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 hamzabellouch/agent-skills --skill datalineage-summarygit clone --depth 1 https://github.com/hamzabellouch/agent-skillsWrote 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/hamzabellouch/agent-skills/datalineage-summary)<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/datalineage-summary"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/datalineage-summary/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/hamzabellouch/agent-skills/datalineage-summary"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/datalineage-summary.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 | $0.00092 | $0.01541 |
| Opus 5 | $0.00046 | $0.00771 |
| Sonnet 5 | $0.00018 | $0.00308 |
| Haiku 4.5 | $0.00009 | $0.00154 |
Grade A, and why
datalineage-summary 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 9d 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.
This is a copy
100% identical to datalineage-summary — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Lineage Summary
This skill guides the agent in investigating and summarizing the Data Lineage graph for a specific focal asset (Table-Level Lineage) or specific fields (Column-Level Lineage). It provides an intuitive left-to-right walkthrough of how data enters and leaves the asset, abstracting away complex node and link details into plain English.
Prerequisites
This skill relies on the Google Cloud Data Lineage (Knowledge Catalog) MCP
Server for graph traversal. Ensure you can run search_lineage queries in
both upstream and downstream directions. For detailed connection configurations
and tool schemas, refer to MCP Usage.
Workflow Logic
1. Get Lineage
Fetch the lineage graph in both directions from the focal point (both upstream
and downstream) by making two separate calls to the MCP tool: one with
"direction": "UPSTREAM" and another with "direction": "DOWNSTREAM".
-
Location Strategy: You MUST use the
read_urltool to fetch the comprehensive list of locations dynamically from the provided Knowledge Catalog Locations link. To ensure cross-regional lineage is not missed, always verify the current list of GCP regions using this link before populating thelocationsarray. You MUST populate thelocationsarray with all supported physical regions fetched from this link. You may optionally additionally determine the asset's specific active region (usingbq showorgcloud storage ls). -
Search Parameters: Use
maxDepth = 10,maxResults = 5000andmaxProcessPerLink = 10as robust defaults when callingsearch_lineage. For example, a DOWNSTREAM call should be formatted like this (expanding thelocationsarray as needed):{ "parent": "projects/project_id/locations/us", "locations": [ "us", "us-central1", "us-east1", "us-west1", "europe-west1", "asia-northeast1" ], "rootCriteria": { "entities": { "entities": [ { "fullyQualifiedName": "bigquery:project.dataset.table" } ] } }, "direction": "DOWNSTREAM", "limits": { "maxDepth": 10, "maxResults": 5000, "maxProcessPerLink": 10 } }
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.
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.
- 9d ago First seen · 157 lines · 92 tokens per session scan A f8a8bcb0d3b9
datalineage-summary is a skill published in the GitHub repository hamzabellouch/agent-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 92 tokens to every session and 1,541 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to datalineage-summary, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
performance-optimization
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high…
debugging-and-error-recovery
Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root cause rather than…
bug-fix-protocol
8-step disciplined bug-fix protocol that treats every production bug as two failures — the code defect itself and the testing system that allowed it through. Use when fixing a production bug, investigating a regression, writing a post-mortem, or auditing a missed defect. Triggers on "fix this bug", "production bug"…
sdlc-bug-report
Workflow for analyzing bug reports, tracing root causes, and generating structured bug-fix implementation plans with rollback strategies.
distributed-tracing
Implement distributed tracing with OpenTelemetry, Tempo/Jaeger — instrumentation, sampling, and trace-to-log correlation. Use when the user asks about distributed tracing, OpenTelemetry setup, span instrumentation, trace propagation, or connecting traces to logs and metrics.