@sherif-fanous/pi-presets-plus
Pi extension: model + thinking + tools + system-prompt presets, with a UI on top.
6.2k listings for pi
445 results · page 6 of 10
Pi extension: model + thinking + tools + system-prompt presets, with a UI on top.
Pi extension that swaps pi's system prompt with a vendored Claude Code system prompt.
A pi coding-agent extension that runs a prompt repeatedly on a timer, pi event, or self-paced (Claude Code-style /loop)
Project-local Pi distribution package: behavioral kernel, skills, prompts, themes, and the four custom agents, with a thin setup CLI.
A scripting language for Pi agents: write the predictable parts of an agent task as code and leave only the fuzzy parts to the model.
Reusable Pi prompt templates for code review, bug fixing, issue analysis, and incident triage.
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
Model Context Protocol (MCP) integration for pi-coding-agent. Connect to any MCP server (stdio, SSE, StreamableHTTP, WebSocket) and use its tools, resources, and prompts natively.
Pi extension that loads a custom system prompt from `~/.pi/agent/system-prompts/*.md` and injects it on every agent turn, with commands to select, toggle, reload, and switch between replace and append modes.
Inject model-specific system prompts into pi turns from local Markdown files.
Memory for pi — Claude-Code-compatible cwd-keyed memory, auto-injected into every prompt. One-command CC→Pi import. The cross-tool on-ramp from Claude Code to pi.
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.
Developer inspection tools for pi: view the system prompt and inspect API request/response round-trips
Drop-in tool-schema and tool-result compression for the Pi coding-agent. Built on TSCG by Furkan Sakizli (SKZL-AI) — wraps @tscg/core and adds tool-result compression plus provider-aware prompt-cache awareness (Anthropic/OpenAI/Ollama). Provider-agnostic,
PI extension that injects markdown rules for any pi tool, including custom registered tools
Independent Pi package that exposes backend-backed Wizard tools and prompt context.
Global, cross-session TODO for pi — persists across all sessions and is auto-injected into every prompt. The disk-backed counterpart to branch-scoped pi todo extensions.
Pi-native agent kit: extensions, skills, themes, prompts, and agents for pi-coding-agent
Trusted Pi extension binding a Pi session to a reviewr pane: prompt context capture, tool-location reporting, and local review-draft staging over a local socket
Pi extension: web search and browsing through a real Playwright browser — JS-rendered pages, cookie walls, SPAs — with prompt-injection sanitization and network-level SSRF protection.
Dev tool: on every provider request, dump the exact payload pi sends (final system prompt plus messages) to a file so you can see precisely what the model receives.
Official Octocode Pi package: system prompt, skills, harness docs, and setup commands for coding agents.
A pi extension that intercepts potentially dangerous bash commands and prompts for confirmation before execution
GPT-5.6, Codex and Pi prompt-caching skill.
Umbrella Pi package: /install picker for a curated set of pi extensions (pi-qq, pi-chrome, pi-linter, pi-bar, pi-prompt-shelf, pi-caveman, pi-graphite, pi-gh-cli, pi-loadout, pi-cp).
Tiny Pi extension that shows the rendered system prompt and active tool schemas at startup.
Pi extension: web_search and web_fetch with 8-stage prompt-injection sanitization and SSRF protection. Zero dependencies.
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.
Inline session linter for Pi — flags vague openers, pronoun soup, scope creep, and other input anti-patterns above the editor.
Kimi K3 prefix-cache optimizer extension for pi-agent (dual-channel, zero-fork)
Interactive menus & input for pi — proactive multi-question tabs, option search filter, single/multi select, typed input (text/secret/number/date/path), configurable emoji
Cleevio taste layer over Atlassian's Rovo MCP server: skill + /spec-from-ticket prompt for the ticket → spec → implementation pipeline. Soft-aware of @cleepi/sdd.
In-process subagent tool for pi with live TUI card widgets, JSONL session logging, and zero system-prompt overhead.
pi extension: a $each@ prompt-loop editor feature with variable insertion over directory children or file lines.
Pi extension: manage per-session system prompt snippets with add/delete UI
StarRouter is a focused model-routing extension for Pi. It chooses the best available model and thinking level for each prompt using a deterministic heuristic prompt profiler, Artificial Analysis benchmark data, provider-scoped model pools, strict model i
Inject a live call-out of the currently-active model into the system prompt each turn, so the orchestrator knows which model it is running and can route accordingly.
Goal mode extension for pi: persistent long-running objectives, /goal-set drafting, Sisyphus prompt style, autoContinue, verification contracts, recursive task lists, and an above-editor status overlay. Fork of pi-goal-x (which forked @capyup/pi-goal).
Spec-Driven Development workflow for pi: skill, prompts, and templates for specs, journals, changelogs, and optional constitution. v0.2.0+ replaces ADRs with spec Decision sections.
Codex-style inline $skill references for the pi coding agent: mention skills anywhere in your prompt and have full SKILL.md bodies injected alongside your message.
Connect [Pi](https://github.com/earendil-works/pi) to your IDE. Pi sees what you have selected in the editor, and you can send it code ranges and diagnostics with a keystroke — no copy-pasting file paths, line numbers, or compiler errors into the prompt.
Track LLM spending per task and pause when a configurable threshold is reached — continue, refine the prompt, or stop. Pi extension by agentoom.com.
Pi skill + prompt + agents for shipping multi-feature work autonomously: decompose a design.md into a DAG of small features, each on its own git worktree+branch off a long-lived epic branch, squash-merged back, then opened as a single PR. Halt only when t
Intent-aware prompt rewriter and execution-contract compiler for Pi
Pi skills and prompt templates for structured YAML artifact workflows: safe-start, codebase-recon, safe-change, architecture review, structured-doc validation, and legacy docs migration.
A blinking cursor and prompt for the Pi coding agent editor
Track skill, prompt-template, extension, and built-in tool usage in pi so you can prune unused resources and keep pi light.
Pi extension: resolve @filepath (files & directories) in AGENTS.md, inject into system prompt