ai-engineering-fluency: Skill for Claude Code

.claude/skills/validate-app-db-schema/SKILL.md

validate-app-db-schema is a skill for Claude Code from rajbos/ai-engineering-fluency. It costs 68 tokens per session (686 once invoked), scanned A, original, MIT.

A database-schema check for the local Copilot application database used to build parent-and-child workspace relationships. A schema is the set of tables and columns in a database; the check also runs a real query against current data.

In plain words
What is it for?
Use it after database-related changes or on a schedule to detect missing tables, columns, or unreadable relationship data.
Why use it?
The database is private and can change when the application updates, which may silently break workspace hierarchy data.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is rajbos/ai-engineering-fluency's own configuration. It tells Claude Code how to work on ai-engineering-fluency 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 ai-engineering-fluency configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .github/skills/validate-app-db-schema/validate-schema.js.

Reuse

Borrowing it

Nothing to install: this file belongs to rajbos/ai-engineering-fluency. 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/rajbos/ai-engineering-fluency/main/.claude/skills/validate-app-db-schema/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rajbos/ai-engineering-fluency

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 validate-app-db-schema

README.md
[![agentmods](https://agentmods.dev/badge/skills/rajbos/ai-engineering-fluency/validate-app-db-schema/github.svg)](https://agentmods.dev/skills/rajbos/ai-engineering-fluency/validate-app-db-schema)
Your own site
<a href="https://agentmods.dev/skills/rajbos/ai-engineering-fluency/validate-app-db-schema"><img src="https://agentmods.dev/badge/skills/rajbos/ai-engineering-fluency/validate-app-db-schema/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 validate-app-db-schema

Your own site · 80×15
<a href="https://agentmods.dev/skills/rajbos/ai-engineering-fluency/validate-app-db-schema"><img src="https://agentmods.dev/badge/skills/rajbos/ai-engineering-fluency/validate-app-db-schema.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 686 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00068 $0.00686
Opus 5.5 $0.00027 $0.00274
Sonnet 5.5 $0.00014 $0.00137
Haiku 4.5 $0.00007 $0.00069

Measured yesterday against content hash 57db660b4ed8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

validate-app-db-schema 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.

.claude/skills/validate-app-db-schema/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate App DB Schema Skill

Validates that the Copilot app's ~/.copilot/data.db still exposes the tables and columns that the extension's session hierarchy feature depends on.

Background

The session hierarchy feature reads parent/child workspace relationships from data.db — a private Copilot app database that is not part of any public API. Its schema can change without notice when the app is updated.

This skill:

  1. Checks that the required tables and columns exist
  2. Runs an actual data query (today's parent/child links) to confirm reads work end-to-end
  3. Reports a clear PASS / FAIL with details so CI or a periodic workflow can surface regressions early

What We Depend On

Table Required columns
workspace_parent_links child_workspace_id, parent_workspace_id, creator_session_id, created_at
workspaces id, session_id, name, updated_at
sessions id, title, created_at, updated_at

The join that the extension uses (simplified):

SELECT cw.session_id, cw.name, pw.session_id, pw.name
FROM workspace_parent_links l
JOIN workspaces cw ON cw.id = l.child_workspace_id
JOIN workspaces pw ON pw.id = l.parent_workspace_id
WHERE cw.session_id IN (...)
   OR pw.session_id IN (...)

Usage

# Basic validation — exits 0 on pass, 1 on fail
node .github/skills/validate-app-db-schema/validate-schema.js

# Output as JSON (for automated processing)
node .github/skills/validate-app-db-schema/validate-schema.js --json

# Show help
node .github/skills/validate-app-db-schema/validate-schema.js --help

Integration

Add to a periodic GitHub Actions workflow or run manually after a Copilot app update. Example:

- name: Validate data.db schema
  run: node .github/skills/validate-app-db-schema/validate-schema.js --json

Implementation Details

The script reads data.db using sql.js (pure WASM — no native SQLite binaries required). It performs three checks:

  1. File exists: ~/.copilot/data.db is present
  2. Schema check: PRAGMA table_info(table_name) confirms all required columns exist
  3. Live query: Runs the actual JOIN query used by the extension against the last 24h of data

Read the full file on GitHub · 73 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 · 73 lines · 68 tokens per session scan A 57db660b4ed8

Subscribe to this mod's changes

validate-app-db-schema is a skill published in the GitHub repository rajbos/ai-engineering-fluency (119 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 686 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-26.

Related

Other skills, from other repositories

review-prs

Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…

googleapis/mcp-toolbox · 162 tokens

azure-cosmos-db-py

Build Azure Cosmos DB NoSQL services with Python/FastAPI following production-grade patterns. Use when implementing database client setup with dual auth (DefaultAzureCredential + emulator), service layer classes with CRUD operations, partition key strategies, parameterized queries, or TDD patterns for Cosmos. Triggers…

microsoft/skills · 96 tokens

Drizzle ORM Testing

Testing patterns for Drizzle ORM covering migration testing, query builder testing, transaction testing, and database integration testing with PostgreSQL, SQLite, and MySQL.

PramodDutta/qaskills · 36 tokens

finance-weekly-outlook

Generate a source-backed weekly financial trading outlook from daily-finance, finance-core-analysis, and finance-explosive-article outputs plus fresh authoritative market data. Use when the user asks for future-one-week market outlook, weekly bullish/bearish sectors, stock picks, China A-share and US stock coverage…

digoal/blog · 122 tokens

postgres-commit-history-article

A workflow for comparing PostgreSQL source-code changes between two Git commits and, when useful, writing a Chinese Markdown article about them. PostgreSQL is a database system, and a commit is a saved change in a Git repository.

digoal/blog · 127 tokens

product-feature-tech-implement

A development workflow that coordinates separate developer, reviewer, and tester roles to implement a feature design and verify it. TDD, or test-driven development, means using tests as part of guiding the implementation.

digoal/blog · 190 tokens