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 commands/ahmedawan-oracle/claude-code-plugins/migrate-jobgit 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.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 | $0.00038 | $0.00635 |
| Opus 5 | $0.00019 | $0.00318 |
| Sonnet 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 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 — 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.
- 4d 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 (2 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 635 once invoked, about $0.0002 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.