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 agentmods add skills/ebizsoft/agentic-claude-code/db2i-surveynpx skills add ebizsoft/agentic-claude-code --skill db2i-surveygit clone --depth 1 https://github.com/ebizsoft/agentic-claude-codeWrote 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/ebizsoft/agentic-claude-code/db2i-survey)<a href="https://agentmods.dev/skills/ebizsoft/agentic-claude-code/db2i-survey"><img src="https://agentmods.dev/badge/skills/ebizsoft/agentic-claude-code/db2i-survey.svg" alt="Measured on agentmods" 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 | $0.00101 | $0.01784 |
| Opus 5 | $0.00051 | $0.00892 |
| Sonnet 5 | $0.00020 | $0.00357 |
| Haiku 4.5 | $0.00010 | $0.00178 |
Grade A, and why
db2i-survey 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 4d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DB2 for i Survey & Exploration
Platform check first: "DB2" is three products. This skill is for
DB2 for i (IBM i / AS/400 — QSYS2 catalog, jdbc:as400: URLs). If
SELECT 1 FROM QSYS2.SYSSCHEMAS FETCH FIRST 1 ROW ONLY fails with
SQL0204, you are on DB2 LUW or z/OS — read
references/other-db2-variants.md: the
stall rules mostly don't apply there (their catalogs are stored, not
computed), but the analysis playbook and catalog translation table do.
The mental model (why naive exploration fails)
On DB2 for i, the SQL catalog (QSYS2.SYSTABLES, SYSCOLUMNS, …) is not
stored data — it is a façade computed over Machine Interface object
metadata. A catalog query resolves by touching live file objects. On an
old, fragmented box with invalid access paths, a schema-wide catalog query
triggers access-path rebuilds and cross-library resolution on every run:
your "metadata read" is the workload. Single-object reads are fast on
the same box for the same reason stat is fast where find / is not.
For scale: a ~300-schema / ~15,000-table instance that stalled indefinitely on
one schema-wide SYSCOLUMNS list completed a full survey — every schema
triaged, tables dictionaried (~11,000 columns), ~600 queries — in about a
minute with zero failures once every query followed the rules below.
Rules of engagement (inviolable — every query, no exceptions)
- Enumerate via
QSYS2.OBJECT_STATISTICS('LIB','FILE'), never viaSYSTABLES WHERE TABLE_SCHEMA=…. It reads object metadata directly — it'sls, not a catalog join. - Pin
TABLE_SCHEMAANDTABLE_NAMEonSYSCOLUMNS/SYSKEYCST. Never resolve across*LIBL. Schema-wide catalog reads are forbidden during exploration. - No
ORDER BYon exploratory queries — sorting a computed view forces full materialization. (Exception:ORDER BY ORDINAL_POSITIONon a single-table column read is fine.) - Cap everything:
FETCH FIRST n ROWS ONLYin the SQL and a client-side max-rows; set a per-statement query timeout so a stall dies in seconds, logged, instead of hanging the survey. - Row counts from
QSYS2.SYSTABLESTAT/SYSPARTITIONSTAT— catalogCARDis stale and older LPARs lackNUMBER_ROWSentirely. - Snapshot once, analyze offline. Pull inventories/dictionaries to local CSVs in one pass; iterate on the copy, never re-scan the live box.
- Read-only, structure-only. Use a SELECT-only profile. Survey queries
touch only QSYS2 catalog/metadata functions — never
SELECT *business rows. Structure (names, text, counts) is shareable; row data is not.
What ships with it
6 files 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.
- 4d ago First seen · 125 lines · 101 tokens per session scan A 489f7f01c200
db2i-survey is a skill published in the GitHub repository ebizsoft/agentic-claude-code (2 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 1,784 once invoked, about $0.0005 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
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.
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
moderator-page-migration
Port a moderator page from the main Next.js app (src/pages/moderator/) into apps/moderator. Use when asked to migrate, move or cut over a /moderator/ page to the spoke, or to port its tRPC procedures and Prisma services to SvelteKit loads/actions and Kysely.
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…
sql-translate
Translate SQL queries between database dialects (Snowflake, BigQuery, PostgreSQL, MySQL, etc.).