ashlr-plugin

40 MCP tools that replace high-volumeRead/Grep/Edit/Bashworkflows with versions that returnlesswithout losing what matters. Claude Code gets automatic PreToolUse redirects (ASHLR_HOOK_MODE=redirect); Codex gets first-class plugin packaging, MCP, skills, and nudge-first hooks.

curl -fsSL https://bun.sh/install | bash

# macOS / Linux curl -fsSL https://plugin.ashlr.ai/install.sh | bash # Windows (PowerShell) irm https://raw.githubusercontent.com/ashlrai/ashlr-plugin/main/docs/install.ps1 | iex

Tested on:Ubuntu 22.04 · macOS 14 (Sonoma) · Windows Server 2022 · TypeScript hooks (no bash required)

- First-call savings projection— see your annual savings extrapolated on your very first ashlr call.
- Multi-host MCP— works in Codex, Claude Code, Cline, Claude Desktop, Cursor, Goose, and generic MCP hosts (ASHLR_MCP_HOSTenv var).
- /ashlr-orchestrate-status— inspect past orchestration runs with per-node timings + tokens.
- Orchestration retry + handoff budget— per-node retry-with-backoff; HANDOFF_PAYLOAD capped at 8KB.
- Orchestration central quota accounting—orchestration_usagetable for Team-tier soft-throttle.
- Bun ≥ 1.3 prereq surfaced+ wizard restart enforcement — closes 2 fatal first-touch cliffs.
- Orchestrator overhead bench— measured ~5-30ms/node, 2.8× parallel speedup vs sequential.
- Pre-existing tsc errors fixed+ permanent dashboard date-drift fix via clock injection.

- /ashlr-orchestrate— multi-agent task graphs with parallel execution, dry-run renderer, and tier-gated subprocess wiring.
- /ashlr-orchestrate-status— inspect past orchestration runs with per-node telemetry and 2.8× measured parallel speedup.
- Live genome— PR-aware + commit-aware sections via git post-commit hook and GitHub webhook delta sync.
- AI-Native discoveries— LLM synthesizesdiscoverysections from your commit history automatically.
- Predictive prefetch(Pro/Team)— background warm-cache on everyashlr__readcuts repeat-hit latency.
- PR + issue retrieval—ashlr__grep --include-prs --include-issues --since-dayspulls live GitHub context.
- Freshness badgesin genome retrieval surface staleness so you trust the answer.
- Cross-language bench:TS −61.3% · Python −63.1% · Rust −46.8% (cross-language headline-57.1%holds).
- Founder WAD-D dashboardat/admin/wad-d— daily-active records + segment breakdown + discovery propagation.

Run this once after install so Claude Code stops asking on every tool call:

That adds ashlr MCP wildcards topermissions.allowin~/.claude/settings.json. It is idempotent. Run/reload-pluginsafter changing permissions, or fully quit and restart Claude Code if reload is unavailable.

# 1. Install curl -fsSL https://plugin.ashlr.ai/install.sh | bash # Inside Claude Code: /plugin marketplace add ashlrai/ashlr-plugin /plugin install ashlr@ashlr-marketplace # 2. Use — read a large file (raw would be ~8,400 tokens) ashlr__read { "path": "src/server.ts" } # Returns snipCompact view: head + tail, elided middle — ~1,700 tokens # 3. Check savings /ashlr-savings

Session savings · ashlr-plugin v1.36.0 ──────────────────────────────────────── ashlr__read 6 calls −42,180 tok $0.13 ashlr__grep 3 calls −11,040 tok $0.03 ashlr__edit 2 calls −3,200 tok $0.01 ───────────────────────────────────────────── Session total −56,420 tok $0.17 Lifetime total −284,900 tok $0.86 7-day sparkline ▁▂▃▃▅▆█

Core efficiency tools (replace built-ins with lower-token equivalents):

ashlr Pro connects to a hosted backend athttps://api.ashlr.ai, unlocking features that require server-side state:

The/ashlr-doctorcommand includes acloudcheck that pings/healthzwith a 3-second timeout and reports latency. SetASHLR_API_URL_DISABLE=1to suppress it in offline environments.

The status bar shows live session savings with a 7-day Braille sparkline:

┌─────────────────────────────────────────────┐ │ ashlr −0 tok $0.00 ▁▁▁▁▁▁▁ idle │ └─────────────────────────────────────────────┘ ┌─────────────────────────────────────────────┐ │ ashlr −12,480 tok $0.04 ▁▂▃▄▅▆█ ██ │ └─────────────────────────────────────────────┘ ┌─────────────────────────────────────────────┐ │ ashlr −48,200 tok $0.14 ▁▃▅▆██ ▓▓▓ !! │ └─────────────────────────────────────────────┘

!!appears when context pressure is high. Install:

bun run ~/.claude/plugins/cache/ashlr-marketplace/ashlr/<version>/scripts/install-status-line.ts

# Claude Code one-liner curl -fsSL https://plugin.ashlr.ai/install.sh | bash

git clone https://github.com/ashlrai/ashlr-plugin cd ashlr-plugin && bun install codex plugin marketplace add ashlrai/ashlr-plugin codex plugin add ashlr@ashlr-marketplace bun run scripts/cli.ts codex-doctor --json

/plugin marketplace add ashlrai/ashlr-plugin /plugin install ashlr@ashlr-marketplace /reload-plugins

Verify with/ashlr-status. If/reload-pluginsis unavailable or/ashlr-statusdoes not see the plugin, fully quit and restart Claude Code.

git clone https://github.com/ashlrai/ashlr-plugin \ ~/.claude/plugins/cache/ashlr-marketplace/ashlr cd ~/.claude/plugins/cache/ashlr-marketplace/ashlr && bun install # Then inside Claude Code: # /plugin marketplace add ashlrai/ashlr-plugin # /plugin install ashlr@ashlr-marketplace # /reload-plugins

The free tier is the product — 40 MCP tools, 34 slash commands, the full genome scribe loop, and every benchmark included. No account required.

Pro ($12/mo, 7-day trial) adds cloud infrastructure for developers who need it: cross-machine stats sync, hosted embedding retrieval, cloud LLM summarizer (no local Ollama required), and a live auto-updating savings badge. Team ($24/user/mo, min 3) adds shared encrypted team genome, org savings dashboard, policy packs, and SSO.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

next-devtools-mcp is a MCP server that provides Next.js development tools and utilities for AI coding assistants like Claude and Cursor.

A demonstration server for ActionKit, providing access to Slack actions via Claude Desktop.

MCP server that lets Claude Code agents delegate tasks to agents in other project directories, with parallel dispatch, sessions, and async jobs.

Anchor Browser (https://anchorbrowser.io) is secure infrastructure for computer-use agents — stealth cloud browsers, authentication, captcha bypass, and a hosted MCP server for Cursor, Claude, and Windsurf.

Connects Blender to Claude AI via the Model Context Protocol (MCP), enabling direct interaction and control for prompt-assisted 3D modeling, scene creation, and manipulation.

Context-optimized security plugin for Claude Code that builds architecture maps and redacts secrets.

Charon gives AI clients scoped, auditable access to Lethe memory. connect to Chatgpt or Claude to store memories locally.

Score CLAUDE.md/AGENTS.md, validate clarx-manifest.json, generate CI workflows, and pull repo scan findings into Cursor, Claude, or Grok.