "Need agents to communicate?" [label="yes"];
"Independent subtasks?" -> "Single agent" [label="no - sequential"];
"Need agents to communicate?" -> "Agent Teams" [label="yes"];
"Need agents to communicate?" -> "Need shared task tracking?" [label="no"];
"Need shared task tracking?" -> "Agent Teams" [label="yes"];
"Need shared task tracking?" -> "Subagents (Agent tool)" [label="no - just results"];
}
Use teams:
- Cross-layer work (frontend + backend + tests) needing coordination
- Research with multiple competing hypotheses sharing findings
- PR review with parallel security/performance/tests reviewers
- Large refactoring where agents own separate modules but must align
Use subagents instead:
- Focused tasks where you only need the result
- No inter-agent communication needed
- Simple parallel dispatch (use
dispatching-parallel-agents)
Teams vs Subagents
| Aspect | Subagents (plain Agent) |
Agent Teams (named Agent + shared tasks) |
|---|---|---|
| Context | Own, returns summary | Own, fully independent |
| Communication | Only back to caller | Agents message each other |
| Coordination | Caller manages all | Shared task list + self-coordination |
| Cost | Lower (summarized results) | Higher (each agent = separate Claude) |
| File conflicts | Caller integrates | Risk if agents edit same files |
| Best for | Focused tasks, results matter | Collaboration, discussion matters |
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 · 237 lines · 55 tokens per session scan A f2f0ba78cc59
agent-teams is a skill published in the GitHub repository OXI-717/ai-native-toolkit (9 stars, last pushed 21d ago), licensed MIT. It adds 55 tokens to every session and 2,184 once invoked, about $0.0002 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…