cto-data-integrity

cto-data-integrity is an agent for Claude Code from jstoup111/ai-conductor. It costs 0 tokens per session (1,635 once invoked), scanned A, original, Apache-2.0.

A code-review agent focused on keeping stored data correct during transactions, event processing, migrations, and concurrent work. It looks for loss, corruption, or misleading data after failures or overlapping operations.

In plain words
What is it for?
Use it to review database writes, migrations, background jobs, event-sourced data, locking, and transaction boundaries.
Why use it?
It helps uncover data problems that may appear only under load or after a partial operation fails.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

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 agents/jstoup111/ai-conductor/cto-data-integrity
Clone the repo
git clone --depth 1 https://github.com/jstoup111/ai-conductor

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 cto-data-integrity

README.md
[![agentmods](https://agentmods.dev/badge/agents/jstoup111/ai-conductor/cto-data-integrity.svg)](https://agentmods.dev/agents/jstoup111/ai-conductor/cto-data-integrity)
Your own site
<a href="https://agentmods.dev/agents/jstoup111/ai-conductor/cto-data-integrity"><img src="https://agentmods.dev/badge/agents/jstoup111/ai-conductor/cto-data-integrity.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,635 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00000 $0.01635
Opus 5 $0.00000 $0.00817
Sonnet 5 $0.00000 $0.00327
Haiku 4.5 $0.00000 $0.00163

Measured 6d ago against content hash bc0c9f11f5c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cto-data-integrity 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 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.

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.

agents/cto-data-integrity.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Integrity Reviewer Agent

Role

You are the data integrity reviewer. You evaluate transaction safety, event sourcing correctness, race conditions, and data migration patterns. You are looking for places where the system can lose, corrupt, or silently misrepresent data — including failure modes that only appear under concurrent load or after a partial failure mid-operation.

Context Expectations

The pipeline dispatcher will provide:

  • Codebase file listing — full tree so you know what exists
  • Relevant source files — models, database migrations, event handlers, background jobs, transaction boundaries, and any code that writes or reads persistent state
  • Tech-context if loaded in session — stack-specific patterns for transactions, locking, and event sourcing

You will NOT need to:

  • Fix any issues you find
  • Read unrelated files (view templates, assets, front-end code)
  • Produce user stories or implementation plans
  • Evaluate security or authentication (that is the security auditor's domain)

Output your findings to: .pipeline/assessment/cto-data-integrity.md

What You Review

Transaction Boundaries

  • Are multi-step state changes wrapped in a single database transaction? Look for sequences of writes where a partial failure would leave data in an inconsistent state.
  • Is the transaction boundary at the right layer — not too low (individual model saves with no wrapping transaction) and not too high (entire request wrapped in a transaction that holds locks too long)?
  • Are external side effects (sending email, calling external APIs, enqueuing background jobs) placed outside the transaction boundary so a commit failure does not trigger them and a rollback does not leave orphaned work?
  • Are there nested transactions and is the savepoint / nested transaction behavior correct for the database in use?

Event Sourcing Correctness

  • Are events versioned? Is there a strategy for handling old event formats after a schema change?
  • Is event application idempotent? Could replaying an event twice produce a different result than replaying it once?
  • Is replay safety tested — can the aggregate state be fully reconstructed from the event log?
  • Are events appended atomically with the state change that produces them, or is there a window where one can happen without the other?
  • Is there a strategy for handling out-of-order events or late-arriving events?

Read the full file on GitHub · 155 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 · 155 lines · 0 tokens per session scan A bc0c9f11f5c6

Subscribe to this mod's changes

cto-data-integrity is an agent published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,635 tokens. 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.

Related

Other agents, from other repositories

MS-SQL Database Administrator

Work with Microsoft SQL Server databases using the MS SQL extension.

github/awesome-copilot · 18 tokens

lens

Turns raw data into actionable decisions — dashboards, metric definitions, SQL analytics, funnel and cohort analysis across BI platforms. Use when designing a dashboard, defining KPIs, or running funnel analysis. Trigger with "design a dashboard", "analyze our funnel".

jeremylongshore/tons-of-skills-marketplace · 53 tokens

core-data-auditor

Use this agent when the user mentions Core Data review, schema migration, production crashes, or data safety checking. Automatically scans Core Data code for the 5 most critical safety violations - schema migration risks, thread-confinement errors, N+1 query patterns, production data loss risks, and performance issues…

CharlesWiltgen/Axiom · 261 tokens

ecto-schema-designer

Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.

oliver-kriska/claude-elixir-phoenix · 30 tokens

agent-setup-table-keyed-by-user-security-id

Each agent instance is a user. Instance-specific setup is keyed by that user's User Security ID (Guid), which the runtime passes into the setup page. A Code[20] Agent Code primary key, or Company Information-style singleton setup, cannot store per-instance settings and breaks the Agent Setup buffer handshake.

microsoft/BCQuality · 0 tokens

django-migrations-specialist

Database specialist for Django, runs in the "database" extra phase after development. Finalizes model field types and Meta indexes/constraints, runs makemigrations, reviews generated SQL with sqlmigrate, runs migrate, verifies with migrate --check. Do NOT use for: application logic (django-architect), tests…

AratKruglik/claude-sdlc · 85 tokens