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/migration-statusgit clone --depth 1 https://github.com/ahmedawan-oracle/claude-code-pluginsWhat 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 | $0.00048 | $0.00803 |
| Opus 5 | $0.00024 | $0.00402 |
| Sonnet 5 | $0.00010 | $0.00161 |
| Haiku 4.5 | $0.00005 | $0.00080 |
Grade A, and why
migration-status 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 2d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/migration-status — parse the last migration report
Reads JOB_REPORT.md (the per-cell pass/fail summary the migrator emits) and converts it to a quick verdict + per-task action list.
Workflow
- Locate
JOB_REPORT.md. Default to the most recent file atreports/<job>/JOB_REPORT.md(local mirror) or<output-base>/<job>/JOB_REPORT.md(workspace path — fetch via REST if no local mirror). - Parse the per-task table.
- Roll up totals + identify the failing cells.
- Recommend the next skill to invoke per failing-task.
Args
$ARGUMENTS
If $ARGUMENTS is a path or a job name, target that. If empty, locate the newest.
Output template
== Migration status: <MyJob> (run dated 2026-XX-XX HH:MM:SS UTC) ==
| Task | Status | Cells: OK | Fail | Fixed | Notes |
|---|---|---|---|---|---|
| <task_a> | PASS | 27 | 0 | 2 | |
| <task_b> | PARTIAL | 18 | 2 | 7 | cell 12, cell 19 |
| <task_c> | FAIL | 0 | - | - | dep notebook unresolved |
Overall: 2/3 PASS, 1 PARTIAL, 0 FAIL → RESULT: PARTIAL
Recommended actions:
• <task_b>: cells 12 + 19 failed all 10 attempts.
→ Invoke aidp-fixup-cell on each with a `why` reason.
• <task_c>: structural failure (dep `helpers/io_utils` couldn't be migrated).
→ Open dep .ipynb manually, fix, then aidp-resume-migration with --only-tasks <task_c>.
Acceptance contracts: (if applicable)
• <task_a>: PASS — 3 consecutive zero windows observed.
Reading the underlying file
Format is documented in references/job-report-format.md. The key fields:
- Per-task
Status∈ {PASS,PARTIAL,FAIL}. - Cell counts:
OK(executed clean),Failed(exhausted 10 attempts),Fixed(passed after >=1 retry). - Failing cell IDs listed in the "Errors & Warnings" section.
When to use
- After any
aidp-migrate-jobrun. - When the user asks "how did the migration go", "did it pass", "what failed".
- Before deciding which fix path to take.
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.
- 2d ago First seen · 68 lines · 48 tokens per session scan A 2db8f9d18e72
migration-status is a command published in the GitHub repository ahmedawan-oracle/claude-code-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 803 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
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
flow-nexus-neural
Train and deploy neural networks in distributed sandboxes.
openrouter-setup
Configure OpenRouter as an OpenAI-compatible endpoint (OPENROUTERAPIKEY in env, never in code) for moonshotai/kimi-k3, deepseek/deepseek-v4, z-ai/glm.
laravel-ai-sdk
Build AI features with the first-party Laravel AI SDK (Laravel 13+); use the laravel:ai-sdk skill exactly as written.
data-scientist
Run the Data Scientist workflow using the canonical contract in .github/agents/data-scientist.agent.md.
audit-prompt
Evaluate an existing prompt for clarity, effectiveness, and edge cases.