What is data-integrity-review?

A data-integrity reviewer for systems that store events and build read models from them. It checks whether schemas, ownership boundaries, projections, hash chains, logs, snapshots, and replay behavior preserve the required data rules.

Use it to review event-sourced or projection-based storage, synchronization, audit trails, snapshots, and replay consistency. It supports both active phase or job reviews and checks after the planned work is complete.

It helps detect cases where syncing, saving, rebuilding, or replaying data produces incorrect results or mixes information between owners. Reviews are tied to documented specifications and invariants rather than coding style.

data-integrity-review — Skill by tamnguyendinh/Anvien

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.

Any agent

npx skills add tamnguyendinh/Anvien --skill data-integrity

Clone the repo

git clone --depth 1 https://github.com/tamnguyendinh/Anvien

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tamnguyendinh/anvien/data-integrity/github.svg)](https://agentmods.dev/skills/tamnguyendinh/anvien/data-integrity)

Your own site

<a href="https://agentmods.dev/skills/tamnguyendinh/anvien/data-integrity"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/data-integrity/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tamnguyendinh/anvien/data-integrity"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/data-integrity.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,510 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. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 5
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00042	$0.08510
Opus 5.5	$0.00017	$0.03404
Sonnet 5.5	$0.00008	$0.01702
Haiku 4.5	$0.00004	$0.00851

Measured 1mo ago against content hash 96aba1eeefe7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

data-integrity-review 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 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.

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.

internal/aicontext/skills/Data-Integrity/SKILL.md · 745 lines

How it starts

The opening of the file, as written. The whole thing — 745 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a senior data integrity specialist for event-sourced and projection-based systems.

Compact-Safe Memory

After any compact or long gap, reload this file plus AGENTS.md.
Use the exact DB, sync, audit, and architecture SPEC family for the scope.
Re-anchor every verdict to invariants, not coding style.

Review Flow

Determine whether the backlog still contains any unfinished phase/job.
Select the correct mode from that backlog state.
Run one autonomous integrity sweep for the selected mode only.
Report every live integrity issue found inside that mode's review surface.

Mode Dispatch

Mode 1 - Phase/Job Data Review . This is the default mode. . Use it when at least one phase/job in Docs/execution/* still lacks both checks (Coder, Supervisor). . The review surface is the full data-integrity surface of the active phase/job. . Anchor to the active phase/job and its exact Docs/SPEC/* family. . Do not narrow the review to one bug, one diff, or one changed file.
Mode 2 - Post-Completion Data Review . Use this only when no phase/job remains in the backlog review path AND reports\\Data-Integrity\\DATA_INTEGRITY_LIFECYCLE_PLAN.md either does not exist or does not have usable content. . The review surface is the full current-head / current-worktree data-integrity surface. . When phase/job backlog is exhausted, phase/job documents are historical context only, not the primary review anchor. . Bug hunts, follow-ups, reject/resubmit work, and current worktree may define the starting anchor, but they must not narrow the integrity sweep to one reported defect only. . Anchor to the exact Docs/SPEC/* family and the current schema/repository/service/projector/snapshot/runtime paths on the current head. . In this mode, old phase/job order must not be pulled back in as review context.
Mode 3 - Post-Completion Data Review with Lifecycle Plan . Use this only when no phase/job remains in the backlog review path AND reports\\Data-Integrity\\DATA_INTEGRITY_LIFECYCLE_PLAN.md exists and has usable content. . The review surface is the current lifecycle-plan cluster on the current head / current worktree. . When phase/job backlog is exhausted, phase/job documents are historical context only, not the primary review anchor. . The lifecycle plan may define the continuous review scope across multiple Data-Integrity runs, but each current run covers one cluster only. . Anchor to the exact Docs/SPEC/* family and the current schema/repository/service/projector/snapshot/runtime paths for the current cluster on the current head. . In this mode, old phase/job order must not be pulled back in as review context.
Explicit scope does NOT automatically force Mode 2 or Mode 3 while phase/job backlog is still open.
Check phase/job backlog first, then dispatch mode.
After mode is chosen, run only that mode's prompt. Do not mix in the other modes' load order or workflow.

Read the full file on GitHub · 745 lines

Files

What ships with it

23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago First seen · 745 lines · 42 tokens per session scan A 96aba1eeefe7

Subscribe to this mod's changes

data-integrity-review is a skill published in the GitHub repository tamnguyendinh/Anvien (12 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 8,510 once invoked, about $0.0002 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 2026-08-31.

Code review Databases ai-agents code-intelligence-mcp dead-code-detection developer-tools graph-database graph-visualization

memgraph-storage-reviewer

Review code changes in Memgraph's storage layer, including MVCC, concurrency patterns, WAL, recovery, DDL operations, index/constraint management, delta chains, and skip list operations. Invoke for pull requests or changes to src/storage/v2/.

memgraph/memgraph · 56 tokens

triage-contributor-pr

Triage open pull requests from external contributors to prisma/orm and produce a per-PR verdict with evidence. Use when a maintainer asks to triage, evaluate, assess, or review the queue of incoming contributor PRs, to decide whether a fork PR is safe to run CI on, to check whether a PR is in scope for its version…

prisma/orm · 131 tokens

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

data-integrity-review