picodesandbox
OS-level sandboxing for pi with interactive permission prompts
6.2k listings for pi
30 results
OS-level sandboxing for pi with interactive permission prompts
A pi extension that prompts before dangerous bash commands and protected file writes.
Agent profiles for pi — preconfigured model, system prompt, tool restrictions, and permission gates
Numbered approval options and Tab-to-comment for Pi's extension select dialogs, including pi-auto-permissions command approval prompts.
Pi skill for maintaining @gotgenes/pi-permission-system config. Covers pattern matching, safe vs dangerous commands, and the prompt-to-rule workflow.
A comprehensive collection of extension packages for Pi the coding agent — token guard, system context, tool profiler, project detector, dirty guard, permission gate, prompt customizer, auto commit, turn clock, branch navigator, and more.
Reusable Pi agent platform, project adapters, MCP/tool policy, and coding workflow harness.
OS-level sandboxing for pi with interactive permission prompts
A pi extension that prompts before session changes when the current git repo has uncommitted changes.
Sandbox write/edit/bash to the project dir — prompt / deny / allow modes, configurable deny-with-redirect rules, per-session allow-deny memory
Interactive cybersecurity news briefing for the Pi coding agent with live multi-source headlines and deep-dive story prompts
Pi Agent extension: inject a default bash timeout and append timeout policy guidance to the system prompt
Pi package scaffold for pi-prompt-guard
Cross-agent marketplace search: find, audit, and install plugins/skills/themes/prompts across pi, omp, claude code, opencode, gemini cli, and codex
In-process tool guard and subagent posture hardening for Pi coding agent. Enforces filesystem allow/deny lists and domain allowlists on read, write, edit, fetch_content, web_search, and get_search_content — with interactive ask-tier prompts to grant acces
Terminal AI agent for Stellar. Chat-driven payments, path payments, trustlines, and friendbot funding on testnet, with a separate signer daemon that prompts for explicit approval on every signature.
A pi extension that intercepts potentially dangerous bash commands and prompts for confirmation before execution
Claude-style OS-level sandboxing for pi with interactive permission prompts. Coexists with pi-tool-display and other bash-overriding extensions. Forked from carderne/pi-sandbox.
Interactive menus & input for pi — proactive multi-question tabs, option search filter, single/multi select, typed input (text/secret/number/date/path), configurable emoji
Track LLM spending per task and pause when a configurable threshold is reached — continue, refine the prompt, or stop. Pi extension by agentoom.com.
OS-level sandboxing for pi with interactive permission prompts (fork)
Named profiles for pi: bundle model, thinking level, tools, and system-prompt instructions, with a soft model-allowlist guard for separating contexts like a personal OpenRouter budget from a work Vertex AI project.
Session lifecycle tools for Vera agent (ask-user, todo, check-vera, output-guard, compaction, prompt-rules, read-cap, conditional-rules, system-env, skill-catalog, time, notify-sound)
TUI secret prompt for pi — agent asks, user types in a masked input, value never reaches the model
Filesystem boundary enforcement for pi — prompts before the agent escapes your project
Security scanner and runtime protection for Pi Coding Agent
Audit Pi system prompt, tool schema, context usage, and MCP overhead.
Filesystem boundary enforcement for pi — prompts before the agent escapes your project
Council deliberation plugin for Pi with roster templates, personas, audit records, and council workflow prompts
Pilot Inspector — A silent sidecar governance agent for Pi that audits workflow, prompt health, and context hygiene at compaction boundaries. Phase 4: Compaction guard, cross-session trends, auto skill generation.