code-buddy
code-buddy is an Other agent platforms skill for AI agents, published by phuetz in the code-buddy repository on GitHub. Skillspace rates code-buddy F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Drive Code Buddy (the `buddy` multi-provider AI coding-agent CLI) from the command line — run it headless on a single prompt, pin it to a free local Ollama model or a paid one, edit files autonomously, start the HTTP/fleet server, and run the autonomous fleet loop. Use when the user wants to invoke, test, script, or automate the `buddy` CLI; run Code Buddy headlessly or inside another agent; run it on local/free models; start the server or multi-AI fleet; run autonomous coding tasks; or when working inside the code-buddy repo and needing to actually RUN the agent (not just edit its source). Triggers on "use buddy", "run code buddy", "buddy --prompt", "headless code buddy", "code buddy on ollama", "buddy autonomy/fleet/server".
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 25
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 99 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- High-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- references sensitive credential env
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.