Packages: F

Every listed package whose name, or scope, starts with F.

@faberon/chat untested Faberon Chat: a Pi extension for drafting plans and operating campaigns
@fadhelhaidar/pi-ask-user untested Standalone Pi questionnaire with combined multi-select and custom answers, Enter-only toggling, and preserved drafts.
@fadhelhaidar/pi-plannotator-compact untested Plannotator Pi extension - interactive plan review with annotations, annotate agent messages, and review code/PRs
@fadhilp/pylon untested Pi workflow extensions and a local web interface.
@fahrizkyputra/pi-auto-resume untested Resume a Pi session automatically after a rate limit: reads the reset hint, waits, then sends a marked continuation. Also waits out 5-hour and weekly plan windows by their real end time, and retries dropped streams and timeless failures on a backoff.
@fahrizkyputra/pi-auto-skill untested After a task, propose turning it into a project skill: the agent drafts it with writing-great-skills, you review and edit it before it is saved to the repo. Afterwards the agent restates your original task, so you never have to scroll back for what is lef
@fahrizkyputra/pi-delete-session untested Delete the active Pi session (and start a fresh one), or multi-select saved sessions to clean up. Confirmation first, extra confirmation for favorites, trash-safe deletion.
@fahrizkyputra/pi-fast-tools untested Fewer and faster tool calls for Pi: recursive grep skips node_modules/build output, tests and builds get a timeout, tsc gets a bigger heap, and the model is told to batch calls and use rg/fd. Optional codemode auto-enable.
@fahrizkyputra/pi-modes untested Selectable, independent agent modes for Pi. /gercep: no tests/typecheck/lint/build, ends with a manual QA checklist. /hati-hati: confirm every risky command, ends with a rollback section. /auto-effort: a small judge model sets thinking per prompt. /auto-r
@fahrizkyputra/pi-session-favorites untested Mark Pi sessions as favorites (★ in the session name) so /resume shows which ones to continue later.
@faiku/pi-default-model-switcher untested Pi extension for switching the default startup model globally or per project
@faiku/pi-faiku-theme untested Pi theme and ASCII input box in opencode's default style, with top-right copy/paste toasts
@faiku/pi-floating-plan untested Pi extension that floats the agent's current plan in a corner of the TUI
@faiku/pi-inline-image-paste untested Pi extension that attaches pasted images inline to your prompt instead of inserting a temporary file path
@falling-ts/pi-chinese untested 强制 pi 全程使用简体中文(思考与输出)。
@falling-ts/pi-working untested 把 pi 运行时的状态指示器翻译为中文(可切英文), 并细分出请求中/响应中/执行中三个阶段。
@fan92rus/pi-goal-x untested Adds /goal to pi: conversational goal planning, flexible or ordered goals, persistent progress, and an independent completion auditor.
@fanchaozz/pi-sentinel untested A pi extension that protects sensitive information (PII & credentials) in coding-agent sessions: inbound tokenization, outbound plaintext restoration for tool calls, derived masked display, and zero-plaintext session persistence.
@fanchaozz/provider-manager untested A pi extension that manages custom providers and models in ~/.pi/agent/models.json via a TUI dashboard, /providers slash command, and remote model sync.
fast-jev-compaction-pi untested Verbatim Jev-guided context compaction for pi: replaces the built-in compaction summary with fast-jev-compaction decisions — stale tool calls/results are dropped or truncated, everything kept stays verbatim.
@fastagent-sh/pi-web-access untested Web search, URL fetching, GitHub repo cloning, PDF extraction, YouTube video understanding, and local video analysis for Pi coding agent. Supports OpenAI, Brave, Parallel, TinyFish, Search1API, Searchinfinity, Querit, Tavily, Firecrawl, Crawl4AI, Jina, SE
@fbraza/pi-cite untested Pi extension with PubMed, Zotero, and literature search tools.
feishu-agent-communication untested 多个AI Agent各干各的，消息靠你手动搬？建一个飞书群把它们拉进来，自动认领、自动交接。直连互@与Gateway路由双路线，兼容OpenClaw/AutoClaw/CherryStudio等8个框架，含8条实测踩坑，MIT
@felipe.3dfx/pi-workflow untested Pi harness package for companion readiness. Product workflow lives in Grupo Ilao engineering skills.
@felores/pi-session-search untested Local, read-only conversation search for Pi sessions
@feniix/pi-devtools untested Devtools extension for pi — branch and PR workflow, release automation, PR feedback resolution, merge commands, with GitHub and Linear tracker support
@feniix/pi-exa untested Exa API extension for pi — web search, content fetching, and advanced search via Exa AI
@feniix/pi-notion untested Notion API extension for pi — read, search, and manage Notion pages, databases, and content
@feniix/pi-ref-tools untested Ref.tools MCP extension for pi — documentation search and URL reading via Ref's Model Context Protocol
@feniix/pi-sequential-thinking untested Archived and no longer maintained: Sequential Thinking extension for pi — structured progressive thinking through defined stages, also runnable as an MCP stdio server
@feniix/pi-statusline untested Fixed two-line status footer for pi with model, thinking, context, git, token, worktree, and skill indicators
@fernado03/oh-my-pi-supreme-token-saver built for omp Amanai reward detector and three toggleable OMP extensions for terse replies, compact shell output, and minimal code decisions — with a manual updater and dry-run support.
@fernado03/pi-flow untested OMP-native static workflows for deliberate engineering decisions — aligned with mattpocock/skills v1.2.x.
@ferologics/pi-extensions untested Custom Pi extensions bundle (deep-review, pi-ghostty-hunk, pi-ghostty-lazygit, pi-notify, pi-slack-user, pi-system-theme, plan-mode, pi-verbosity-control)
@ferologics/pi-skills untested Custom skills for Pi coding agent
@ferris1225/pi-subagents untested A managed sub-agent team for pi: lightweight scout research and artisan implementation, one-shot runs, read-only status, and Git worktree isolation.
@ff-labs/pi-fff works pi extension: FFF-powered fuzzy file and content search
@fiale-plus/pi-rogue untested Public Pi-Rogue package containing the explicit Advisor and read-only Board extension.
figma-bridge-cli untested Figma design data for AI agents: a CLI for shell-only agents and a pi package (one compact tool) — no MCP, no desktop app
find-flight untested Google Flights search for agents — a pi extension (search_flights tool) + portable skill, powered by the fast-flights scraper.
@fink-andreas/pi-linear-tools untested Pi extension with Linear SDK tools and configuration commands
@finn763/pit-stop untested F1 pit-stop for codebases: load, find, propose, fix, ideas, report
@finngi/pi-background untested Managed Bash and session-owned background processes for Pi
@finngi/pi-context untested Project context overlays and selected session instructions for Pi
@finngi/pi-delegation untested Pi agent discovery, delegation and communication
@finngi/pi-permissions untested Approve Pi tool calls by rule, by asking you, or with a classifier model
@finngi/pi-resources untested Session selection of native skills and package guidance for Pi
@firstpick/pi-extension-anthropic-auth-recovery untested Offer a plan-only Pi recovery flow for classified Anthropic compatibility errors.
@firstpick/pi-extension-bang-command-autocomplete untested Autocomplete for !<command> in Pi, with optional shell-history indexing.
@firstpick/pi-extension-codex-fast-mode untested Session-scoped Codex subscription Fast and Ultrafast modes for Pi requests.
@firstpick/pi-extension-cursor-composer untested Pi extension and custom model provider for Cursor SDK Composer 2.5.
@firstpick/pi-extension-docx untested Fail-closed DOCX inspection, rendering, transactional editing, diffing, validation, and commit tools for Pi agents.
@firstpick/pi-extension-git-footer-status untested Enhanced Pi footer with git status, token usage, context usage, and model telemetry.
@firstpick/pi-extension-git-guided-workflow untested Guided Git workflow for Pi TUI and WebUI with explicit commit and push safeguards.
@firstpick/pi-extension-grill-me untested Questionnaire-guided design interview command and persistence tools for Pi.
@firstpick/pi-extension-image-generation untested Choose an OpenRouter image model in Pi and generate images with user confirmation.
@firstpick/pi-extension-nixos-wiki-local untested Local NixOS/Nix documentation search and retrieval tools for Pi backed by minimal sparse clones of official repositories.
@firstpick/pi-extension-release-npm untested Pi command to run npm package release workflow with publish confirmation.
@firstpick/pi-extension-review untested Deterministic frozen-snapshot code reviews for Pi.
@firstpick/pi-extension-safety-guard untested Interactive guardrails for dangerous bash commands and protected file edits in Pi.
@firstpick/pi-extension-setup-skills untested Interactive Pi command to enable or disable local skills from a multi-selection list.
@firstpick/pi-extension-small-modal-reliability untested Task-state, loop-detection, scratchpad, and verification harness for improving small-LLM reliability in Pi.
@firstpick/pi-extension-stats untested Token and cost usage analytics command for Pi session history.
@firstpick/pi-extension-subagent-minimum-fanout untested Guide Pi reviewer provider diversity with same-provider fallback when alternatives are unavailable or blocked.
@firstpick/pi-extension-todo-progress untested Aggressive automatic todo progress widget for multi-goal prompts in Pi.
@firstpick/pi-extension-tools untested Interactive active-tool manager for Pi.
@firstpick/pi-extension-workbook untested High-fidelity, fail-closed XLSX/XLSM inspection, rendering, editing, diffing, and validation tools for Pi agents.
@firstpick/pi-package-webui untested Pi Web UI companion package with a local browser UI CLI plus /webui-start and /webui-status commands.
@firstpick/pi-prompts-code-workflows untested Reusable Pi prompt templates for code review, bug fixing, recommendation implementation, issue analysis, incident triage, and landing-page design concepts.
@firstpick/pi-prompts-git-pr untested Reusable Pi prompt templates for commits, pull requests, and PR review workflows.
@firstpick/pi-skill-code-quality untested Agents should invoke this skill whenever they write or edit code in permanent files, regardless of language or change size. Improve code directly within the authorized task while preserving explicit review-only requests.
@firstpick/pi-skill-deep-research untested 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.
@firstpick/pi-skill-feature-development-workflow untested Portable Agent Skill for governing lightweight and complex feature-development workflows, including planning, delegated implementation, integration, review, reporting, and completion gates.
@firstpick/pi-skill-frontend-design untested Portable Agent Skill for distinctive web interfaces with expected interaction behavior, accessible controls, failure recovery, and task-based verification.
@firstpick/pi-skill-project-readme untested Portable Agent Skill for evidence-based project READMEs with separately approved advanced-user and contributor companion documents.
@firstpick/pi-skill-subagent-governance untested Portable Agent Skill that governs one or more delegated children through role fit, plan-backed workers, one-writer isolation, handoffs, bounded retry safety, and reviewer finding disposition.
@firstpick/pi-themes-bundle untested Firstpick's custom Pi coding agent themes.
@fitchmultz/pi-calculator untested Deterministic high-precision calculator tool for Pi
@fitchmultz/pi-mcp-adapter untested Token-efficient MCP adapter for the Pi coding agent
@fitchmultz/pi-stash untested A pi extension for stashing draft messages and restoring them later.
@fitchmultz/pi-subagents untested Pi extension for subagent orchestration and local session coordination
fito-tui untested Fito for pi: case-based practice for software engineers, in your terminal.
@floez-werk/pi-extension-release-tool untested Release tooling for FloezWerk pi extensions: scaffolding, README release-notes sync, GitHub release notes and the shared CI/CD workflows.
@floez-werk/piagent-pretty-api-error untested Pi extension: renders provider/API errors as a readable, highlighted block with ctrl+o raw-data expansion instead of raw JSON.
@floez-werk/piagent-private-ai untested Pi extension: use private-ai (privatemode.ai) models as a provider
@floez-werk/piagent-realtime-provider-cost untested Pi extension: shows the effective token prices (input/output, per 1M tokens) of the provider/model of the last API call in the status bar.
@floez-werk/piagent-realtime-provider-maxtokens untested Pi extension: clamps max_completion_tokens for OpenRouter requests to the smallest provider endpoint limit, so OpenRouter's length filter stops excluding providers.
@flowot/pi-pition untested Notion 个人记录助手 — 把 Notion 数据库变成 pi agent 的持久化存储（page列表透明、属性追加合并、区间事件记录、5阶段引导配置）。
@floydous/pi-agent-kernel untested Focused code retrieval, editing, safety checks, and language-server support for Pi.
@focksor/pi-token-speed untested pi extension: show assistant output token speed and TTFT in the footer, aggregated across in-process subagents
@fodx/codelens untested Local, branch-aware code search & relation graph. SQLite FTS5 + tree-sitter symbols + source-graph edges, exposed as an MCP server and CLI. No chat LLM required.
@fookhsu/pi-scheduler untested RENAMED to agents-cron — keep this stub only so old `pi-scheduler` crontab entries and installs keep working.
@foolsecret/pi-planmode untested 为 Pi Agent 打造的计划模式 — 只读探索、计划提取与执行进度追踪 | Plan mode for Pi Agent — read-only exploration, plan extraction & execution progress tracking
@foolsecret/pi-pricer untested Pi 模型计费配置中心 — 统一的模型价格与规则引擎 | Model pricing config & rules engine for Pi extensions
@foolsecret/pi-prompt untested 为 Pi Agent 打造的输出精简提示插件 — 多档力度压缩输出 token 省钱 | A prompt-verbosity plugin for Pi Agent — tiered output compression to save tokens & cost
@foolsecret/pi-usager untested Pi Agent 的用量与计费状态栏 — 实时费用、token、缓存命中率与 GLM/DeepSeek 余额 | Usage & billing HUD for Pi Agent — real-time cost, tokens, cache & GLM/DeepSeek balance
fp-skills untested Functional Core / Imperative Shell and Effect workflow skills for Pi
@fractaal/pi-agentic-processes untested Agentic process lifecycle tools for Pi: background bash tasks, sparse monitors, and headless management APIs.
@fractaal/pi-btw untested /btw side conversations for Pi: branch the current context into a tool-blocked panel and optionally send the discussion back.
@fractaal/pi-claude-bridge untested Pi provider bridge that runs Claude Code through the Claude Agent SDK.
@fractaal/pi-context-window untested Portable per-session and per-model context-window budgets for Pi
@fractaal/pi-cross-agent-memory untested Portable Pi extension that injects Claude Code and Codex memory indexes for projects encountered during a Pi session.
@fractaal/pi-directive-roots untested Directive-root loading and mid-turn discovery for Pi across CLAUDE.md, AGENTS.md, MEMORY.md, and shared skill directories.
@fractaal/pi-fractal-compact untested Ben/Fractal high-fidelity compaction extension for Pi.
@fractaal/pi-goal-x untested Portable single-goal runtime for Pi
@fractaal/pi-todo untested Portable branch-local Todo plans for Pi
@fradser/pi-agent-teams untested Multi-agent team system for Pi — resident teammates, shared task board, and peer-to-peer messaging
@fradser/pi-btw untested Side questions for Pi — /btw answers in a read-only overlay, never entering the session history. Unlike Claude Code's /btw, it can actually call read-only tools (read, grep, find, ls) to verify facts in the codebase.
@fradser/pi-context untested Retrieve context for repositories, libraries, and technical questions with one native tool that launches an isolated prompt-constrained Pi research child.
@fradser/pi-impeccable untested Native Pi design procedures with a unified concern-organized taste library
@fradser/pi-memory untested Native /memory command for pi — auto-memory guidance, instructions menu, and manual consolidation (no skill surface)
@fradser/pi-monitor untested Result-contract background monitoring for Pi — capture noisy command output outside model context and expose one structured terminal result
@fradser/pi-plan-mode untested Minimal plan mode for Pi — read-only exploration and planning before implementation, with dedicated model support.
@fradser/pi-recap untested Session recap for Pi — shows a concise summary of what's happening above the TUI input box, like Claude Code's ✦ Recap: feature
@fradser/pi-utils untested Native Pi commands and utilities for continuation, session awareness and control, thinking levels, and git worktrees
@fradser/pi-vision untested Transparent image-to-text bridge for text-only Pi models using a configurable vision model
@francocarballar/pi-turn-tps untested Aggregated turn tokens per second for Pi, excluding tools and gaps between model calls.
@freibergergarcia/phone-a-friend untested CLI relay that lets AI coding agents collaborate
@french-castle/jev-code untested Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, plus one-command setup.
@french-castle/jev-router untested Route each coding-agent turn to the cheapest model that can finish it. Switchyard-style execution signals, TypeSafe's jev as the judge, and honest cost accounting. Works with Claude Code, Codex, OpenCode, and Pi.
@french-castle/skill-scanner untested Scan Agent Skills for prompt injection, hidden instructions, exfiltration, and remote code before Claude Code, Codex, OpenCode, Pi, or npx skills installs them. Standalone and offline by default; TypeSafe's jev is an optional second opinion.
@fro.bot/systematic untested Compound-engineering loops for OpenCode, Pi, and Claude Code
@frostime/pi-provider-usage untested A query-only Pi extension for provider usage, quotas, and balances.
@frostime/pi-usage-analytics untested Tracing and usage analytics for Pi, covering provider/model, directory, timeline, history import, and safe daily compaction.
@ftrdotdev/pi-inquiry untested Interactive questions for the pi coding agent: a single `question` tool renders option lists, tabbed forms, and free-text answers
@ftrdotdev/pi-qrspi untested A planning workflow for [Pi](https://pi.dev) coding agents. The agent works in six phases. You approve each phase before the next one starts. Nothing gets implemented until you approve the plan.
@ftrdotdev/pi-tracker untested Session-persistent todolist extension for Pi
@ftrdotdev/pi-tui untested House TUI components and the pi interface extension: themed boxes, a pure box-frame model, and the header/footer/editor/settings/preview chrome
fv-skills-baif untested Formal verification skills for Pi, Claude Code, Codex, OpenCode, and Antigravity. Rust -> Lean 4 via Aeneas.
@fyeeme/pi-ask-user built for omp oh-my-pi's `ask` tool migrated to a pi extension — tabbed multi-question dialog with a Submit review page, inactivity countdown, RPC degradation, and headless hiding.
@fyeeme/pi-ask-user-lite untested Structured ask_user tool for pi — lets the LLM surface clarifying questions with options, multi-select, recommended defaults, and free-form Other input.
@fyeeme/pi-dynamic-workflows untested Deterministic TypeScript workflow orchestration for pi. Fuses the pi-dynamic-workflows design (declarative graph, 10 step primitives, heuristic planner, outcome collectors) with Claude Code's workflow engine coordination mechanisms (deterministic sandbox,
@fyeeme/pi-goal untested Goal mode for pi — one persistent autonomous objective looped until verified success: goal tool (create/get/complete/impossible/resume/drop), token/time budget accounting with budget-limit steering, automatic continuation turns, /goal and /guided-goal com
@fyeeme/pi-hooks untested Claude Code-compatible hooks runner for pi. Reads hooks config (priority: ~/.pi/agent/hook.json, then project .pi/hook.json) and maps SessionStart, PreToolUse, and Stop events to pi lifecycle events.
@fyeeme/pi-mermaid-viewer untested Render Mermaid diagrams from the conversation in the browser.
@fyeeme/pi-peon-ping untested peon-ping adapter for pi — routes lifecycle events through peon.sh for sound packs, notifications, and trainer reminders.
@fyeeme/pi-review untested Review & cleanup assets for pi: /code-review and /code-simplify commands dispatching declarative prompt templates (parallel strategy as frontmatter data) plus review methodology skills and finder/verifier agent definitions. Spawning lives in @fyeeme/pi-su
@fyeeme/pi-session-name untested Auto-name pi sessions with a short LLM-generated title so --resume lists are easy to scan. Supports first (once) and auto (content-aware rename) modes; never overwrites manual names.
@fyeeme/pi-statusline untested Rich custom status bar for pi with token usage, cost, DeepSeek balance, context window, and timing.
@fyeeme/pi-subagents untested General-purpose subagent fan-out for pi: a `subagent` tool (single/parallel) spawning real pi subprocesses, three-source agent discovery (user/project/bundled), plus the shared dispatch core (spawnAgent, per-call abort, maxTurns budget, concurrency ceilin
@fyeeme/pi-thinking-ui untested Faithful, terminal-native three-mode thinking visualization for Pi.
@fyeeme/pi-todo untested Phased todo list tool for pi — nine operations (init/start/done/rm/drop/block/unblock/append/view) over phase/task state persisted with the session, a /todo command, and a todo_updated event bus broadcast for other extensions.
@fyhax1ki/pi-custom-providers untested Pi extension that manages third-party providers and relay endpoints through models.json