connect-local-agent

connect-local-agent is a skill for Claude Code from Aicoo-Team/AICOO-Skills. It costs 143 tokens per session (1,519 once invoked), scanned A, original, MIT.

A setup guide for making the coding agent on your computer reachable by another person’s agent through a live collaboration bridge.

In plain words
What is it for?
Connecting a local Claude Code or Codex session, keeping the bridge running, and allowing paired agents to send requests to it.
Why use it?
It explains the prerequisites and setup needed for agent-to-agent collaboration while requiring the local owner to approve tool actions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex.

Part of the Aicoo Agent Skills plugin — 21 skills shipped together

Good fit Connecting a local Claude Code or Codex session, keeping the bridge running, and allowing paired agents to send requests to it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aicoo-team/aicoo-skills/connect-local-agent
Install

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.

Any agent
npx skills add Aicoo-Team/AICOO-Skills --skill connect-local-agent
Clone the repo
git clone --depth 1 https://github.com/Aicoo-Team/AICOO-Skills

Made for: Claude Code.

Or install Aicoo Agent Skills, the plugin that ships this one along with the rest of its 21 skills.

Wrote 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.

agentmods badge for connect-local-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/aicoo-team/aicoo-skills/connect-local-agent/github.svg)](https://agentmods.dev/skills/aicoo-team/aicoo-skills/connect-local-agent)
Your own site
<a href="https://agentmods.dev/skills/aicoo-team/aicoo-skills/connect-local-agent"><img src="https://agentmods.dev/badge/skills/aicoo-team/aicoo-skills/connect-local-agent/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.

agentmods 80×15 button for connect-local-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/aicoo-team/aicoo-skills/connect-local-agent"><img src="https://agentmods.dev/badge/skills/aicoo-team/aicoo-skills/connect-local-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 143 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,519 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

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 →

  • high Privilege Escalation · line 59
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Rogue Agent · line 50
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 110
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00143 $0.01519
Opus 5 $0.00072 $0.00759
Sonnet 5 $0.00029 $0.00304
Haiku 4.5 $0.00014 $0.00152

Measured 12d ago against content hash 4c1755db03c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

connect-local-agent 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 12d 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.

skills/connect-local-agent/SKILL.md · 126 lines

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.

Connect Local Agent — start the collaboration bridge

You set up and start the Aicoo local-agent bridge on the user's machine. The bridge registers this device with Aicoo and holds a live Claude Code / Codex session, so another person's agent can send it a request and get an answer back — with every tool call gated on the owner's approval (a message conveys intent, not authority).

This is the reachable side. The bridge is a long-lived process — it must keep running.

Prerequisites

  • AICOO_API_KEY environment variable set (aicoo_sk_live_...)
  • Claude Code CLI ≥ 2.1.211 (the bridge drives it as the local runtime)
  • git + Node.js
echo "${AICOO_API_KEY:+API key set (${#AICOO_API_KEY} chars)}" || echo "NO AICOO_API_KEY"
claude --version   # need ≥ 2.1.211; install/upgrade: npm i -g @anthropic-ai/claude-code

If AICOO_API_KEY is missing, get one at https://www.aicoo.io/settings/api-keys (or run onboarding).


Step 1: Get the bridge

if [ ! -d aicoo-local-agent ]; then
  git clone https://github.com/Aicoo-Team/aicoo-local-agent.git
fi
cd aicoo-local-agent && git pull --ff-only 2>/dev/null; npm install

The bridge is the open-source Aicoo Local Agent (Apache-2.0) — anyone can clone it. It bundles both a self-hostable reference control plane and the hosted-Aicoo transport used below.


Step 2: Start the bridge (background, keep alive)

Server: production https://www.aicoo.io, or a preview the user names (e.g. https://yourcoo.ai) via CCD_SERVER_URL.

SERVER="${CCD_SERVER_URL:-https://www.aicoo.io}"
SPOOL="me.spool"   # remember this file — the asker side needs it for its reply route

nohup env \
  CCD_AICOO=1 \
  CCD_SERVER_URL="$SERVER" \
  CCD_TOKEN="$AICOO_API_KEY" \
  npm run bridge -- --adapter claude-code --spool "$SPOOL" \
  > bridge.log 2>&1 &
echo "bridge starting (pid $!) against $SERVER — logging to bridge.log"

CCD_AICOO=1 selects the Aicoo transport; CCD_TOKEN reuses the API key (an OAuth access token works too); the bridge registers its endpoint + a managed session and heartbeats. deviceId is auto-generated and persisted next to the spool. It does not auto-set the default route — Step 4.

Read the full file on GitHub · 126 lines

Changes

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.

  1. 12d ago First seen · 126 lines · 143 tokens per session scan A 4c1755db03c3

Subscribe to this mod's changes

connect-local-agent is a skill published in the GitHub repository Aicoo-Team/AICOO-Skills (35 stars, last pushed 1mo ago), licensed MIT. It adds 143 tokens to every session and 1,519 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

artifact-deploy

One-click deploy a user's pre-built app/artifact into their OWN AWS account and get a global public HTTPS link (Vercel-like), with a default TTL and promote-to-persistent. Use when the user says "deploy this", "ship this demo", "give me a public link", "share this externally", or "deploy to AWS".

kirodotdev/KiroCrew · 74 tokens

explain-for

Explain a topic, a piece of code, an error, or a design decision calibrated to one named audience — a 5-year-old, a 5th grader, a manager, a designer, a graduate student, a parent. Resolves who the explanation is for (from the request, or from what memory already records about that person), establishes the ground…

kirodotdev/KiroCrew · 102 tokens

learn-from-sage

Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.

kirodotdev/KiroCrew · 56 tokens

papyrus-latex-suggestions

Propose actual inline replacement text (old → new) as accept/reject suggestions — LaTeX "suggesting mode" / track changes — that render directly in the PDF. Use when the author wants concrete edit proposals they can see and accept or reject. For remarks ABOUT the text (notes, not replacements), use…

kirodotdev/KiroCrew · 77 tokens

mochi-remind

Handle due reminders — notify the user with natural language and mark them done.

kirodotdev/KiroCrew · 20 tokens

agent-initialization

Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.

Prism-Shadow/penguin-harness · 30 tokens