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 skills add Marc-Dvci/praxis-datahub --skill datahub-verified-remediationgit clone --depth 1 https://github.com/Marc-Dvci/praxis-datahubWrote 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/marc-dvci/praxis-datahub/datahub-verified-remediation)<a href="https://agentmods.dev/skills/marc-dvci/praxis-datahub/datahub-verified-remediation"><img src="https://agentmods.dev/badge/skills/marc-dvci/praxis-datahub/datahub-verified-remediation/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.
<a href="https://agentmods.dev/skills/marc-dvci/praxis-datahub/datahub-verified-remediation"><img src="https://agentmods.dev/badge/skills/marc-dvci/praxis-datahub/datahub-verified-remediation.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00140 | $0.02883 |
| Opus 5 | $0.00070 | $0.01442 |
| Sonnet 5 | $0.00028 | $0.00577 |
| Haiku 4.5 | $0.00014 | $0.00288 |
Grade A, and why
datahub-verified-remediation 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 12d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DataHub Verified Remediation
You are an expert data reliability engineer. Your role is to take one schema-drift incident from "something changed upstream" to a proof-carrying change set a data team would actually merge — and to refuse to hand over anything you cannot evidence.
The rule that governs this whole skill: entity lineage tells you what might be affected; only a column-level field path proves this specific field is still consumed. Never propose a code change on entity lineage alone.
Multi-Agent Compatibility
This skill is designed to work across multiple coding agents (Claude Code, Cursor, Codex, Copilot, Gemini CLI, Windsurf, and others).
What works everywhere:
- The full evidence → generate → verify → human-gate workflow
- DataHub reads via MCP tools or the DataHub CLI
- Remediation via the Praxis MCP server or its CLI
Claude Code-specific features (other agents can safely ignore these):
allowed-toolsin the YAML frontmatter above
Reference file paths: Skill-specific references are in references/ and templates
in templates/; both ship with this skill and resolve wherever it is installed. Paths
under ../shared-references/ refer to the shared library of the upstream
datahub-skills repository and resolve only once this skill is installed there — this
skill never requires them, so nothing below breaks without them.
Not This Skill
| If the user wants to... | Use this instead |
|---|---|
| Trace dependencies or map a pipeline, with no code change | /datahub-lineage |
| Search for entities, or answer "who owns X?" | /datahub-search |
| Add or update descriptions, tags, owners | /datahub-enrich |
| Create assertions, run quality checks, manage incidents | /datahub-quality |
Key boundary: Lineage explains impact. This skill repairs it, and gates the
repair on verification and a named human. If the user only wants to understand the
blast radius, hand off to /datahub-lineage and stop.
What ships with it
4 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.
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.
- 12d ago First seen · 279 lines · 140 tokens per session scan A 36df01ebe01c
datahub-verified-remediation is a skill published in the GitHub repository Marc-Dvci/praxis-datahub (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 140 tokens to every session and 2,883 once invoked, about $0.0007 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
refactoring-dbt-models
Safely refactors dbt models with downstream impact analysis. Use when restructuring dbt models for: (1) Task mentions "refactor", "restructure", "extract", "split", "break into", or "reorganize" (2) Extracting CTEs to intermediate models or creating macros (3) Modifying model logic that has downstream consumers (4)…
debugging-dbt-errors
Debugs and fixes dbt errors systematically. Use when working with dbt errors for: (1) Task mentions "fix", "error", "broken", "failing", "debug", "wrong", or "not working" (2) Compilation Error, Database Error, or test failures occur (3) Model produces incorrect output or unexpected results (4) Need to troubleshoot…
altimate-code
Delegates dbt and warehouse work to altimate-code, a specialized CLI agent with 100+ purpose-built data tools. USE THIS SKILL FIRST whenever the task mentions or implies: warehouse access (Snowflake, BigQuery, Redshift, Databricks, Postgres, MySQL, DuckDB), column-level lineage, downstream-impact analysis, dbt builds…
documenting-dbt-models
Documents dbt models and columns in schema.yml. Use when working with dbt documentation for: (1) Adding model descriptions or column definitions to schema.yml (2) Task mentions "document", "describe", "description", "dbt docs", or "schema.yml" (3) Explaining business context, grain, meaning of data, or business rules…
testing-dbt-models
Adds schema tests and data quality validation to dbt models. Use when working with dbt tests for: (1) Adding or modifying tests in schema.yml files (2) Task mentions "test", "validate", "data quality", "unique", "notnull", or "acceptedvalues" (3) Ensuring data integrity - primary keys, foreign keys, relationships (4)…
dbt-agent-readiness
Audit a dbt project for agent-readiness: what would an AI agent get wrong if you pointed it at this data today? Produces a prioritized report organized by failure modes (wrong numbers, wrong table, wrong column, can't join, query fails). Scales via two-pass architecture with parallel subagents. Each subagent reads its…