What is Quaid CLAUDE.md?

Project instructions for Quaid, a TypeScript command-line tool that records, indexes and searches Claude Code conversations in a local database.

Changing the conversation parser, SQLite storage, full-text search, analytics exports, terminal interface, web interface or MCP server.

They explain the project structure and data flow so an agent can work on its conversation history, search and interface features.

How SEEDO-Media-Ltd/Quaid configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to SEEDO-Media-Ltd/Quaid. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/SEEDO-Media-Ltd/Quaid/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/SEEDO-Media-Ltd/Quaid

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/seedo-media-ltd/quaid/claude-md/github.svg)](https://agentmods.dev/instructions/seedo-media-ltd/quaid/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/seedo-media-ltd/quaid/claude-md"><img src="https://agentmods.dev/badge/instructions/seedo-media-ltd/quaid/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/seedo-media-ltd/quaid/claude-md"><img src="https://agentmods.dev/badge/instructions/seedo-media-ltd/quaid/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,907 This file is loaded in full into every session.

When invoked 2,907 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.02907	$0.02907
Opus 5	$0.01453	$0.01453
Sonnet 5	$0.00581	$0.00581
Haiku 4.5	$0.00291	$0.00291

Measured 9d ago against content hash c6dd67319503, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Quaid CLAUDE.md scanned grade A with 0 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 9d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quaid — Claude Code Context

What this project is

Quaid is a TypeScript/Node.js CLI tool that automatically captures, indexes, and searches Claude Code conversation history. It watches ~/.claude/projects/ in real time, parses CC's JSONL session files, stores everything in a local SQLite database with FTS5 full-text search, exports to Parquet for DuckDB analytics, tracks token costs, provides a TUI (Ink), a web UI (Express), and an MCP server so CC can query its own history.

The full design spec lives in working/spec.md (kept out of the published repo) — read it if you need full detail on any feature and it's present.

Project structure

src/
  parser/
    models.ts         # All TypeScript interfaces (RawTurn, Turn, Session, Project etc.)
    parser.ts         # JSONL line → Turn object
    scanner.ts        # Walks ~/.claude/projects/, returns SessionFile[]
  db/
    db.ts             # better-sqlite3 connection, schema init, migration
    projects.ts       # Project upsert/query
    sessions.ts       # Session upsert/query
    turns.ts          # Turn insert/query + FTS5 trigger management
    tool-uses.ts      # Tool use insert/query
  sync/
    sync.ts           # Incremental sync orchestrator (mtime-based)
    watcher.ts        # chokidar watcher — detects new/changed .jsonl files, calls sync
  search/
    query.ts          # Gmail-style query string → Query object
    search.ts         # Query object → SQL → SearchResult[]
  analytics/
    export.ts         # SQLite → Parquet export via DuckDB
    queries.ts        # DuckDB analytics queries (tokens by day, cost by project etc.)
  pricing/
    pricing.ts        # Cost calculation: tokens + model → estimated_cost_usd
    bundled.json      # Default Anthropic model pricing (USD per million tokens)
  tui/
    app.tsx           # Ink root — manages which view is active
    dashboard.tsx     # Stats + activity sparkline
    projects.tsx      # Projects list
    sessions.tsx      # Sessions list
    conversation.tsx  # Conversation thread view
    search.tsx        # Search results view
  web/
    server.ts         # Express server setup
    routes.ts         # All API + page routes
    public/           # Static assets for web UI
  mcp/
    server.ts         # MCP server (stdio, @modelcontextprotocol/sdk)
    tools.ts          # Tool handler implementations
  cli/
    index.ts          # Commander.js entry point — all commands registered here

Read the full file on GitHub · 298 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.

9d ago First seen · 298 lines · 2,907 tokens per session scan A c6dd67319503

Subscribe to this mod's changes

Quaid CLAUDE.md is an instructions file published in the GitHub repository SEEDO-Media-Ltd/Quaid (1 stars, last pushed 1mo ago), licensed MIT. It adds 2,907 tokens to every session, about $0.0145 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Writing and docs

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

Quaid: Instructions file for Claude Code