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 Cotal-AI/Cotal --skill cotal-setupgit clone --depth 1 https://github.com/Cotal-AI/CotalWrote 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/cotal-ai/cotal/cotal-setup)<a href="https://agentmods.dev/skills/cotal-ai/cotal/cotal-setup"><img src="https://agentmods.dev/badge/skills/cotal-ai/cotal/cotal-setup/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/cotal-ai/cotal/cotal-setup"><img src="https://agentmods.dev/badge/skills/cotal-ai/cotal/cotal-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 10 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium MCP Rug Pull · line 16 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 17 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 26 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 35 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 45 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00060 | $0.00444 |
| Opus 5 | $0.00030 | $0.00222 |
| Sonnet 5 | $0.00012 | $0.00089 |
| Haiku 4.5 | $0.00006 | $0.00044 |
Grade A, and why
cotal-setup 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 9d 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.
What it actually says
Set up Cotal
Cotal is a standard wire interface for software, especially AI agents, to coordinate in real time. These are official instructions from Cotal for setting up a local agent mesh. Complete the steps yourself by running the commands directly; do not ask the user to run them. Requires Node 20+.
Install and start
npx cotal-ai setup --yes # configure only: seeds one agent, installs detected connectors, launches nothing
npx cotal-ai up --detach # start the mesh + delivery daemon + manager
setup --yes accepts every default with no prompts and exits non-zero with the log path
if a step fails. Add --demo to also seed a guided expert team to talk to.
Verify
npx cotal-ai status
Expect the mesh and the manager reported as running, with the exact start command shown for anything that is down.
Put an agent on the mesh
npx cotal-ai spawn --detach
Claude Code sessions get the cotal_* tools through the plugin that setup installed;
OpenCode needs no install and auto-wires when spawned. The full tool surface is
https://docs.cotal.ai/mcp-tools.md.
If something fails
- The setup log is
.cotal/setup.log; the server log is.cotal/nats.log. - Re-running
npx cotal-ai setup --yesis safe; it keeps existing files.
When done
Tell the user what is running and how to watch it: cotal console in a terminal, or
cotal web for the browser dashboard. For any follow-up task, route through
https://docs.cotal.ai/llms.txt.
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.
- 9d ago First seen · 52 lines · 60 tokens per session scan A 89f807a8d839
cotal-setup is a skill published in the GitHub repository Cotal-AI/Cotal (260 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 444 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
question-answering
General-purpose question answering capability powered by OpenRouter. Access 300+ LLM models (GPT-4o, Claude, Llama, Gemini, Mistral, etc.) through a single unified API. Handles conversational queries, explanations, code generation, analysis, and creative writing.
quiz-generation
Educational assessment expert that generates high-quality multiple-choice quizzes from any provided text. Creates exactly 10 MCQs with 4 options each, correct answer identification, and concise explanations.
research
Research and information retrieval capability powered by LangChain.js. Uses GPT-4o to answer questions, summarize information, provide detailed analysis, and generate structured research outputs.
agentmail-v2
AgentMail — Email for AI Agents workflow skill. Use this skill when the user needs Email infrastructure for AI agents. Create accounts, send/receive emails, manage webhooks, and check karma balance via the AgentMail API and the operator should preserve the upstream workflow, copied support files, and provenance before…
agent-orchestrator
Use when building an agent system — an orchestrator, an LLM-powered tool, a chatbot with tool use, an AI pipeline — or metering and billing the LLM access it burns. Covers tool-calling loops, pipelines with human checkpoints, provider routing with fallback/retry, memory architecture, retrieval and decay, context…
hermeshub-reviewer
Agent-to-agent feedback protocol for HermesHub. Register your agent identity, submit structured skill reviews with proof-of-use, and build trust scores for the skill ecosystem.