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 collibra/chip --skill dq-rule-workbenchgit clone --depth 1 https://github.com/collibra/chipWrote 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/collibra/chip/dq-rule-workbench)<a href="https://agentmods.dev/skills/collibra/chip/dq-rule-workbench"><img src="https://agentmods.dev/badge/skills/collibra/chip/dq-rule-workbench/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/collibra/chip/dq-rule-workbench"><img src="https://agentmods.dev/badge/skills/collibra/chip/dq-rule-workbench.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.02620 |
| Opus 5.5 | $0.00017 | $0.01048 |
| Sonnet 5.5 | $0.00008 | $0.00524 |
| Haiku 4.5 | $0.00004 | $0.00262 |
Grade A, and why
dq-rule-workbench 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.
How it starts
The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data quality rule workbench
A multi-turn flow for creating DQ rules against one or more catalog columns at scale — from templates (bulk) or plain-language intent (Text2SQL) — without the user writing SQL by hand. This skill orchestrates existing tools; it does not add new API surface.
Relationship to the other DQ skills:
collibra/dq-rules— the mechanics of a single rule on an existing job (validate → create → inspect → read results). This workbench reuses those rules and defers to that skill for the per-rule detail.- Job creation — when a column has no suitable job, this flow calls
prepare_create_data_quality_job+create_data_quality_job(see their tool descriptions).
Tools this flow orchestrates
- Target columns:
search_catalog_columns(metadata filters — description, data type, data-steward role, and relations to a business term / business rule / data element / data attribute; needs the Knowledge Graph API), plussearch_asset_keyword(domain/community/asset-type + free-text),discover_data_assets(natural-language),get_asset_details(by UUID). - Resolve DQ location / job + detect PUSHDOWN:
prepare_create_data_quality_job(resolves a catalog Table asset → connection / edge / job and reports the job type).create_data_quality_jobwhen none exists. - Duplicate detection:
find_data_quality_rules(filter byjobName+columnName). - Define rules — two paths:
- Templates:
list_data_quality_rule_templates/get_data_quality_rule_template→deploy_data_quality_rule_template(bulk). - Plain-language / AI:
generate_data_quality_rule_sql(Text2SQL) →create_data_quality_rule.
- Templates:
- Review SQL:
validate_data_quality_rule. - Read results:
get_data_quality_rule_results(per-run rule outcomes, once the job has run). - Catalog associations:
edit_asset(add_relation) to Business Rule, Data Element, Data Attribute, or a catalog Data Quality Rule asset.
Hard rules
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 Changed · +1 lines 5c6240b8f47c
- 2mo ago First seen · 179 lines · 42 tokens per session scan A 364226a3141f
dq-rule-workbench is a skill published in the GitHub repository collibra/chip (37 stars, last pushed yesterday), licensed Apache-2.0. It adds 42 tokens to every session and 2,620 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 2026-08-30.
dq-rule-workbench compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dq-rule-workbenchcollibra/chip | Skill | 37 | yesterday | Apache-2.0 | A | 42 | Claude Code, Codex |
| create-prprisma/orm | Skill | 48k | yesterday | Apache-2.0 | A | 48 | Claude Code, Codex |
| schema-explorationlangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 57 | Claude Code, Codex |
| atlas-mssqlariga/atlas | Skill | 8.8k | yesterday | Apache-2.0 | A | 163 | Claude Code |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |
| nornicdb-cypher-queriesorneryd/NornicDB | Skill | 923 | yesterday | MIT | A | 79 | Claude Code, Codex |
| volcengine-rds-postgresqlbytedance/agentkit-samples | Skill | 484 | today | Apache-2.0 | A | 63 | Claude Code, Codex |