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 moshthepitt/lionclaw --skill team-localgit clone --depth 1 https://github.com/moshthepitt/lionclawWrote 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/moshthepitt/lionclaw/team-local)<a href="https://agentmods.dev/skills/moshthepitt/lionclaw/team-local"><img src="https://agentmods.dev/badge/skills/moshthepitt/lionclaw/team-local/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/moshthepitt/lionclaw/team-local"><img src="https://agentmods.dev/badge/skills/moshthepitt/lionclaw/team-local.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.01175 |
| Opus 5 | $0.00033 | $0.00588 |
| Sonnet 5 | $0.00013 | $0.00235 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
team-local 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 10d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Local
Use this skill to communicate with sibling LionClaw project instances on the
same machine. Do not use sockets, raw HTTP, local project files, or channel
configuration directly. The bundled scripts resolve recipients; the
channel_send MCP tool sends messages.
Available Scripts
scripts/list- lists sibling project instances and route status as JSON.scripts/resolve <instance>- validates one recipient and prints its concreteteam-localroute as JSON.
Workflow
- When the user asks you to contact another local instance, first identify the
intended recipient instance name. Common names include
main,reviewer, andqa. - Run
scripts/listif you need to discover available siblings or check route status. - Run
scripts/resolve <instance>before sending when the recipient is ambiguous, newly mentioned, or the send needs to be important/reliable. - Send by calling the
channel_sendMCP tool with the resolvedchannel_id,conversation_ref, optionalthread_ref, messagetext,format_hint, and any/runtimeattachments. Keep messages concise and include enough context for the receiving instance to act without reading your private chain of thought. - Read the MCP tool result.
"ok": truemeans LionClaw accepted the outbox item;"ok": falsemeans it did not. Report the error code and message instead of inventing recipient delivery status.
Examples
List reachable siblings:
scripts/list
Resolve one recipient:
scripts/resolve reviewer
Then call the channel_send MCP tool using the printed route fields:
{
"channel_id": "team-local",
"conversation_ref": "team-local:peer:<home-id>",
"text": "Please check the latest result and send your conclusion back to main with team-local.",
"format_hint": "markdown"
}
Send an attachment written by the current runtime turn by including it in the MCP call:
{
"channel_id": "team-local",
"conversation_ref": "team-local:peer:<home-id>",
"text": "Report attached.",
"format_hint": "plain",
"attachments": [{ "path": "/runtime/results/report.txt" }]
}
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.
- 10d ago First seen · 126 lines · 66 tokens per session scan A cb7c419db2cf
team-local is a skill published in the GitHub repository moshthepitt/lionclaw (16 stars, last pushed 8d ago), licensed MIT. It adds 66 tokens to every session and 1,175 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
agentfield-use
Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
neuron-structured-output
Design and implement structured output classes for Neuron AI agents using SchemaProperty attributes and validation rules. Use this skill when the user mentions structured output, JSON schema extraction, data validation, output classes, DTOs for AI responses, extracting structured data from LLM, or configuring property…
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…