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 tower/agent-skills --skill tower-ontologygit clone --depth 1 https://github.com/tower/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/tower/agent-skills/tower-ontology)<a href="https://agentmods.dev/skills/tower/agent-skills/tower-ontology"><img src="https://agentmods.dev/badge/skills/tower/agent-skills/tower-ontology/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/tower/agent-skills/tower-ontology"><img src="https://agentmods.dev/badge/skills/tower/agent-skills/tower-ontology.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 | $0.00125 | $0.03511 |
| Opus 5 | $0.00063 | $0.01755 |
| Sonnet 5 | $0.00025 | $0.00702 |
| Haiku 4.5 | $0.00013 | $0.00351 |
Grade A, and why
tower-ontology 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 8d 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tower Ontology Builder
This skill turns an undocumented catalog into a verified entity model stored on the catalog itself, so every future agent and person starts with the semantics instead of re-deriving them.
Core loop: inventory the catalog → profile each table with SQL → prove the relationships → write each entity to knowledge as you go → report the map and the open questions.
The output is not a document. It is a set of tower catalogs knowledge entries that tower-data reads on its next run.
The one rule that makes this skill worth running
An agent can guess an entity model from column names in seconds, and it will be confidently wrong. This skill's value is that it proves things with SQL before recording them.
Split every claim into two piles:
| Derivable from the data — verify, then record | Only a human knows — ask, or mark inferred |
|---|---|
Grain: is id actually unique? |
What the entity means to the business |
| Join validity, cardinality, orphan rate | Which of two overlapping tables is authoritative |
Enum domains (SELECT DISTINCT status) |
What "active", "internal", "churned" mean |
| Null rates, date coverage, row counts | Which rows to exclude by default |
Whether deleted_at behaves like a soft delete |
Why a column exists |
Never record a guess as confirmed. A wrong confirmed entry is worse than no entry — it silently poisons every future analysis.
Fast path
# 0. Don't clobber existing work
tower catalogs knowledge list default -j
# 1. Whole inventory — every namespace, table, column, and type in one call
tower catalogs show default --full -j
# 2. Per table: one profile query (see the battery below)
tower catalogs query default -j --sql '...'
# 3. Record immediately, one entry per table
tower catalogs knowledge set default entity-bronze-runs --scope table --object bronze.runs ...
Step 0: Check what already exists
tower catalogs knowledge list default -j
- Empty (
[]) — greenfield, run the full pass. - Has entries — you are refreshing, not rebuilding. Read existing entries first (
knowledge show default <name> -j), diff the inventory against them, and only profile tables that have noentity-*entry or whose columns changed. Never overwrite aconfirmedentry sourced from a human with aninferredone of your own; if you believe it's wrong, tell the user and let them decide.
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.
- 8d ago First seen · 245 lines · 125 tokens per session scan A 47a38254a4b3
tower-ontology is a skill published in the GitHub repository tower/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 125 tokens to every session and 3,511 once invoked, about $0.0006 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
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for prisma-next. Use when the user wants to create a pull request, open a PR, or submit changes for review.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
nornicdb-cypher-queries
Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…