pi-context-view
Pi extension to visualize context usage and inspect the hidden parts: base prompt, tools defs, and extension injections
$ pi install npm:pi-context-viewExtensions, skills, prompt templates, and themes published to npm. Install with pi install npm:<package>. See the package docs for details.
Pi extension to visualize context usage and inspect the hidden parts: base prompt, tools defs, and extension injections
$ pi install npm:pi-context-viewPi terminal UI extension with session management, context inspection, Tool/MCP usage tracking, sidebar panels, and a compact footer
$ pi install npm:pi-ui-extensionLive context pressure and token-use reports
$ pi install npm:@mrclrchtr/supi-contextUnicrab startup splash and the /unipi:info dashboard — this session, context, usage, compaction savings
$ pi install npm:@pi-unipi/info-screenAn opinionated minimal Pi footer - one-line status bar showing subscription usage, path, status, model and context.
$ pi install npm:pi-minimal-footerGuardrail extensions for Agentic Driver: advisory review, bounded Herdr communication, and guarded worker lifecycle.
$ pi install npm:@evoclock/pi-agentic-driverEnhanced Pi footer with git status, token usage, context usage, and model telemetry.
$ pi install npm:@firstpick/pi-extension-git-footer-statusRun a pi coding agent on one goal for days. It checkpoints to disk, sleeps on a countdown, then wakes with an empty context and resumes from loop.md. A long-running autonomous agent loop: one extension, one skill, no build step.
$ pi install npm:circadian-loopMinimal Pi extension that automatically compacts context at a configurable usage threshold.
$ pi install npm:pi-auto-compactCustom footer: model, cost, context usage, git branch, lines changed, tmux status files
$ pi install npm:@nicknisi/pi-statuslineToken/cost inline stats for the pi coding agent: dim transcript line with this turn's output, cumulative tokens, context %, and cost. Modes via /token-summary verbose|brief|off.
$ pi install npm:@erlin-ai/pi-token-summaryPi extension to keep context usage near a configurable soft limit
$ pi install npm:max-contextResponsive Pi footer for session context, active provider usage, and extension statuses.
$ pi install npm:@marcosgilf/pi-footerPi footer with a compact two-line layout for model, thinking, context, cache, subscription quota, session time, Git, and Context Mode
$ pi install npm:@j1nn0/pi-footerpi extension: three-line status area with token-speed sparkline, AI output-time timer, skill counts and estimated default context usage
$ pi install npm:@xiaosat/pi-speed-sparklineSession sidebar for Pi's fullscreen TUI: context, usage, activity, git and tools beside the conversation
$ pi install npm:@oldsuns/pi-sidebarPi extension that shows context window usage visualization
$ pi install npm:pi-context-usageFlight-deck HUD and telemetry deck for pi: live context pressure, token throughput, cost and tool activity, mounted above the editor.
$ pi install npm:pi-cockpit-hudRich custom status bar for pi with token usage, cost, DeepSeek balance, context window, and timing.
$ pi install npm:@fyeeme/pi-statuslineContext usage breakdown for Pi — shows how the model context is split across system prompt, tools, MCP tools, skills, memory files, and messages.
$ pi install npm:@juancrg90/context-barPi package that watches context usage and triggers a tidy handoff before the window runs out.
$ pi install npm:pi-tidy-contextCompact Pi footer statusline with Git/worktree context, token usage, and neon celebrations for exceptional prompt-cache hits.
$ pi install npm:@hank-warren/pi-statuslineShow the agent the context window size, usage, and a planning threshold you set.
$ pi install npm:@utpalsinghdev/pi-context-windowPi extension with a calm two-line context and usage footer
$ pi install npm:@valdo766hi/pi-footerMinimal footer for pi with context gauge and subscription usage bars
$ pi install npm:@ogulcancelik/pi-minimal-footerPi extension: Pi's compaction summary, written by extending the session's cached request. Adds nothing to the context.
$ pi install npm:@prjct.app/pi-self-compactCompact two-line status footer for pi: model, thinking level, tokens, cost, TPS, cache hit rate, context usage, live git diff, and working/turn timers.
$ pi install npm:pi-status-footerCustom pi footer with git status, context usage, cost and model info
$ pi install npm:@giovannipapini/gipi-statusbarPi extension to visualize context usage and inspect the hidden parts: base prompt, tools defs, and extension injections
$ pi install npm:@xprnvd/pi-context-viewCost transparency status line for Pi: full-detail token and cost breakdown (input/output/cache), cache hit rate, context usage, model, and thinking level.
$ pi install npm:@nilskluewer/pi-cost-transparency-statuslineGLM Coding Plan (Zhipu BigModel credit-based plans, incl. team) quota usage in the pi footer — org/project context headers, /glm-quota report, /glm-quota-setup wizard
$ pi install npm:pi-glm-quotaSession spend, live rate-limit windows, footer segments, and per-message timestamps. Display only, never in the model context.
$ pi install npm:@tduyng/pi-costContext windows, account usage, and fast-mode controls for Codex in Pi
$ pi install npm:@eleith-pi/codexPer-model context-usage thresholds for Pi's built-in auto-compaction, so models with different context windows and performance profiles compact at the right time
$ pi install npm:pi-model-aware-compactionStatusline extension for pi-coding-agent - replicates /statusline from Claude Code with customizable templates, git status, model info, and context usage with gradient colors.
$ pi install npm:@pixu1980/pi-statuslineRTK command rewriting and tool output compaction extension for the Pi coding agent. Rewrites bash commands to their rtk equivalents and compacts noisy tool output to reduce context window usage. (fork of MasuRii extension)
$ pi install npm:@estebanforge/pi-rtk-optimizerA compact Pi footer showing model, Git, context, quotas, and active work/subagent status.
$ pi install npm:@mhjerryjin/pi-footerA compact Pi footer with context, cost, cache usage, and a run timer.
$ pi install npm:@lwlee2608/pi-footerLive observability dashboard for pi coding agent sessions — tokens, cost, TPS, runtime, git stats, and context usage
$ pi install npm:pi-observabilityReal-time AI observability — monitor context windows, tool calls, token costs, and compaction for coding agents.
$ pi install npm:@hydrotik/airCompact footer for the pi coding agent — model/thinking and context usage on the left, MCP server count on the right, extension statuses below
$ pi install npm:@alexeyco/pi-statuslineA context-window composition bar with ChatGPT Codex subscription usage for Pi.
$ pi install npm:@pithos-kit/context-barSession token, cost, cache, and context usage for Pi.
$ pi install npm:@marcosgilf/pi-sessionHiViz — audit and refactor standing AI-agent instructions (AGENTS.md/CLAUDE.md/skills/MCP) for prompt debt. Trace every rule before cutting it: probe-verified, safety-preserving; drift checks with MCP usage telemetry, constitution tests, blame provenance,
$ pi install npm:@zorgzeleniy/hivizSee what pi actually sends and where it comes from: per-source attribution of the system prompt (AGENTS.md, skills, memory), per-tool schema cost, real token usage — one /llm-audit command with a settings panel and a clickable HTML report (pi extension).
$ pi install npm:@abianbiya/llm-auditTokens and subsidy (API list-price value) per session, project and every project, in the docked panel. Never touches the model's context.
$ pi install npm:@prjct.app/pi-usage