Repository: agentstack
Author: i-am-bee·Source status: Clear source
Deploy, and share agents with open infrastructure, free from vendor lock-in.
Score basis：Clear source · High execution risk · Claude · Evidence completeness 63%
Pre-install score
69 · Manual review
One primary score for ranking and pre-install decisions; Evidence completeness 63%.
Risk decision
Documented signals
network_access, shell_execution
Install readiness
source-documented · source-link only
SkillTrust only shows install guidance and copy actions; it never executes installs.
Before you install
Review source, permissions, and execution risk first, then alternatives. Scores prioritize review; they do not replace manual judgment.
Install guidance
This area handles the execution step: review explicit or inferred tool fit, then decide whether to copy commands.
Explicitly supported
Claude
Shown with the common install pattern for this tool.
No explicit install command yet. Review the repository and install docs before deciding.Copy is disabled because no explicit command is available yet.
Review source and permissions first. If no explicit command is available, start from the repository guidance.
Current risk hints: network_access, shell_execution
Audit main stage
This stage turns 15 audit dimensions into one pre-install score; the constellation only explains the gaps instead of becoming a second score.
The purpose is visible, but source, permissions, or install evidence needs checking.
Current advice
Review before install
Review source, permissions, and execution details before copying commands.
Execution profile
High
Check command, file-write, and network behavior first.
Evidence completeness
63%
This shows how much public evidence supports the score; it is not a safety certification.
Start with the overall shape and the weakest three items, then use the list below for full labels, scores, and actions.
Start here
Read the weakest three first, then move into the full 15-item list.
Full 15-dimension list
The default view starts from the lowest scores; switch to risk-first when you want severity before score.
Repository
i-am-bee/agentstack
Author
i-am-bee
Community signal
1.1K stars · 170 forks
Favorites
0
Last updated
2026-04-25
Primary source
i-am-bee/agentstack
Source status
Clear source
Install method
source-documented
Related: Keyword overlap...
Why related: Keyword overlap, Same repository ecosystem, Same author
Repository: claude-code
Author: anthropics · Source status: Clear source
Skill Development skill from anthropics/claude-code.
Score basis：Clear source · High execution risk · Claude · Evidence completeness 65%
Related: Also supports Claude, Codex...
Why related: Also supports Claude, Codex, Keyword overlap
Repository: claude-code
Author: anthropics · Source status: Clear source
Agent Development skill from anthropics/claude-code.
Score basis：Clear source · High execution risk · Claude · Evidence completeness 65%
Related: Also supports Claude, Codex...
Why related: Also supports Claude, Codex, Keyword overlap
Repository: openclaw/skills
Author: cinience · Source status: Clear source
Use when working with OpenSearch vector search edition via the Python SDK (ha3engine) to push documents and run HA/SQL searches.
Score basis：Clear source · High execution risk · Claude · Evidence completeness 69%
Related: Also supports Claude, Codex...
Why related: Also supports Claude, Codex, Keyword overlap
Repository: agentstack
Author: i-am-bee · Source status: Clear source
Deploy, and share agents with open infrastructure, free from vendor lock-in.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 65%
Repository: beeai-framework-ts-starter
Author: i-am-bee · Source status: Clear source
Template to quickly start working with Bee Agent Framework.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 65%
Repository: beeai-code-interpreter
Author: i-am-bee · Source status: Clear source
An HTTP service intended as a backend for an LLM that can run arbitrary pieces of Python code.
Score basis：Clear source · High execution risk · Universal · Evidence completeness 65%