pointless: Instructions file for Claude Code

CLAUDE.md

pointless CLAUDE.md is an instructions file for Claude Code from moorjani-ajay/pointless. It costs 1,189 tokens per session, scanned A, original, MIT.

Repository instructions for Pointless, a self-hosted presentation tool that agents control through MCP and that publishes interactive HTML presentations at share links. It is a pnpm monorepo, meaning one repository contains several related packages.

In plain words
What is it for?
Developing Pointless across its server, web app, shared package, database, and end-to-end tests.
Why use it?
They explain how the project is structured, run, tested, formatted, linted, and type-checked.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is moorjani-ajay/pointless's own configuration. It tells Claude Code how to work on pointless itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pointless configures →

Reuse

Borrowing it

Nothing to install: this file belongs to moorjani-ajay/pointless. 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/moorjani-ajay/pointless/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/moorjani-ajay/pointless

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.

agentmods badge for pointless CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/moorjani-ajay/pointless/claude-md.svg)](https://agentmods.dev/instructions/moorjani-ajay/pointless/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/moorjani-ajay/pointless/claude-md"><img src="https://agentmods.dev/badge/instructions/moorjani-ajay/pointless/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,189 This file is loaded in full into every session.
When invoked 1,189 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01189 $0.01189
Opus 5 $0.00594 $0.00594
Sonnet 5 $0.00238 $0.00238
Haiku 4.5 $0.00119 $0.00119

Measured 7d ago against content hash 67572abb4a1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pointless 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 7d 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 · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 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.

What this is

Pointless is a self-hosted presentation tool driven over MCP: an LLM client connects to /mcp and authors presentations as complete, self-contained interactive HTML documents, published at unguessable share links (/d/<token>). pnpm monorepo, Node 24+, TypeScript ESM throughout.

Commands

pnpm install
pnpm --filter @pointless/shared build   # required once before dev/typecheck (server & web import built types)
docker compose up -d db                 # local Postgres on :5432
export DATABASE_URL=postgres://pointless:pointless@localhost:5432/pointless
pnpm dev                                # server on :3000 (tsx watch)
pnpm dev:web                            # Vite on :5173, proxies /api /raw /mcp to :3000

Checks (all must pass for a PR; pnpm run check bundles the first four):

  • pnpm run format:check / pnpm run format — Prettier
  • pnpm run lint — ESLint
  • pnpm run typechecktsc --noEmit per package
  • pnpm test — Vitest; requires Docker (testcontainers starts a throwaway Postgres)
  • pnpm e2e — Playwright; builds all packages and boots the real server; needs Postgres on :5432 (or DATABASE_URL)

Single test file: pnpm vitest run server/test/mcp.test.ts (add -t 'name' for one test). Server test files run serially (fileParallelism: false) because they share one database.

Commits/PR titles must follow Conventional Commits — enforced by Husky commitlint locally and on the PR title in CI (PRs are squash-merged, so the title becomes the commit subject). release-please derives versions/CHANGELOG from these.

Architecture

Three workspace packages: shared/ (types only, must be built first), server/ (@pointless/server), web/ (@pointless/web, React SPA served as static files by the server in production).

Server (server/src/)

  • index.ts is only init() + createApp().listen(); everything testable lives in app.ts (createApp() builds the Express app without binding a port — tests drive it with Supertest).
  • mcp.tsbuildMcpServer(baseUrl) registers the six tools (get_design_guide, create_presentation, set_html, get_presentation, list_presentations, publish). The /mcp endpoint is stateless: a fresh McpServer + StreamableHTTPServerTransport per POST, no sessions. designguide.ts holds the authoring contract returned by get_design_guide.
  • db.ts — single decks table in Postgres; schema is created by init() on startup (no migration framework). The pg pool opens lazily on first query so DATABASE_URL can be set late (tests rely on this). publishPresentation passwordHash semantics: undefined = unchanged, null = remove, string = set.
  • auth.ts — scrypt password hashing, constant-time comparison, and viewKey(hash, token): the proof-of-unlock a client earns via POST /api/shared/:token/unlock and then passes as ?k= to view a protected deck.

Read the full file on GitHub · 58 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. 7d ago First seen · 58 lines · 1,189 tokens per session scan A 67572abb4a1f

Subscribe to this mod's changes

pointless CLAUDE.md is an instructions file published in the GitHub repository moorjani-ajay/pointless (0 stars, last pushed 15d ago), licensed MIT. It adds 1,189 tokens to every session, about $0.0059 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.

Related

Other instructions, from other repositories

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens