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.
npx agentmods add instructions/jeffgreendesign/textrawl/claude-mdgit clone --depth 1 https://github.com/jeffgreendesign/textrawlWrote 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.
[](https://agentmods.dev/instructions/jeffgreendesign/textrawl/claude-md)<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>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 | $0.02814 | $0.02814 |
| Opus 5 | $0.01407 | $0.01407 |
| Sonnet 5 | $0.00563 | $0.00563 |
| Haiku 4.5 | $0.00281 | $0.00281 |
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.
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.
preinstallrunsonly-allow pnpm— npm/yarn will be rejected. - ESM project (
"type": "module"). All imports MUST use explicit.jsextension even for.tsfiles. - Package manager: pnpm 9.15+. Workspace includes
website/,desktop/, anddashboard/.
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).
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.
- 3d ago First seen · 147 lines · 2,814 tokens per session scan A ecfdd2d890c3
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.
Other instructions, from other repositories
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
core copilot-instructions.md
Instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
telegramify-markdown AGENTS.md
Instructions for sudoskys/telegramify-markdown, covering telegramify-markdown agent guide, task routing, quick commands, project rules and architecture map.
codemark GEMINI.md
Instructions for DanielCardonaRojas/codemark, covering development workflow and debugging with the tui logging system.
easy-notion-mcp CLAUDE.md
Instructions for Grey-Iris/easy-notion-mcp, covering easy-notion-mcp, open source context, .meta/ publication policy (hybrid, 2026-07-02), standing priorities and commands.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).