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.
npx agentmods add skills/jhostalek/dotclaude/audit-data-integritynpx skills add JHostalek/dotclaude --skill audit-data-integritygit clone --depth 1 https://github.com/JHostalek/dotclaudeWrote 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.
[](https://agentmods.dev/skills/jhostalek/dotclaude/audit-data-integrity)<a href="https://agentmods.dev/skills/jhostalek/dotclaude/audit-data-integrity"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/audit-data-integrity.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00094 | $0.03064 |
| Opus 5 | $0.00047 | $0.01532 |
| Sonnet 5 | $0.00019 | $0.00613 |
| Haiku 4.5 | $0.00009 | $0.00306 |
Grade A, and why
audit-data-integrity scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
!cat "${CLAUDE_SKILL_DIR}/../shared/audit-workflow.md"
Run as the data-integrity dimension. Determine whether data retains its intended identity, meaning, relationships, completeness, ordering, precision, provenance, and lifecycle guarantees across every authoritative and derived representation. Include violations that appear only through component interaction, concurrency, failure, deployment, recovery, or historical data.
Work top-down
- Reconstruct the data model from product behavior, domain rules, schemas, migrations, storage configuration, APIs/events, code, tests, operational procedures, and deployed topology. Identify entities, identities, relationships, authoritative and derived stores, owners, trust boundaries, writers/readers, state machines, conservation laws, validity windows, and legal deletion or retention states.
- State the integrity invariants and their consequences before inspecting implementation details. Cover what must be atomic, unique, referentially valid, ordered, monotonic, balanced, durable, reproducible, traceable, recoverable, or consistently deleted; also state permitted staleness, partiality, and conflict.
- Map each material datum through its lifecycle: creation or ingestion, validation, normalization, transformation, persistence, transaction commit, publication, replication, indexing/caching, reads, updates, correction, migration, archival, restore, deletion, and reconciliation. Include alternate, batch, administrative, retry, failover, rollback, mixed-version, and manual-repair paths.
- Inspect architecture-wide invariants and dangerous compositions first. Then trace exact write/read paths and failure windows across components. Apply every applicable baseline area and derive domain-specific probes.
Never infer integrity from an ORM, database engine, transaction helper, framework default, schema, constraint, type, generated client, helper abstraction, naming convention, common pattern, or test presence. Verify the exact schema and constraint state, isolation and durability settings, call path, ordering, failure timing, deployment topology, historical shapes, and recovery behavior. A valid local write can still create globally invalid data.
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.
- 5d ago First seen · 151 lines · 94 tokens per session scan A f88e89ad9b7e
audit-data-integrity is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed today), licensed CC0-1.0. It adds 94 tokens to every session and 3,064 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
databases
· Configure/tune/migrate PostgreSQL, MongoDB, MySQL/MariaDB, MSSQL. Triggers: 'database', 'postgres', 'mysql', 'mongodb', 'database schema', 'database migration', 'pgbouncer', 'EXPLAIN'. Not for HTTP APIs (use backend-api).
factory-db-migration
The operational discipline for running a destructive change against a production database — schema migrations, data backfills, one-shot RPCs, historical seed imports. Adjacent to factory-data-layer.md (schema design) and factory-deployment.md (where migrations execute in CI) — this skill is about the runbook around…
factory-api
API conventions for both server actions and tRPC builds. Covers the decision between them, per-mutation Zod input schemas, central router composition, pagination shape, multi-field search via Drizzle ilike + or(), mutation lifecycle hooks, conditional query enabling, stale-time defaults, error response shape and…
factory-data-layer
Database schema, ORM, and migration conventions across builds. Drizzle as default with domain-partitioned schema modules, shared timestamps helper, multi-tenancy keys with cascade delete, pgTableCreator prefixing, JSONB for flexible attributes, schema-derived type exports, polymorphic table patterns, ESLint Drizzle…
factory-db-migration-engineer
Use when planning or executing a destructive change against a production database — schema migrations with backfills, periodic data imports, one-shot RPCs, drop-constraint operations, anything that mutates prod tables and cannot be trivially undone. Sister agent to db-schema-architect (schemas) and…
factory-db-schema-architect
Use when designing or modifying database schemas, migrations, multi-tenant data models, or polymorphic table structures. Carries the factory's data-layer conventions — Drizzle with domain-partitioned schema modules, shared.ts with timestamps helper and pgTableCreator, org-keyed FKs with cascade delete, JSONB envelope…