Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From agentic-usability
Launch an interactive shell inside a microsandbox for debugging agent auth, environment, and workspace setup. Supports bare, executor, and judge modes with optional test case scaffolding.
npx claudepluginhub pspdfkit-labs/agentic-usability --plugin agentic-usabilityHow this skill is triggered — by the user, by Claude, or both
Slash command
/agentic-usability:sandbox [project-directory] [--mode executor|judge] [--test TC-001] [--target node-20] [--run runId][project-directory] [--mode executor|judge] [--test TC-001] [--target node-20] [--run runId]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Launch an interactive shell inside a microsandbox identical to what the pipeline uses. Useful for debugging agent auth, inspecting environment variables, testing commands, and reproducing sandbox issues.
Guides designing, deploying, and operating kubernetes-sigs/agent-sandbox Kubernetes operator for AI agent runtimes in isolated pods, authoring Sandbox CRDs, tuning warm pools, and SDK integration.
Builds secure code execution sandboxes on Cloudflare Workers with Sandbox SDK. Handles commands, Python/JS/TS interpreters, files, ports; prefers Cloudflare docs retrieval.
Enables secure execution of untrusted Python/Node.js code, git operations, and scripts in persistent Linux containers on Cloudflare edge using Workers SDK.
Share bugs, ideas, or general feedback.
Launch an interactive shell inside a microsandbox identical to what the pipeline uses. Useful for debugging agent auth, inspecting environment variables, testing commands, and reproducing sandbox issues.
echo "Arguments: $ARGUMENTS"
By default the sandbox boots with just the target image, secrets, and env vars — no agent install or workspace setup.
agentic-usability sandbox -p <project>
Boots a sandbox with the configured secrets and env vars. Nothing else is installed or scaffolded.
agentic-usability sandbox -p <project> --mode executor
agentic-usability sandbox -p <project> --mode executor --test TC-001
Installs the executor agent CLI. With --test, also scaffolds the workspace, uploads PROBLEM.md, and uploads public sources — mirroring the execute stage setup.
agentic-usability sandbox -p <project> --mode judge --test TC-001
agentic-usability sandbox -p <project> --mode judge --test TC-001 --run <runId>
Installs the judge agent CLI. With --test, restores the workspace snapshot from a previous run (or uploads solution files), uploads all sources (private + public) — mirroring the judge stage setup.
| Flag | Default | Description |
|---|---|---|
--target <name> | first in config | Which target image to use |
--mode <mode> | (none) | executor or judge — installs agent CLI and optionally sets up workspace |
--test <id> | (none) | Test case to scaffold (requires --mode) |
--run <runId> | latest | Run to load workspace snapshot from (judge mode) |
--output <dir> | results/sandbox-debug-<timestamp>/ | Directory to save debug artifacts |
Once inside the sandbox, you have a full shell. Press Ctrl-] to detach and destroy the sandbox.
Common debugging tasks:
printenv | grep KEY — check which env vars are setcodex login --with-api-key — test Codex authcat /workspace/PROBLEM.md — verify problem statementls /workspace/sources/ — check uploaded sourcesAfter detaching, the following artifacts are saved to the output directory:
| File | Description |
|---|---|
agent-egress.log.json | Network traffic captured during the session |
setup.log | Scaffolding and agent install output |
workspace-snapshot.tar.gz | Tarball of /workspace after session ends |
agent-session.jsonl | Agent CLI session log (if available) |
Run agentic-usability sandbox -p $ARGUMENTS and report the results.