intelaisense: Instructions file for Claude Code

CLAUDE.md

intelaisense CLAUDE.md is an instructions file for Claude Code from vonargo/intelaisense. It costs 1,198 tokens per session, scanned A, original, MIT.

A set of repository instructions for working on intelaisense, a Claude Code add-on that supplies project signals to an AI coding agent. It documents the add-on’s commands, architecture, tests, and rules that must remain unchanged.

In plain words
What is it for?
Use it when developing or maintaining intelaisense, including running its Python tests, validating its package, or enabling and disabling project signals.
Why use it?
It gives contributors a shared reference for running tests, checking the package, and changing signal settings without breaking the add-on’s structure.

Instructions file for Claude Code

Written for Claude Code: ${CLAUDE_PROJECT_DIR} variable. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is vonargo/intelaisense's own configuration. It tells Claude Code how to work on intelaisense 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 intelaisense configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to vonargo/intelaisense. 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/vonargo/intelaisense/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vonargo/intelaisense

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 intelaisense CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vonargo/intelaisense/claude-md.svg)](https://agentmods.dev/instructions/vonargo/intelaisense/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vonargo/intelaisense/claude-md"><img src="https://agentmods.dev/badge/instructions/vonargo/intelaisense/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,198 This file is loaded in full into every session.
When invoked 1,198 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01198 $0.01198
Opus 5 $0.00599 $0.00599
Sonnet 5 $0.00240 $0.00240
Haiku 4.5 $0.00120 $0.00120

Measured 6d ago against content hash df75fbaab8b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

intelaisense CLAUDE.md scanned grade A with 1 finding 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 6d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **`diagnostics` uses `subprocess.run(..., shell=True)` deliberately.** The command is a user-authored config template (same trust as the plugin); the interpolated file path is `shlex.quote`-d. Do not "harden" it to `sh
CLAUDE.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 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

intelaisense is a Claude Code plugin that gives an AI coding agent a perception layer — ambient, on-write signals (the "squiggly line" analog) pushed into the agent's context as it works. It is not an application; it is hooks + a dispatcher + pluggable signals, packaged like the containuity plugin.

Commands

Tests use pytest in an isolated venv (the system Python is externally-managed; do not pip install into it):

.venv/bin/python -m pytest tests/ -q          # full suite
.venv/bin/python -m pytest tests/test_staleness.py -v   # one file
.venv/bin/python -m pytest tests/test_dispatch.py::test_malformed_stdin_exits_zero -v  # one test

If .venv is missing: python3 -m venv .venv && .venv/bin/python -m pip install pytest.

Plugin packaging smoke check: bash scripts/validate.sh (parses the manifest + hooks.json, checks the hook entry exists).

Control the signals for a project: python3 scripts/cli.py status|enable <signal>|disable <signal> [--dir=PATH].

Architecture

The flow is: hook → dispatcher → signals → additionalContext.

  • hooks/hooks.json registers PreToolUse (Edit|Write) and PostToolUse (Read|Edit|Write), both invoking the thin shell wrapper hooks/intelaisense.sh, which execs scripts/dispatch.py.
  • scripts/dispatch.py is the single entry point. It reads the hook JSON from stdin, builds an Event, loads config, opens the StateStore, runs discover_signals(config), and for each signal calls run() only when (event_type, tool_name) is in that signal's interests(). It formats annotations under a char budget and prints {"hookSpecificOutput": {"additionalContext": ...}} only when there is text.
  • scripts/intelaisense/ is the package: types.py (Event, Annotation), state.py (StateStore), config.py (load_config + DEFAULTS), output.py (format_annotations), and signals/ (base.py + the three signal modules).
  • signals/__init__.py is a lazy registry: it maps signal name → (module, class) and imports inside discover_signals under try/except, so a missing or broken signal module is skipped, never fatal.

Read the full file on GitHub · 52 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. 6d ago First seen · 52 lines · 1,198 tokens per session scan A df75fbaab8b6

Subscribe to this mod's changes

intelaisense CLAUDE.md is an instructions file published in the GitHub repository vonargo/intelaisense (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,198 tokens to every session, about $0.0060 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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 · 5,182 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