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 johnqtcg/awesome-skills --skill oracle-migrationgit clone --depth 1 https://github.com/johnqtcg/awesome-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/johnqtcg/awesome-skills/oracle-migration)<a href="https://agentmods.dev/skills/johnqtcg/awesome-skills/oracle-migration"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/oracle-migration/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/johnqtcg/awesome-skills/oracle-migration"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/oracle-migration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00141 | $0.05922 |
| Opus 5.5 | $0.00056 | $0.02369 |
| Sonnet 5.5 | $0.00028 | $0.01184 |
| Haiku 4.5 | $0.00014 | $0.00592 |
Grade A, and why
oracle-migration 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 1mo 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 — 420 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oracle Migration Safety Review
Quick Reference
| If you need to… | Go to |
|---|---|
| Understand what this skill covers | §1 Scope |
| Check mandatory prerequisites | §2 Mandatory Gates |
| Choose review depth | §3 Depth Selection |
| Handle incomplete context | §4 Degradation Modes |
| Analyze DDL safety item by item | §5 DDL Safety Checklist |
| Design a phased execution plan | §6 Execution Plan |
| Avoid common migration mistakes | §7 Anti-Examples |
| Score the review result | §8 Scorecard |
| Format review output | §9 Output Contract |
| Look up DDL lock behavior by operation | references/oracle-ddl-lock-matrix.md |
| Plan a large-table (>10M rows) change | references/large-table-migration.md |
§1 Scope
In scope — schema migration safety for Oracle 12.1 / 12.2 / 19c / 21c / 23ai:
- ALTER TABLE (add/drop/modify column, add/drop constraint, rename, move)
- CREATE / DROP / REBUILD INDEX (including ONLINE)
- Constraint management (FK, CHECK, UNIQUE with ENABLE NOVALIDATE pattern)
- Partition DDL (ADD/DROP/SPLIT/MERGE/EXCHANGE PARTITION, global index impact)
- Data backfill and transformation (CTAS, INSERT /*+ APPEND */, ROWID batching)
- Online table redefinition (DBMS_REDEFINITION)
- Migration file review (Flyway, Liquibase, custom PL/SQL deploy scripts)
- Rollback planning (DDL auto-commits — no transactional DDL rollback)
Out of scope — delegate to dedicated skills:
- Query optimization, bind variable tuning, plan stability →
oracle-best-practise - Application code changes →
go-code-revieweror language-specific reviewer - Security hardening, privilege management →
security-review
What ships with it
60 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.
- references/large-table-migration.md 27 KB
- references/migration-anti-examples.md 7.6 KB
- references/oracle-ddl-lock-matrix.md 10 KB
- references/oracle-version-licensing-matrix.md 10 KB
- scripts/lint_migration.py 74 KB runs code
- scripts/mutation_sweep.py 22 KB runs code
- scripts/run_regression.sh 2.2 KB runs code
- scripts/tests/COVERAGE.md 20 KB
- scripts/tests/golden/001_missing_ddl_lock_timeout.json 1.2 KB
- scripts/tests/golden/002_constraint_without_novalidate.json 1.4 KB
- scripts/tests/golden/003_missing_rollback.json 1.9 KB
- scripts/tests/golden/004_alter_move_without_online.json 1.4 KB
- scripts/tests/golden/005_partition_ddl_no_update_indexes.json 1.3 KB
- scripts/tests/golden/006_monolithic_update.json 1.4 KB
- scripts/tests/golden/007_well_formed_phased.json 1.9 KB
- scripts/tests/golden/008_good_dbms_redefinition.json 2.5 KB
- scripts/tests/golden/009_degraded_no_context.json 1.2 KB
- scripts/tests/golden/010_multi_step_workflow.json 1.8 KB
- scripts/tests/golden/011_column_type_without_redef.json 1.9 KB
- scripts/tests/golden/012_rowid_chunking_unexecutable.json 2.2 KB
- scripts/tests/golden/013_rename_swap_not_atomic.json 2.1 KB
- scripts/tests/golden/014_flashback_after_structural_ddl.json 1.9 KB
- scripts/tests/golden/015_copy_dependents_unchecked.json 2.1 KB
- scripts/tests/golden/016_nologging_hint_noop.json 1.9 KB
- scripts/tests/golden/017_widening_is_not_a_rewrite.json 1.6 KB
- scripts/tests/golden/018_uncommitted_dml_before_ddl.json 1.6 KB
- scripts/tests/golden/019_se2_online_unavailable.json 1.5 KB
- scripts/tests/golden/020_move_online_version_gate.json 1.5 KB
- scripts/tests/golden/021_truncate_without_backup.json 1.4 KB
- scripts/tests/golden/022_rename_column_live.json 1.6 KB
- scripts/tests/golden/023_index_rebuild_and_validate.json 1.6 KB
- scripts/tests/golden/024_nologging_ctas_no_recovery.json 1.6 KB
- scripts/tests/golden/025_session_setting_across_releases.json 1.5 KB
- scripts/tests/golden/026_planned_two_step_cutover.json 2.0 KB
- scripts/tests/golden/027_ddl_lock_timeout_zero.json 1.6 KB
- scripts/tests/golden/028_ddl_lock_timeout_absurd.json 1.3 KB
- scripts/tests/golden/029_small_table_constraint_is_a_note.json 1.5 KB
- scripts/tests/golden/030_truncate_with_snapshot.json 1.6 KB
- scripts/tests/golden/031_partition_ddl_no_global_indexes.json 1.5 KB
- scripts/tests/golden/032_interim_table_is_not_live.json 1.6 KB
- scripts/tests/golden/033_ddl_lock_timeout_invalid.json 1.5 KB
- scripts/tests/golden/034_ddl_lock_timeout_substitution.json 1.4 KB
- scripts/tests/golden/035_snapshot_of_the_wrong_table.json 1.7 KB
- scripts/tests/golden/036_restore_point_covers_everything.json 1.7 KB
- scripts/tests/golden/037_normal_restore_point_is_not_a_guarantee.json 1.9 KB
- scripts/tests/golden/038_partial_snapshot_is_not_a_backup.json 1.6 KB
- scripts/tests/golden/039_empty_interim_ctas_is_not_a_backup.json 1.6 KB
- scripts/tests/golden/040_guaranteed_restore_point_on_se2.json 1.7 KB
- scripts/tests/golden/041_unknown_edition_stays_conservative.json 1.7 KB
- scripts/tests/golden/042_targeted_snapshot_covers_the_dropped_column.json 1.6 KB
- scripts/tests/golden/043_join_filtered_ctas_is_unverifiable.json 1.8 KB
- scripts/tests/golden/044_copy_without_a_recovery_key.json 1.6 KB
- scripts/tests/golden/045_restore_point_advice_is_not_a_merge.json 1.7 KB
- scripts/tests/golden/046_table_alias_is_not_a_restriction.json 1.5 KB
- scripts/tests/golden/047_multi_column_drop_list_form.json 1.4 KB
- scripts/tests/golden/048_doomed_columns_cannot_key_each_other.json 1.6 KB
- scripts/tests/golden/049_multi_column_drop_with_keyed_copy.json 1.4 KB
- scripts/tests/report_coverage.py 6.8 KB runs code
- scripts/tests/test_golden_scenarios.py 16 KB runs code
- scripts/tests/test_server_harness.py 12 KB runs code
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.
- 1mo ago First seen · 420 lines · 141 tokens per session scan A ad3c233f1854
oracle-migration is a skill published in the GitHub repository johnqtcg/awesome-skills (30 stars, last pushed 18d ago), licensed MIT. It adds 141 tokens to every session and 5,922 once invoked, about $0.0006 per session on Opus 5.5. 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
db-schema-designer
Design normalized relational database schemas — ERDs, indexes, constraints, migrations, and performance optimization.
migration-generator
Generate database migrations with up/down scripts — Alembic, Flyway, Liquibase, and framework-native migrations.
sql-builder
Write and optimize complex SQL queries — JOINs, CTEs, window functions, query plans, and dialect-specific syntax.
sql-analyst
Perform SQL-based data analysis — exploratory queries, aggregations, funnels, cohorts, and insight narratives.
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…
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.