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 Aicoo-Team/AICOO-Skills --skill connect-local-agentgit clone --depth 1 https://github.com/Aicoo-Team/AICOO-SkillsWrote 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/aicoo-team/aicoo-skills/connect-local-agent)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00143 | $0.01519 |
| Opus 5.5 | $0.00057 | $0.00608 |
| Sonnet 5.5 | $0.00029 | $0.00304 |
| Haiku 4.5 | $0.00014 | $0.00152 |
Grade A, and why
connect-local-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connect Local Agent — start the collaboration bridge
You set up and start the Aicoo local-agent bridge on the user's machine. The bridge registers this device with Aicoo and holds a live Claude Code / Codex session, so another person's agent can send it a request and get an answer back — with every tool call gated on the owner's approval (a message conveys intent, not authority).
This is the reachable side. The bridge is a long-lived process — it must keep running.
Prerequisites
AICOO_API_KEYenvironment variable set (aicoo_sk_live_...)- Claude Code CLI ≥ 2.1.211 (the bridge drives it as the local runtime)
git+ Node.js
echo "${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.
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.
- 2mo ago First seen · 126 lines · 143 tokens per session scan A 4c1755db03c3
connect-local-agent is a skill published in the GitHub repository Aicoo-Team/AICOO-Skills (35 stars, last pushed 3mo ago), licensed MIT. It adds 143 tokens to every session and 1,519 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
security-conductor
Operating procedure for the kirocrew-security-conductor agent. Use when a security conductor session is seeded, inspected or debugged. Run vulnerability discovery on one target as a supervised fleet — one auditor per attack surface, an independent verifier per finding, two human gates.
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".
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
explain-for
Explain a topic, code, error or design decision for one named audience (a 5-year-old, a manager, a designer, a grad student, a parent). Resolves who it is for, pins the ground truth first, then tunes vocabulary, analogy, tone and depth to that audience. Use when an audience is named.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.