agentmods.dev

rosetta database.instructions.md

Project instructions for the SQLite database layer, including how the database starts, which driver to use, and how documentation data is stored.

In plain words
What is it for?
Use it when changing SQLite tables, database startup, write-ahead logging, full-text search, triggers, or data definitions.
Why use it?
It prevents different parts of the project from using conflicting database settings or table assumptions.

Instructions file for GitHub Copilot

43 15d ago A scan 753 tokens original MIT
View the source file tikoci/rosetta
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/tikoci/rosetta/database
Clone the repo
git clone --depth 1 https://github.com/tikoci/rosetta

Made for: GitHub Copilot.

Per session 753 This file is loaded in full into every session.
When invoked 753 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 $0.00753 $0.00753
Opus 5 $0.00377 $0.00377
Sonnet 5 $0.00151 $0.00151
Haiku 4.5 $0.00075 $0.00075

Measured yesterday against content hash 286045ef91e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rosetta database.instructions.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 yesterday.

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.

.github/instructions/database.instructions.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Database Layer

Key Rules

  • Use bun:sqlite — never better-sqlite3 or other drivers
  • WAL mode + foreign keys enabled in initDb()
  • DB_PATH env var overrides default ros-help.db
  • Singleton pattern: one Database instance shared across modules

Tables

  • pages + pages_fts — legacy Confluence HTML pages (breadcrumb path, URL, text, code); do not assume this identity model works for the future Docusaurus extractor
  • callouts + callouts_fts — Note/Warning/Info/Tip callouts (FK → pages)
  • sections — page sections split by h1–h3 headings with anchor IDs (FK → pages)
  • page_tables + page_table_rows + page_table_cells — normalized Docusaurus pipe tables with raw Markdown, page/section provenance, and actual ragged row widths
  • properties + properties_fts — Docusaurus table/bullet properties plus historical Confluence properties (FK → pages; table-derived rows link to page_table_rows)
  • commands — command tree entries from inspect.json (FK → pages for linked dirs)
  • ros_versions — tracked RouterOS versions with channel metadata
  • command_versions — junction: command_path × ros_version (full extracted history)
  • schema_nodes + schema_node_presence — multi-arch deep-inspect schema; presence is pruned to active channel heads in release DBs
  • devices + devices_fts — MikroTik products with hardware specs (from product matrix CSV)
  • device_test_results — benchmark rows per device (ethernet/IPSec throughput)
  • changelogs + changelogs_fts — parsed per-entry changelog data (version, category, breaking flag)
  • videos + videos_fts — MikroTik YouTube video metadata
  • video_segments + video_segments_fts — chapter-level transcript segments (FK → videos.id)
  • dude_pages + dude_pages_fts — archived Dude wiki pages from Wayback/cache
  • dude_images — screenshot metadata for Dude wiki pages
  • skills + skills_fts — RouterOS agent skill guides from tikoci/routeros-skills
  • skill_references — reference documents attached to skills
  • glossary — seeded RouterOS terms and aliases
  • db_meta — release provenance and schema/update metadata

Read the full file on GitHub · 47 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. yesterday First seen · 47 lines · 753 tokens per session scan A 286045ef91e3

Subscribe to this mod's changes

rosetta database.instructions.md is an instructions file published in the GitHub repository tikoci/rosetta (43 stars, last pushed 15d ago), licensed MIT. It adds 753 tokens to every session, about $0.0038 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 2026-08-30.

DatabasesResearchWriting and docsaibunclaude-codecopilotmcpmcp-server
Related

Other instructions, from other repositories

agentconfig.org AGENTS.md

Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.

agentconfig/agentconfig.org · 2,368 tokens

relay AGENTS.md

Instructions for ImBIOS/relay, covering agents.md — relay, project overview, tech stack, architecture and support policy.

ImBIOS/relay · 1,340 tokens

agentconfig.org CLAUDE.md

Instructions for agentconfig/agentconfig.org, a project described as: Elevate your AI assistants by configuring them for any role or workflow. Explore the primitives that unlock their full potential.

agentconfig/agentconfig.org · 5 tokens

bun-mcp copilot-instructions.md

Copilot instructions for TomasHubelbauer/bun-mcp, covering github copilot instructions for the bun-mcp repository and formatting.

TomasHubelbauer/bun-mcp · 253 tokens

gini-agent AGENTS.md

AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.

Open-Curiosity/gini-agent · 3,639 tokens

DevoxxGenieIDEAPlugin GEMINI.md

Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…

devoxx/DevoxxGenieIDEAPlugin · 257 tokens