agent environment check
Diagnostic tool to verify file paths, directory writability, and state persistence for AI agent skills.
Free
Works with the AI Agents you already use
agent environment check
Example session with this skill installed
Run the environment check to see if we can save persistent data in this skill folder.
- Read your context and instructions
- Compiled the agent environment check
I have executed the diagnostic script to map the environment and verify write permissions.
Environment Diagnostic Report
| Metric | Value |
|---|---|
| Persistence Verdict | persisted |
| Skill Folder | /home/user/agent/skills/env-check/ |
| Working Directory | /home/user/agent/ |
| Writability | True (verified via write-read-delete test) |
| Python Version | 3.10.12 |
| Runs Recorded | 2 |
{
"location": {
"script": "/home/user/agent/skills/env-check/scripts/check_environment.py",
"folder": "/home/user/agent/skills/env-check/scripts",
"cwd": "/home/user/agent/",
"is_under_cwd": true
},
"write_tests": {
"skill_folder": "writable",
"tmp": "writable",
"cwd": "writable"
},
"persistence": {
"verdict": "persisted",
"install_id": "8f2d3a1b",
"runs_recorded": 2
},
"delivered_files": [
{"name": "check_environment.py", "size": 4096},
{"name": "state.json", "size": 124}
]
}
Next steps
- You can safely use the skill folder for local caching as persistence is confirmed.
- Use the absolute path
/home/user/agent/skills/env-check/for any internal file references. - Proceed with installing dependencies in the detected virtualenv at
/home/user/agent/.venv.
Connects securely to your tools. The creator never sees your data.
About this skill
When building skills that need to cache OAuth tokens, store local databases, or run scripts, guessing file paths and permissions is a recipe for runtime errors. This skill removes the guesswork by running a live diagnostic to verify exactly where your agent files land and what it can actually write to.
What it does
- Absolute path discovery identifies the script location, skill folder, and agent working directory.
- Write-test validation performs real create-write-read-delete cycles against five candidate directories.
- Persistence verification tracks state between runs to determine if files written to the skill folder survive.
- Bundle auditing lists every file delivered alongside the script to verify full package arrival.
- Environment probing reports Python versioning, virtualenv status, and critical shell variables.
How it works
- Initialize the script to capture baseline paths and environment metadata.
- Execute write tests across local directories to confirm actual filesystem permissions.
- Write state to a local file to prep for the persistence check.
- Run again to compare the current state against the previous run for the persistence verdict.
Frameworks & tools
This skill requires Python 3.9 or newer. It uses only the standard library with no external package dependencies.
Why this beats prompting it yourself
Prompting an agent to "find its directory" often returns relative paths or hallucinated locations depending on the shell environment. This tool uses actual OS execution to confirm permissions and state survival, providing a concrete JSON manifest rather than a guess.
Use cases
- Verify persistence for skills that need to store local SQLite databases or JSON caches.
- Debug deployment issues when a bundled script or asset fails to load.
- Confirm writability before attempting to generate logs or temporary artifacts.
Known limitations
Requires an agent with shell execution capabilities. It cannot test persistence in a single run; a second invocation is necessary to confirm file survival.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LLM Ops.
Requires shell access. Persistence verdict requires two separate runs. Does not detect network-level constraints.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 4 days ago
- Free with an Agensi account
- Software
Python