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 andre-simplifica/oracle-apex-ai-skills --skill oracle-apex-exportgit clone --depth 1 https://github.com/andre-simplifica/oracle-apex-ai-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/andre-simplifica/oracle-apex-ai-skills/oracle-apex-export)<a href="https://agentmods.dev/skills/andre-simplifica/oracle-apex-ai-skills/oracle-apex-export"><img src="https://agentmods.dev/badge/skills/andre-simplifica/oracle-apex-ai-skills/oracle-apex-export/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/andre-simplifica/oracle-apex-ai-skills/oracle-apex-export"><img src="https://agentmods.dev/badge/skills/andre-simplifica/oracle-apex-ai-skills/oracle-apex-export.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 | $0.00058 | $0.01289 |
| Opus 5 | $0.00029 | $0.00645 |
| Sonnet 5 | $0.00012 | $0.00258 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
oracle-apex-export 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oracle APEX Export
Export supported Oracle APEX applications from 24.2 onward and application-schema database source with an explicit publication intent.
Before Exporting
- Read repository instructions and
.oracle-apex-ai/project-profile.md. - Read
.oracle-apex-ai/export-policy.jsonwhen present. - Confirm the configured SQLcl connection by checking the expected
USERandSERVICE_NAME, then confirm app ID, workspace, schema owner, and destination paths. - Confirm the live APEX version and run
validate_oracle_apex_compatibility.py; stop below 24.2. - Inspect current Git status and existing versioned artifacts.
- Determine the mode from export-modes.md.
- Confirm whether official repository publication was explicitly requested.
Do not infer official export authorization from a development, diagnosis, compile, or test request.
Modes
temporary-inspection: disposable read-only APEX export outside official folders.initial-baseline: first complete APEX export plus full application-schema structural DDL.application-snapshot: complete official APEX application export only.release: complete official APEX application export plus a full or partial five-file database bundle and pending DDL/DML.builder-fallback: manual App Builder download when the project permits it and SQLcl export is unavailable.
Read export-modes.md for entry and exit criteria.
APEX Export Contract
For official APEX exports:
- use the app ID and export options from the project profile;
- export to a candidate directory first;
- prefer a split source tree containing
install.sqlandapplication/; - include
readable/only on supported APEX releases before 26.1; - on APEX 26.1 or later, do not request
READABLE_YAML, because Oracle produces APEXlang instead; - include a monolithic
f<APP_ID>.sqlwhen the project requires it; - do not assume a split export also creates the monolithic file; run the project-approved non-split application export when both forms are required;
- treat split SQL, the version-allowed readable YAML, and the monolithic file as one atomic application snapshot;
- reject
.apx, APEXlang directories, and APEXlang generate/export/validate/import commands in every version; - make the Supporting Objects decision explicit;
- validate candidate structure and content before replacing the official snapshot;
- compare the diff to the requested application and scope;
- keep secrets, credentials, and environment-specific substitutions out of public artifacts.
What ships with it
9 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.
- agents/openai.yaml 370 B
- references/database-baseline.md 2.7 KB
- references/database-release.md 3.6 KB
- references/export-modes.md 3.4 KB
- references/export-retention.md 2.2 KB
- references/parallel-export.md 4.4 KB
- references/pending-migrations.md 3.2 KB
- references/release-bundle.md 3.2 KB
- references/snapshot-runtime-contract.md 2.5 KB
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 · 120 lines · 58 tokens per session scan A 00c5efc8ae62
oracle-apex-export is a skill published in the GitHub repository andre-simplifica/oracle-apex-ai-skills (20 stars, last pushed 17d ago), licensed MIT. It adds 58 tokens to every session and 1,289 once invoked, about $0.0003 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.
Other skills, from other repositories
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
nebula-logger-purging-and-retention
Use this skill when the user wants to configure how long Nebula Logger keeps log records before deleting or archiving them. Covers retention date semantics on Logc, the LogBatchPurger batch job, LogBatchPurgeScheduler, purge action values, and how to tune retention per user, profile, or scenario.
ddia-systems
Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choice", "which database should I use", "SQL or NoSQL", "replication lag", "partitioning strategy", "consistency vs availability", "stream processing", "ACID…
database-patterns
DB schema design and query tuning: normalization, indexing, N+1, transactions, EXPLAIN. Triggers: schema, index, slow query, N+1, PostgreSQL, MySQL, EXPLAIN, deadlock, query plan.
migration-patterns
Zero-downtime DB migrations: expand-contract, double-write, backfill, blue-green. Triggers: migration, schema change, backfill, ALTER TABLE, online DDL.
migrate
Run/create DB migrations (Alembic, Prisma, Laravel, Django, Flyway, Drizzle); checks backup. Triggers: apply migration, rollback, generate migration.