textrawl CLAUDE.md

textrawl CLAUDE.md is an instructions file for coding agents from jeffgreendesign/textrawl. It costs 2,814 tokens per session, scanned A, original, MIT.

A personal knowledge server that searches imported documents using both meaning-based search and exact-text search, while also supporting a memory graph, conversation recall, and proactive insights. It stores data in PostgreSQL with vector-search support.

In plain words
What is it for?
Use it when installing dependencies, configuring the environment, developing or building the Node.js server, checking types, linting, or working on its website, desktop app, or dashboard.
Why use it?
It records the required tools, package manager, workspace layout, and embedding constraints so agents can develop and run the server correctly.

Instructions file

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 instructions/jeffgreendesign/textrawl/claude-md
Clone the repo
git clone --depth 1 https://github.com/jeffgreendesign/textrawl

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.

agentmods badge for textrawl CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jeffgreendesign/textrawl/claude-md.svg)](https://agentmods.dev/instructions/jeffgreendesign/textrawl/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jeffgreendesign/textrawl/claude-md"><img src="https://agentmods.dev/badge/instructions/jeffgreendesign/textrawl/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,814 This file is loaded in full into every session.
When invoked 2,814 The same file — it is already loaded in full.
Security scan A 0 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 $0.02814 $0.02814
Opus 5 $0.01407 $0.01407
Sonnet 5 $0.00563 $0.00563
Haiku 4.5 $0.00281 $0.00281

Measured 3d ago against content hash ecfdd2d890c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

textrawl 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 3d 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 · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Textrawl is a personal knowledge MCP server: hybrid (vector + FTS) search over imported documents, a memory graph, conversation recall, and proactive insights. Postgres + pgvector (Neon). Supports OpenAI, Google AI, or Ollama embeddings — not interchangeable (different dimensions; you cannot switch without re-embedding).

Toolchain

  • Node.js >= 22 required. preinstall runs only-allow pnpm — npm/yarn will be rejected.
  • ESM project ("type": "module"). All imports MUST use explicit .js extension even for .ts files.
  • Package manager: pnpm 9.15+. Workspace includes website/, desktop/, and dashboard/.

Commands (from package.json)

Task Command
Install deps pnpm install
Interactive env setup pnpm setup (generates .env with secure token)
Dev server (watch) pnpm dev
Build server pnpm build (tsc + esbuild bundle to dist/)
Start built server pnpm start
Typecheck pnpm typecheck
Lint (Biome) pnpm lint / pnpm lint:fix
Lint (Markdown) pnpm lint:md
Unit tests pnpm test (vitest, run once)
Single test file pnpm test path/to/file.test.ts
Test watch mode pnpm test:watch
Quick quality pnpm quality (lint + lint:md + typecheck)
Fast local gate pnpm verify:fast (quality + test + security/docs/tool-sync checks)
Canonical CI gate pnpm verify (verify:fast + build + docs build)
MCP inspector pnpm inspector (against running localhost:3000/mcp)
Desktop app dev pnpm desktop:dev
Docs site dev pnpm docs:dev
CLI convert pnpm convert -- <subcommand> ...
CLI upload pnpm upload -- <path>
Postgres analysis pnpm pg:analyze
Insights backfill pnpm insights:backfill (windowed scan over whole corpus)

The verify gates invoke three shell scripts directly: scripts/security-check.sh (secret/RLS scan; also exposed as pnpm security-check), scripts/docs-check.sh (doc freshness; no pnpm alias), and scripts/tool-sync-check.sh (also exposed as pnpm tool-sync; asserts the MCP tool list stays in sync between src/tools/, README.md, and AGENTS.md).

Read the full file on GitHub · 147 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. 3d ago First seen · 147 lines · 2,814 tokens per session scan A ecfdd2d890c3

Subscribe to this mod's changes

textrawl CLAUDE.md is an instructions file published in the GitHub repository jeffgreendesign/textrawl (5 stars, last pushed 1mo ago), licensed MIT. It adds 2,814 tokens to every session, about $0.0141 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.