huginnDB: Instructions file for Claude Code

CLAUDE.md

huginnDB CLAUDE.md is an instructions file for Claude Code from Alexfp28/huginnDB. It costs 5,892 tokens per session, scanned A, original, MIT.

Project-specific instructions for HuginnDB, a desktop database manager built with Rust, React, and TypeScript. It explains the project’s identity, supported databases, coding conventions, collaboration rules, and known issues.

In plain words
What is it for?
Use it when working on HuginnDB code, documentation, commits, changelog entries, security matters, or communication with its maintainer.
Why use it?
It gives a coding agent the context needed to make changes that fit this particular repository instead of treating it like a generic project.

Instructions file for Claude Code

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

This is Alexfp28/huginnDB's own configuration. It tells Claude Code how to work on huginnDB 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 huginnDB configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Alexfp28/huginnDB. 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/Alexfp28/huginnDB/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Alexfp28/huginnDB

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 huginnDB CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alexfp28/huginndb/claude-md/github.svg)](https://agentmods.dev/instructions/alexfp28/huginndb/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alexfp28/huginndb/claude-md"><img src="https://agentmods.dev/badge/instructions/alexfp28/huginndb/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for huginnDB CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/alexfp28/huginndb/claude-md"><img src="https://agentmods.dev/badge/instructions/alexfp28/huginndb/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 5,892 This file is loaded in full into every session.
When invoked 5,892 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 $0.05892 $0.05892
Opus 5.5 $0.02357 $0.02357
Sonnet 5.5 $0.01178 $0.01178
Haiku 4.5 $0.00589 $0.00589

Measured 1mo ago against content hash 1ba69e6ddd5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

huginnDB 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -L -o sample-data/chinook.db `
CLAUDE.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project context for Claude Code sessions on this repo. Skim this first; reach for README.md / CONTRIBUTING.md / SECURITY.md for the public-facing detail.

Identity

  • HuginnDB — desktop database manager, Tauri 2 (Rust backend) + React + TypeScript frontend.
  • Targets PostgreSQL, MySQL, SQLite, MongoDB, and Microsoft SQL Server. Inspired by HeidiSQL but minimal-UI / keyboard-first / Monaco-everywhere.
  • Public repo: https://github.com/Alexfp28/huginnDB.
  • License: MIT. Status: 1.29.x (stable; SemVer applies). MongoDB support landed in 1.1.0; the headless MCP connector (huginndb-mcp) landed across the 1.5–1.9 line (per-connection write policy in 1.9.0); HuginnDB Pulse (live server health/performance monitoring, MySQL + MongoDB) landed in 1.20.0; the AI panel (local-first, read-only, off by default — Settings → AI, assisted actions and agent mode) landed in 1.22.0. Since 1.23.0 every dialog declares one of three anatomies (prompt/panel/workbench) through DialogContent, and window.confirm is retired in favour of the in-app ConfirmHost — do not reintroduce either a hand-written header rail or a native prompt. Since 1.24.0 a database's own actions live on a database node (DatabaseNodeMenu, rendered by both explorers) rather than on the connection, and a shared origin is consumed by slice (tab_state::OriginScope — connections / environments / JSON Schemas, the one per-resource flag that defaults to on; see gotcha #83). Since 1.25.0 the workspace's current connection is derived from the focused tab by src/stores/session/focusFollowsTab.ts — do not add another setSelectedConnectionId call site to approximate it. Since 1.26.0 a VS Code colour theme can be imported (.vsix or a bare *-color-theme.json) or browsed and installed straight from Open VSX (Settings → Appearance's Extensions panel) — the registry URL is read from ThemePrefs inside the backend, never named by the frontend, the same addressing rule the AI panel already followed (see gotchas #87–#88). Since 1.27.0 the timeout on the reads the app issues on its own behalf (listing databases/tables, describing a relation, the liveness ping) is the user's — ConnectionPrefs::operation_timeout_secs globally, overridden by ConnectionProfile::operation_timeout_secs, resolved only through db::pool::operation_timeout — not a constant; a query the user runs stays unbounded. Since 1.28.0 the grid's server-side filter, projection, sort, collation and index hint are edited in one place, the inline query panel (src/components/grid/QueryPanel.tsx) — the advanced-filter dialog is gone, and its Result line and Explain are built by the same backend code the browse runs, so they cannot describe a different statement from the one that executes; do not bring back a second surface that edits the active filters. Since 1.29.0 a managed policy (crate::policy, docs/POLICY.md) can bound both people and their AI: the AI at the one bridge::exec::execute choke point (gotcha #94), people in each #[tauri::command] wrapper — never in the _inner core, which bridge::exec shares — with guard::HUMAN_POLICY classifying every registered command and a test failing on one that is unclassified or never calls the guard (gotcha #95). A new command that touches a database must state what the policy asks of it; the interface's locks are advisory and the backend refuses regardless (gotcha #96).

Read the full file on GitHub · 191 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. 1mo ago Changed · +1 lines · +445 tokens per session 1ba69e6ddd5d
  2. 1mo ago Changed · +183 tokens per session 1b244d3cc57c
  3. 1mo ago Changed · +9 lines · +690 tokens per session 106510923f6f
  4. 1mo ago Changed · +122 tokens per session 6d1060121a92
  5. 1mo ago Changed · +66 tokens per session 2cf708338aa5
  6. 1mo ago Changed · +455 tokens per session a2aadc719ad5
  7. 1mo ago Changed · +10 lines · +244 tokens per session 95f2daf8b5db
  8. 2mo ago Changed a064647554d6
  9. 2mo ago Changed · +1 lines · +98 tokens per session 6570c66c7b78
  10. 2mo ago First seen · 170 lines · 3,589 tokens per session scan A bfba70aa94ce

Subscribe to this mod's changes

huginnDB CLAUDE.md is an instructions file published in the GitHub repository Alexfp28/huginnDB (2 stars, last pushed 1mo ago), licensed MIT. It adds 5,892 tokens to every session, about $0.0236 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

huginnDB CLAUDE.md compared with instructions from other repositories

huginnDB CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
huginnDB CLAUDE.mdAlexfp28/huginnDBInstructions file21mo agoMITA5,892Claude Code
vibetags com-example-config-AsyncTestConfig.instructions.mdPIsberg/vibetagsInstructions file25yesterdayMITA82GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot