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 andey0Saikiran/tableau-lineage --skill tableau-workbook-auditgit clone --depth 1 https://github.com/andey0Saikiran/tableau-lineageWrote 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/andey0saikiran/tableau-lineage/tableau-workbook-audit)<a href="https://agentmods.dev/skills/andey0saikiran/tableau-lineage/tableau-workbook-audit"><img src="https://agentmods.dev/badge/skills/andey0saikiran/tableau-lineage/tableau-workbook-audit/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/andey0saikiran/tableau-lineage/tableau-workbook-audit"><img src="https://agentmods.dev/badge/skills/andey0saikiran/tableau-lineage/tableau-workbook-audit.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 | $0.00073 | $0.00656 |
| Opus 5 | $0.00036 | $0.00328 |
| Sonnet 5 | $0.00015 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00066 |
Grade A, and why
tableau-workbook-audit 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 11d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing and tracing Tableau workbooks
These tools read Tableau workbooks from the local disk and return their structure. Everything runs on the user's machine; no file is uploaded.
Always start here
Run analyze_workbook first on any workbook you have not seen in this conversation. It
is cheap and tells you the shape of the file (how many calculations, parameters,
worksheets and data sources) so you can choose the right follow-up instead of guessing.
Choosing the right tool
| The user asks | Use |
|---|---|
| "what is wrong with this workbook", "what can I delete", "why is it slow" | audit_workbook |
| "what does X depend on", "what breaks if I change X" | trace_dependencies |
| "what changed between these two files" | diff_workbooks |
| "show me the calculations", "what is the formula for X" | list_calculated_fields, then get_field for one field |
| "which sheets filter on X", "what filters exist" | list_filters |
| "what does each sheet use" | list_worksheets |
| "what SQL does this run" | list_sql_queries |
| "draw the lineage", "give me the graph" | get_lineage_graph |
| "what parameters exist" | list_parameters |
Never guess a file path
Every tool needs a real path to a .twbx or .twb. If the user has not given one, ask,
or offer to look in an obvious place such as ~/Downloads. Do not invent a filename and
do not retry a path that already failed with "File not found".
Reporting unused fields honestly
audit_workbook returns unused fields with a confidence level and a reason. These are
candidates for review, not a safe-delete list: a workbook file cannot prove a field is
unreferenced everywhere, and things like sets, groups and dashboard actions are not
visible to the parser. Always surface the confidence and the reason, and say plainly that
the user should check before deleting. Never tell someone a field is definitely safe to
remove.
Presenting results
Tool output is JSON built for machines. Summarise it: lead with the number that answers the question, then the specifics. For an audit, give the headline counts first (how many unused, how much of the workbook, how many performance findings), then the highest-severity findings with their suggested fixes. Do not paste raw JSON back at the user unless they ask for it.
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.
- 11d ago First seen · 56 lines · 73 tokens per session scan A 2847bbeae5c6
tableau-workbook-audit is a skill published in the GitHub repository andey0Saikiran/tableau-lineage (7 stars, last pushed 19d ago), licensed MIT. It adds 73 tokens to every session and 656 once invoked, about $0.0004 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
malloy-dashboards
Build or modify a Malloy Publisher dashboard, a tagged .malloy file in a package's dashboards/ directory, with auto-rendered filter controls, a grid layout, and # drill click-through. Use when the user asks for a dashboard, a filterable operational view, or drill-through between views, and no code is wanted.
malloy-gotchas-modeling
Common Malloy modeling mistakes and how to avoid them. Read BEFORE writing source definitions, dimensions, measures, or joins. Covers reserved words, NULL checks, date functions, type casts, field management (extend except/accept/rename vs include public/internal/private), and query-based source gotchas.
malloy-model
Build Malloy semantic models with base source and joined source files. Use when creating or modifying .malloy files, user asks to "create a malloy model", "add dimensions", "add measures", "create a source", or any Malloy model authoring task.
malloy-charts
Chart selection guidance and renderer reference for Malloy views. Use when choosing visualization types, adding chart annotations, user asks "what chart should I use", "how should I visualize this", or when deciding between barchart, linechart, scatterchart, etc.
malloy-materialization
Add and debug Malloy Persistence materializations in a package - persist an expensive source so queries read a pre-built table. Read this whenever the user wants to materialize a source, add a persist annotation, speed up a slow source, or asks why a persist source isn't building.
malloy-model-as-you-go
After answering a data question, write down what the answer assumed so the next reader can trust the number. A field with a.