lineage

A skill for tracing where data comes from and where it flows in Collibra's technical lineage graph.

In plain words
What is it for?
It finds upstream sources and downstream users of tables, files, code, and other data entities, and can retrieve transformation SQL or scripts when requested.
Why use it?
It separates physical data flow from business catalog links and prevents using the wrong kind of identifier when following a lineage path.

Skill for Claude CodeCodex

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 skills/collibra/chip/lineage
Any agent
npx skills add collibra/chip --skill lineage
Clone the repo
git clone --depth 1 https://github.com/collibra/chip

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 860 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 $0.00026 $0.00860
Opus 5 $0.00013 $0.00430
Sonnet 5 $0.00005 $0.00172
Haiku 4.5 $0.00003 $0.00086

Measured 2d ago against content hash 2038f393acae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

lineage 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 2d 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.

pkg/skills/files/collibra/lineage/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technical lineage

Technical lineage maps the physical data flow — including unregistered assets, temporary tables, and source code — across systems. This is broader than business lineage (which only covers cataloged Collibra assets). Almost every lineage question follows the same three-stepit shape:

  1. Resolve the entity with search_lineage_entities (the entry point).
  2. Walk the graph with get_lineage_upstream or get_lineage_downstream.
  3. Selectively resolve the most relevant entities with get_lineage_entity. Do not resolve every ID — summarize from graph structure.

get_lineage_transformation returns SQL or script bodies; only call it when the user asks to see the actual transformation logic. search_lineage_transformations is a specialized search by transformation name, not a general entry point.

Hard rule: lineage IDs are not DGC UUIDs

get_lineage_upstream, get_lineage_downstream, get_lineage_entity, and get_lineage_transformation all use lineage entity IDs, which live in a separate ID space from Collibra DGC asset UUIDs. Passing a DGC UUID directly to any of these tools will fail or return the wrong entity.

The only bridge from a DGC asset to the lineage graph is:

search_lineage_entities(dgcId=<DGC UUID>)  →  lineage entity ID

Always start there when the user gives you a catalog asset.

Column-level lineage limitation

search_lineage_entities cannot reliably resolve columns:

  • nameContains does not work for columns — the lineage graph does not expose column names through that filter.
  • dgcId does not reliably resolve column UUIDs because there is no consistent mapping between catalog column UUIDs and lineage column entity IDs.

The workaround: find the parent table first, then walk into its columns from the lineage graph. See references/column-lineage-workaround.md.

Workflows

Upstream sources for an asset

  1. search_lineage_entities(nameContains="<table-name>") or (dgcId=<UUID>) → entity ID
  2. get_lineage_upstream(entityId=<id>) → source entities + transformation IDs (paginated)
  3. Summarize the graph. If the user wants details on a specific source, call get_lineage_entity for that one ID.
  4. Only call get_lineage_transformation if the user wants the SQL or script body.

Read the full file on GitHub · 82 lines

Files

What ships with it

1 file 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.

  1. 2d ago First seen · 82 lines · 26 tokens per session scan A 2038f393acae

Subscribe to this mod's changes

lineage is a skill published in the GitHub repository collibra/chip (36 stars, last pushed 4d ago), licensed Apache-2.0. It adds 26 tokens to every session and 860 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens