setup

A setup procedure for PAI Knowledge OS, a local system that indexes and searches stored information and gives Claude access to that memory.

In plain words
What is it for?
Use it after cloning PAI or when checking an existing installation, including prerequisites, indexing, daemon setup, MCP registration, and troubleshooting.
Why use it?
It removes the manual work of selecting storage, building components, installing the background service, and connecting the command-line and memory tools.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/mnott/pai/setup
Any agent
npx skills add mnott/PAI --skill setup
Clone the repo
git clone --depth 1 https://github.com/mnott/PAI

Made for: Claude Code, Codex.

Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,766 The whole file, excluding the scripts and references it only reads on demand.
Security scan E 4 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00105 $0.06766
Opus 5 $0.00053 $0.03383
Sonnet 5 $0.00021 $0.01353
Haiku 4.5 $0.00011 $0.00677

Measured 2d ago against content hash def6a98f5c96, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade E, and why

setup scanned grade E with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 ~/.config/pai/config.json

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

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

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -q "PAI_DIR" ~/.claude/settings.json 2>/dev/null && echo "SETTINGS_OK" || echo "SETTINGS_MISSING"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://bun.sh/install | bash
.claude/skills/setup/SKILL.md · 756 lines

How it starts

The opening of the file, as written. The whole thing — 756 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PAI Knowledge OS - Setup

Gets PAI fully running from a fresh clone — or verifies an existing install is healthy.

Each step checks the current state first. If already done, it reports what was found and skips. If partially done, it completes only the missing parts. Running this on a fully installed system is safe and informative.

Quick path: For most users, pai setup handles everything automatically — storage, CLAUDE.md, PAI skill, hooks, settings.json wiring, statusline, daemon, and MCP registration. The steps below document what pai setup does internally and how to troubleshoot each part.

What PAI Is

PAI has three components:

Component Binary Role
CLI dist/cli/index.mjs The pai command — indexing, search, management
Daemon dist/daemon/index.mjs Background service, launchd-managed as com.pai.pai-daemon
MCP shim dist/daemon-mcp/index.mjs Thin proxy from Claude Code to daemon over Unix socket

The daemon does the heavy lifting (indexing, embeddings). The MCP shim gives Claude Code access to PAI's memory tools. The CLI lets you inspect and manage everything.


Step 1 — Check Prerequisites

Check first:

bun --version
docker --version 2>/dev/null || echo "Docker not installed"

If already done:

Bun [version] is installed. Docker [version / not installed]. Continuing.

If Bun is missing:

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

Then open a new shell so bun is on $PATH. Docker is optional — only needed for PostgreSQL mode.


Step 2 — Install Dependencies and Build

Check first:

# Check if the build is current: dist must exist AND be newer than src
REPO="$PWD"   # set this to wherever PAI was cloned

if [ -f "$REPO/dist/cli/index.mjs" ] && \
   [ -f "$REPO/dist/daemon/index.mjs" ] && \
   [ -f "$REPO/dist/daemon-mcp/index.mjs" ]; then
  # Check if any source file is newer than the build output
  NEWEST_SRC=$(find "$REPO/src" -name "*.ts" -newer "$REPO/dist/cli/index.mjs" 2>/dev/null | head -1)
  if [ -z "$NEWEST_SRC" ]; then
    echo "BUILD_CURRENT"
  else
    echo "BUILD_STALE: $NEWEST_SRC is newer than dist"
  fi
else
  echo "BUILD_MISSING"
fi

Read the full file on GitHub · 756 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 756 lines · 105 tokens per session scan E def6a98f5c96

Subscribe to this mod's changes

setup is a skill published in the GitHub repository mnott/PAI (45 stars, last pushed 8d ago), licensed MIT. It adds 105 tokens to every session and 6,766 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it E with 4 findings (asks for root, downloads and executes remote code, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens