connhex-tools CLAUDE.md

connhex-tools CLAUDE.md is an instructions file for coding agents from compiuta-origin/connhex-tools. It costs 373 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for a workspace containing an SDK, an MCP server, and a command-line tool in one repository. A workspace of related packages is often called a monorepo.

In plain words
What is it for?
Use it when working on the Connhex tools workspace, including installing dependencies, running tests and checks, and starting its server or command-line tool.
Why use it?
It tells Claude Code how this particular repository is organised, tested, formatted, and run.

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/compiuta-origin/connhex-tools/claude-md
Clone the repo
git clone --depth 1 https://github.com/compiuta-origin/connhex-tools

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 connhex-tools CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/compiuta-origin/connhex-tools/claude-md.svg)](https://agentmods.dev/instructions/compiuta-origin/connhex-tools/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/compiuta-origin/connhex-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/compiuta-origin/connhex-tools/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 373 This file is loaded in full into every session.
When invoked 373 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 $0.00373 $0.00373
Opus 5 $0.00187 $0.00187
Sonnet 5 $0.00075 $0.00075
Haiku 4.5 $0.00037 $0.00037

Measured 3d ago against content hash 7bcdc5fdcc4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

connhex-tools 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 · 35 lines

What it actually says

Project

connhex-tools — the tools workspace for Connhex. Hosts the SDK, the MCP server, and the CLI as sibling packages in a single uv workspace.

Workspace layout

Three packages under packages/:

  • connhex-sdk — async Connhex API client, auth, and per-domain services + schemas. No fastmcp / no server dependencies. Importable as connhex.
  • connhex-mcp — the MCP server (fastmcp-based). Depends on connhex-sdk. Console entry point: connhex-mcp.
  • connhex-cli — Typer-based CLI scaffold. Depends on connhex-sdk.

The workspace root pyproject.toml owns dev deps (pytest, ruff, pre-commit) and the single uv.lock. Each package has its own pyproject.toml and uses uv_build.

Commands

uv sync                              # install workspace + dev deps
uv run pytest                        # run all tests (paths configured in root pyproject)
uv run pytest packages/connhex-sdk/tests/test_jsonapi.py::test_name   # single test
uv run ruff check . && uv run ruff format .
uv run pre-commit run --all-files

uv run connhex-mcp --mode local --transport stdio        # default local stdio
uv run connhex-mcp --mode local --transport streamable-http
uv run connhex-mcp --mode remote                          # requires CONNHEX_PUBLIC_URL

Python ≥ 3.11. Ruff line-length 80, target py311.

Conventions

  • Conventional Commits. Atomic where practical.
  • Tests live under each package's tests/ directory; the root pyproject lists them in testpaths.
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 · 35 lines · 373 tokens per session scan A 7bcdc5fdcc4f

Subscribe to this mod's changes

connhex-tools CLAUDE.md is an instructions file published in the GitHub repository compiuta-origin/connhex-tools (1 stars, last pushed 1mo ago), licensed MIT. It adds 373 tokens to every session, about $0.0019 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.