extension
@yevhen.b/pi-preflight
Tool-call approvals and policy rules for Pi.
+2
Packages
6.2k listings for pi · 0 reviewed by us
🛡 Guards & policy Block or rewrite dangerous tool calls, sandbox commands, enforce permissions.
323 results · page 1 of 7
extension
pi-thegreataxios-staples
Personal staple extension for pi coding-agent — protected paths
tool
@tangle-network/tcloud-agent
Agent run-loop primitive over Tangle sandbox transports — runs an AgentProfile against a brief with criterion gates, budget caps, and streaming events. Includes TangleToolProvider for Pi tool integration.
+1
extension
@yoseph_23/implannotator
Approval-gated frontend implementation for Pi, combining Implannotator design guidance with Plannotator reviews.
+3
extension
@akshaykarle/pi-tools
Pi coding agent extensions — security hardening, agent teams and more
+7
extension
@a5c-ai/babysitter-pi
Orchestrate complex, multi-step workflows with event-sourced state management, hook-based extensibility, and human-in-the-loop approval — pi
toolextension
cc-safety-net
A coding agent CLI hook - block destructive git and filesystem commands before execution
+1
extension
betterwright
A persistent, policy-guarded Playwright browser for AI agents with network controls, trusted credential filling, proof screenshots, and CAPTCHA helpers.
+4
promptextension
pi-sandbox
OS-level sandboxing for pi with interactive permission prompts
+2
extension
@xaccefy/pi-casefile
Offensive security case tracker for Pi Agent — bug bounties, CTFs, security audits
+2
extension
@xaccefy/pi-exploitsearch
ExploitSearch extension for Pi Agent — query preview.is security corpus for attack techniques, primitives, and bypasses
extension
@aliou/pi-guardrails
+2
extension
@agentapprove/pi
Agent Approve extension for Pi - approve or deny AI agent tool calls from your iPhone and Apple Watch
+2
skillprompt
@piagent/platform
Reusable Pi agent platform, project adapters, MCP/tool policy, and coding workflow harness.
+4
extension
@amaster.ai/pi-security
Pi extension for resource-aware security policy engine and tool authorization
extension
@johanthoren/jeff
Jeff is a model-native quality control plane and cooperative workflow protocol for trusted operators and friendly agents, not a security sandbox.
+1
extension
@firstpick/pi-extension-safety-guard
Interactive guardrails for dangerous bash commands and protected file edits in Pi.
skillextension
@ory/pi
Ory plugin for Pi (the minimal coding agent): scaffolding skills, a local Ory instance, and authentication, authorization, and audit for every tool call
extension
@agwab/pi-subagent
Minimal subagent runtime for Pi.
+1
extension
pi-permission-system
Permission enforcement extension for the Pi coding agent.
+3
extension
@thurstonsand/pi-permissions
Pi extension package for user, project, and package-level tool permission hooks
+1
extension
pi-defender
Defense-in-depth protection for Pi coding agent. Blocks dangerous commands and protects sensitive files — rename of pi-damage-control.
+4
extension
@wernerbisschoff/pi-gatekeeper
Permission enforcement extension for Pi/OMP
+2
extension
@xynogen/pix-gate
Pi extension — permission gate for dangerous bash commands (confirm/block with TUI dialog)
extension
@pandi-coding-agent/pandi-container
Extensión de Pi para administrar sandboxes de Apple `container` (micro-VMs Linux): un comando /container y una herramienta container_sandbox invocable por el modelo (status/list/create/run/stop/remove).
skill
amber-protocol
Amber Protocol: repository-local governance kit for coding agents — install, audit, validate, and hand off agent-facing project state.
skill
@yammd/forge-skills
Global AI Skills Ecosystem for code review and audit
themeskill
zmarketplace
Cross-agent marketplace search: find, audit, and install plugins/skills/themes/prompts across pi, omp, claude code, opencode, gemini cli, and codex
+1
extension
pi-perm
Config-driven Pi sandbox and permission extension using sandbox-runtime.
+1
promptextension
picodesandbox
OS-level sandboxing for pi with interactive permission prompts
+1
extension
pi-approval-guardian
A fail-closed-by-default Pi approval gate that reviews shell actions, private data access, and sensitive file mutations with an isolated risk model and explicit temporary bypass.
+1
extension
@xaccefy/pi-engage
Authenticated-session manager for Pi Agent — store and resolve cookie, OAuth client-credentials, and mTLS auth for authorized pentest targets
+2
extension
@ramtinj95/pi-infra-command-guard
Approval guard for risky infrastructure, cloud, container, repository, secret, and local file commands in Pi and GPT-5.6 Code Mode
+2
tool
hyperresearch-pi
Deep research harness for pi — tier-adaptive 16-step pipeline with adversarial audit, source provenance, and a persistent searchable vault. Wraps the hyperresearch Python CLI.
+3
extension
@agentoom/pi-reviewer
Post-task multi-area code review extension for pi — 7 specialised review areas (general, security, code quality, UI/UX, testing, performance, scope) with a checkbox picker UI
toolextension
pi-opa-net
OPA-backed bash command guard for the pi ecosystem — structured decision-output.v1 JSON, fail-open default, Claude Code hook protocol compatible. Agent-agnostic engine + CLI.
skill
@firstpick/pi-skill-deep-research
Agents should invoke this skill for high-stakes or complex research needing multi-source evidence, scientific/technical fact-checking, decision traces, or rigorous verification. Runs deterministic two-phase research with schema/policy validation.
extension
@spences10/pi-redact
Tool-output redaction for Pi that replaces likely secrets before they reach the model context
extension
@josephyoung/pi-heimdall
Guardian extension for pi — security guards that block accidental secret exposure, enforce command policies, protect .env files, and sandbox bash commands
+1
toolextension
@bacnh85/pi-windows-tools
Pi extension for Windows-native tool manipulation — shell profiles, path conversion, command execution, WSL bridge, safety policy, and developer tool discovery.
+1
extension
@senad-d/guardme
Deny-first Pi guardrails that keep LLM shell and file access safe, transparent, and user-approved.
extension
@gotgenes/pi-permission-model-judge
Deny-first typo-path model judge — a pi-permission-system Authorizer chain link
extension
@spences10/pi-confirm-destructive
Git-aware Pi guardrail that asks for confirmation before destructive shell actions can change or lose work
extension
@monotykamary/pi-localterm
localterm <-> pi integration: Kitty graphics for the browser renderer, scrubbing localterm-managed secret env vars from the agent's bash-tool children, and OSC 9 desktop notifications when the agent finishes a long turn.
extension
@erichll/pi-sandbox
Sandbox Runtime-backed Linux and macOS sandbox with pi-auto-review approval
+3
skill
@soulofzephir/pi-skill-pentesting
Comprehensive pentesting & security check skill for Pi coding agent - headers, ports, SQLi, XSS, OWASP Top 10
skill
@loopskills/claude-skills
Research-driven planning, debugging, and audit skills for Claude Code and Pi
+2
skillextension
pi-permission-modes
Declarative, user-definable permission modes for the pi coding agent: OS-level sandboxing (bubblewrap / sandbox-exec), an allow/ask/deny policy engine, real bash AST gating (tree-sitter), tool hiding, and skill/custom-tool gating.
+3