claude-buddy

claude-buddy is a skill for Claude Code, Codex from autonomous-ai/autonomous-os. It costs 36 tokens per session (830 once invoked), scanned A, original, Apache-2.0.

A skill for coordinating with Claude Desktop and Claude Code, which are AI tools running on the user's Mac.

In plain words
What is it for?
It helps read an approval request aloud, then approve or deny it when the user responds.
Why use it?
It lets the user approve or reject Claude's waiting tool-permission requests by voice and keeps track of Claude's activity.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit It helps read an approval request aloud, then approve or deny it when the user responds.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/autonomous-ai/autonomous-os/claude-buddy
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 autonomous-ai/autonomous-os --skill claude-buddy
Clone the repo
git clone --depth 1 https://github.com/autonomous-ai/autonomous-os

Made for: Claude Code, Codex.

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 claude-buddy

README.md
[![agentmods](https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/claude-buddy/github.svg)](https://agentmods.dev/skills/autonomous-ai/autonomous-os/claude-buddy)
Your own site
<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-os/claude-buddy"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/claude-buddy/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 claude-buddy

Your own site · 80×15
<a href="https://agentmods.dev/skills/autonomous-ai/autonomous-os/claude-buddy"><img src="https://agentmods.dev/badge/skills/autonomous-ai/autonomous-os/claude-buddy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 830 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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: 1 finding, 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 Data Exfiltration · line 25
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00036 $0.00830
Opus 5 $0.00018 $0.00415
Sonnet 5 $0.00007 $0.00166
Haiku 4.5 $0.00004 $0.00083

Measured 10d ago against content hash e041ce3289ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

claude-buddy scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST http://127.0.0.1:5002/claude-desktop/approve \
skills/claude-buddy/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Buddy

The user runs Claude on their Mac (Claude Desktop and/or Claude Code). A companion daemon on this device bridges them: it surfaces Claude's state and asks you to approve tool permission prompts out loud, so the user can say "yes" instead of clicking. The daemon listens on 127.0.0.1:5002.

When you receive a [sensing:buddy_approval] event

Claude Desktop is waiting for the user to approve or deny a tool call.

Workflow:

  1. Express emotion: curious (intensity 0.8)
  2. Read the approval details from the event message
  3. Ask the user naturally: mention the tool name and what it affects
  4. Wait for the user's verbal response

If user says approve/yes/ok/go ahead:

curl -s -X POST http://127.0.0.1:5002/claude-desktop/approve \
  -H "Content-Type: application/json" \
  -d '{"id": "<prompt_id from event>"}'

If user says deny/no/skip/cancel:

curl -s -X POST http://127.0.0.1:5002/claude-desktop/deny \
  -H "Content-Type: application/json" \
  -d '{"id": "<prompt_id from event>"}'

When you receive a [sensing:claude_code_approval] event

Claude Code (the CLI on the user's Mac) is waiting for the user to approve or deny a tool call. The Mac is blocked on your answer, so respond promptly.

Workflow:

  1. Express emotion: curious (intensity 0.8)
  2. Read the approval details from the event message (tool name + what it affects)
  3. Ask the user naturally: mention the tool and what it will do
  4. Wait for the user's verbal response

If user says approve/yes/ok/go ahead:

curl -s -X POST http://127.0.0.1:5002/claude-code/approve \
  -H "Content-Type: application/json" \
  -d '{"id": "<prompt_id from event>"}'

If user says deny/no/skip/cancel:

curl -s -X POST http://127.0.0.1:5002/claude-code/deny \
  -H "Content-Type: application/json" \
  -d '{"id": "<prompt_id from event>"}'

If you don't answer in time the Mac falls back to its own on-screen dialog — no harm done, but answering promptly is what makes the voice flow feel instant. Say "Claude Code" naturally; never mention prompt ids, HTTP, or these internals.

Read the full file on GitHub · 90 lines

Files

What ships with it

1 file 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.

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. 10d ago First seen · 90 lines · 36 tokens per session scan A e041ce3289ba

Subscribe to this mod's changes

claude-buddy is a skill published in the GitHub repository autonomous-ai/autonomous-os (317 stars, last pushed today), licensed Apache-2.0. It adds 36 tokens to every session and 830 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.