@fadouse/pi-permission
Native permission and sandbox extension for pi.
6.2k listings for pi
323 results · page 6 of 7
Native permission and sandbox extension for pi.
MikroTik RouterOS .rsc auditor — 115 security checks, CVSS scoring, conflict detection, CVE lookup, cross-checks & linting
Load API keys with secret-tool
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
Official ryk Pi integration for fail-closed bash and file protection.
Use automatically when evaluating or applying Dolt, the Git-like version-controlled SQL database, for database branching, merging, diffs, audit history, rollback, or versioned MySQL replica workflows.
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)
Approval-gated frontend implementation for Pi, combining Implannotator design guidance with Plannotator reviews.
Layered permission control extension for pi-coding-agent
Apply Divio's four-quadrant documentation system to write, audit, classify, restructure, and review technical documentation. Use when creating or improving tutorials, how-to guides, reference docs, explanations, docs...
Professional multi-agent codebase auditing and automated repair engine
Lightweight Docker sandbox for pi coding agent
A pi extension that scans locally installed pi packages for vulnerabilities and supply-chain risk.
Agent security framework. Immutable audit trail, permission policies, self-modification detection, destructive command guard.
Global, multi-project OS sandboxing for the pi coding agent
A read-only two-stage code review extension for pi
A security middleware for Pi that intercepts and blocks the writing of API keys and secrets to disk.
Security reconnaissance toolkit. Headers audit, SSL check, DNS, port scan, tech fingerprinting, path discovery.
High-signal security review package for Pi.
Audit npm dependencies for vulnerabilities, outdated packages, and license compliance — integrated into pi.dev workflow
Orchestrated multi-phase development missions for pi — architect, implement, test, audit, verify
Append-only project-local learning ledger for Pi with two separate trust gates: manual human approval, and a bounded auto-safe machine gate that is on by default in Pi-trusted projects. Selective fork of Matt Devy's pi-continuous-learning.
Lightweight regex-based PII mask/unmask extension for Pi coding agent. Redacts emails, phones, SSNs, credit cards, API keys, and more before they reach the LLM. Restores originals in responses.
iota embedded policy engine as a pi coding-agent extension: hash-pinned bless, agents.yaml enforcement for read/write/edit/bash, JSONL decision log
ABP Pi whiteboarding guard plus whiteboarding skill: one user-facing question at a time.
Pi extension that adds a safe readonly python sandbox in the currrent directory
Block secrets and PII before they land: regex + entropy scanning for files, diffs, and AI coding agents. CLI, MCP server, Claude/Cursor skill, and pi extension.
Core pi extensions: safe-guard, git-guard, auto-session, custom-footer, and more.
Pi agent harness with policy gates, project detection, verification loop, drift protection, artifact validation, and runtime enforcement for weak models
Confirmation and protection layer for dangerous git/bash/edit/write actions
Pi-compatible sandbox extension for filesystem-aware bash and tool enforcement
Sandbox profiles for Pi: open/intro-sec/engineering with file-tool enforcement and telemetry
X/Twitter API v2 reference skill for pi — auth (Bearer / OAuth 1.0a / 2.0), endpoints, pricing, and a mandatory cost guard.
Permission enforcement extension for the Pi coding agent
Dependency health scanner. Outdated, heavy, licenses, dupes, tree.
Security hooks for Pi to reduce accidental destructive actions and secret-file access.
Pi extension that appends system reminders to repeated tool call results.
Supervised job runtime extension for pi with isolated workers, audit artifacts, and retry-aware orchestration.
Auto-recover trapped tool calls from thinking blocks for Qwen3.6 and similar models
Pi extension that confirms before delete/edit operations - protects files from accidental changes
Load shared credentials into Pi while blocking and redacting secret access.
TUI secret prompt for pi — agent asks, user types in a masked input, value never reaches the model
A Pi extension that performs security audits on other extensions before install or update. Uses the currently selected AI model to analyze extension source code against configurable audit rules.
Prevents Windows-native Pi file tools from silently writing to mangled paths when agents reuse Git Bash/MSYS paths like /c/Users/...
Pi extension that prevents context bloat by automatically sandboxing heavy tool outputs (bash, web_search, fetch_content, exa_search, read) to temp files
Prebuilt and audited distribution of the Pi permission system extension
IDE integration for pi with any IDE running a Claude Code plugin-including VS Code, Neovim, IntelliJ IDEA, and other JetBrains IDEs. It lets the LLM interact with your IDE for operations like diff view/approval and lets you reference code from your IDE in
Confirm or block dangerous bash commands before the Pi coding agent executes them.