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 autonomous-ai/autonomous-os --skill claude-buddygit clone --depth 1 https://github.com/autonomous-ai/autonomous-osWrote 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/autonomous-ai/autonomous-os/claude-buddy)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00036 | $0.00830 |
| Opus 5 | $0.00018 | $0.00415 |
| Sonnet 5 | $0.00007 | $0.00166 |
| Haiku 4.5 | $0.00004 | $0.00083 |
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 \ 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:
- Express emotion: curious (intensity 0.8)
- Read the approval details from the event message
- Ask the user naturally: mention the tool name and what it affects
- 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:
- Express emotion: curious (intensity 0.8)
- Read the approval details from the event message (tool name + what it affects)
- Ask the user naturally: mention the tool and what it will do
- 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.
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.
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 · 90 lines · 36 tokens per session scan A e041ce3289ba
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.
Other skills, from other repositories
rosclaw-embodied
A set of rules for completing robot tasks in ROSClaw, a system for running and checking robot work. It covers approved robot files, acceptance evidence, and separate rules for simulation and real hardware.
default
Skill "default" from ros-claw/rosclaw, covering skill.md, skill id, intent, preconditions and effects.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
add-matrix
Add Matrix channel integration via Chat SDK. Works with any Matrix homeserver.
add-resend
Add Resend (email) channel integration via Chat SDK.
add-macos-statusbar
Add a macOS menu bar status indicator for NanoClaw. Shows a bolt icon with a green/red dot indicating whether NanoClaw is running, with Start, Stop, and Restart controls. macOS only.