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.
git clone --depth 1 https://github.com/ahmedawan-oracle/claude-code-pluginsWrote 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/commands/ahmedawan-oracle/claude-code-plugins/migrate-job)<a href="https://agentmods.dev/commands/ahmedawan-oracle/claude-code-plugins/migrate-job"><img src="https://agentmods.dev/badge/commands/ahmedawan-oracle/claude-code-plugins/migrate-job/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/commands/ahmedawan-oracle/claude-code-plugins/migrate-job"><img src="https://agentmods.dev/badge/commands/ahmedawan-oracle/claude-code-plugins/migrate-job.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 | $0.00038 | $0.00635 |
| Opus 5.5 | $0.00015 | $0.00254 |
| Sonnet 5.5 | $0.00008 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
migrate-job 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 2mo 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/migrate-job — guided full migration
Drive the migrator end-to-end with checkpoints between phases. Asks the user before running each long-running step so they can abort or adjust.
Workflow
- Confirm prerequisites (invoke
aidp-migrator-bootstrapsilently — surface any gaps). - Ask for the source — either a Databricks workspace path OR a Databricks Job ID. Don't proceed without it.
- Build the DAG — invoke
aidp-build-dag. Show the resulting task count + dep count. Ask "looks right?" before next step. - Data check — invoke
aidp-check-data. Show the OK/MISSING/EMPTY counts.- If any MISSING / EMPTY: ask the user how to handle. Options: (a) migrate catalog first via
aidp-migrate-catalog, (b) configureaidp-bucket-mapping, (c) proceed anyway (with a clear warning).
- If any MISSING / EMPTY: ask the user how to handle. Options: (a) migrate catalog first via
- Migrate — invoke
aidp-migrate-job. Surface live log tail. - Status — when the run finishes, invoke
/migration-statuson the resultingJOB_REPORT.md.
Args (optional — if user provided them upfront)
$ARGUMENTS
If $ARGUMENTS contains a Databricks Job ID or workspace path, jump straight to step 3 (skip the question).
Checkpoints to surface to the user
Between phases, give the user a 1-line summary + the cost estimate of the next step:
[Phase 1/5] DAG built: 7 tasks, 18 dep notebooks, output reports/<MyJob>_manifest.json
[Phase 2/5] About to scan source data on cluster — ~2 min, no token cost. Proceed? (y/N)
...
[Phase 4/5] About to start Pass-2 migration — est. 30-90 min, $10-30 in Claude tokens. Proceed? (y/N)
Do not auto-proceed past the migrate step without explicit user confirmation. Pass-2 is expensive.
When to stop
- User aborts at any checkpoint.
- Data check shows >50% MISSING — likely the catalog hasn't been migrated yet; route to
/migrate-cataloginstead. - Cluster is not Active — instruct the user to start it before continuing.
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.
- 2mo ago First seen · 43 lines · 38 tokens per session scan A 3e0219dd0bb1
migrate-job is a command published in the GitHub repository ahmedawan-oracle/claude-code-plugins (4 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 635 once invoked, about $0.0002 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 2026-08-31.
migrate-job compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| migrate-jobahmedawan-oracle/claude-code-plugins | Command | 4 | 3mo ago | MIT | A | 38 | Claude Code |
| bootmicrosoft/PromptKit | Command | 113 | 10d ago | MIT | A | 14 | GitHub Copilot |
| music-suno-promptfrankxai/Starlight-Intelligence-System | Command | 10 | today | MIT | A | 23 | Claude Code |
| audit-promptOwl-Listener/ai-design-skills | Command | 202 | 5mo ago | MIT | A | 13 | Claude Code |
| laravel-ai-sdkjpcaparas/superpowers-laravel | Command | 157 | 4mo ago | MIT | A | 27 | Claude Code |
| vlm-ocr-evaluationscdenney/open-science-skills | Command | 69 | 2d ago | none | A | 0 | Claude Code |
| dare-llm-integrationdewtech-technologies/dare-method | Command | 5 | 3mo ago | MIT | A | 0 | Claude Code |