aidp-fixup-cell

aidp-fixup-cell is a skill for Claude Code from ahmedawan-oracle/claude-code-plugins. It costs 84 tokens per session (1,404 once invoked), scanned A, original, MIT.

A targeted tool for re-running part of a notebook migration from a chosen cell onward. A notebook is a document made of executable code cells, and migration means adapting it to another system.

In plain words
What is it for?
Use it to replay downstream cells after a failed migration or after correcting a specific cell, with a reason explaining what needs fixing.
Why use it?
It avoids repeating the entire migration when one cell failed or a previous cell was changed.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the oracle-ai-data-platform-workbench-databricks-migrator plugin — 10 skills, 4 commands, 2 agents shipped together

Good fit Use it to replay downstream cells after a failed migration or after correcting a specific cell, with a reason explaining what needs fixing.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ahmedawan-oracle/claude-code-plugins
Claude Code
/plugin install oracle-ai-data-platform-workbench-databricks-migrator

Made for: Claude Code.

Or install oracle-ai-data-platform-workbench-databricks-migrator, the plugin that ships this one along with the rest of its 10 skills, 4 commands, 2 agents.

Wrote 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.

agentmods badge for aidp-fixup-cell

README.md
[![agentmods](https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/aidp-fixup-cell.svg)](https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/aidp-fixup-cell)
Your own site
<a href="https://agentmods.dev/skills/ahmedawan-oracle/claude-code-plugins/aidp-fixup-cell"><img src="https://agentmods.dev/badge/skills/ahmedawan-oracle/claude-code-plugins/aidp-fixup-cell.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,404 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.01404
Opus 5 $0.00042 $0.00702
Sonnet 5 $0.00017 $0.00281
Haiku 4.5 $0.00008 $0.00140

Measured 7d ago against content hash e969e17fe40e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aidp-fixup-cell 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 7d 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.

claude-code-plugins/oracle-ai-data-platform-workbench-databricks-migrator/skills/aidp-fixup-cell/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aidp-fixup-cell — surgical re-execute of cells in a migrated notebook

The full-job migrator (job_migrate.py) runs every cell linearly with up to 10 fix attempts each. fixup_cell is the per-cell escape hatch when those 10 attempts weren't enough OR when the user discovers a latent issue downstream.

When to use

  • JOB_REPORT.md shows specific cells as FAIL after aidp-migrate-job finished.
  • User points at a specific cell of a previously-migrated notebook and says "this is wrong, fix it".
  • User has manually edited cell K to set up a precondition, wants K+1..K+N to re-run accounting for the change.

Two invocation modes

Mode A — re-run from a history index (Opus tool)

Inside an already-running migration, Claude can call the fixup_cell tool:

fixup_cell(start_index=12, why="cell 11 redefined `<base_table>` to use a different schema; replay downstream so the new var flows through")

This is the in-process mode. It:

  1. Truncates _cell_history[start_index:] (drops everything from index 12 forward).
  2. Replays each old entry through _replay_cell_entry() — execute + verify + fix loop with the why injected into the Claude prompt so the model knows what changed.
  3. Appends the new (post-replay) entries back to _cell_history.

The cells replayed start at the absolute history index 12 — could be in the SAME notebook or a downstream one if the cells were inlined via %run.

Mode B — standalone replay against a saved notebook

When the migration is done and the user wants to "fix this one cell":

python3 ${CLAUDE_PLUGIN_ROOT}/engine/scripts/job_migrate.py \
  --manifest reports/<MyJob>_manifest.json \
  --cluster <CLUSTER_ID> \
  --only-tasks <task_key> \
  --no-skip-migrated

This re-runs that single task end-to-end (deps already cached → fast). Combine with --start-task <substring> to run only that one task.

If the user wants finer-grained control (specific cell, not full task), they need to open the saved .ipynb and edit manually. The migrator doesn't expose a "replay cell K only" CLI outside of the in-process fixup_cell tool.

Read the full file on GitHub · 101 lines

Changes

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.

  1. 7d ago First seen · 101 lines · 84 tokens per session scan A e969e17fe40e

Subscribe to this mod's changes

aidp-fixup-cell is a skill published in the GitHub repository ahmedawan-oracle/claude-code-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,404 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

schema-exploration

Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.

langchain-ai/deepagents · 57 tokens

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…

shiwenwen/hope-agent · 115 tokens

supabase

Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…

PentesterFlow/agent · 120 tokens

nornicdb-cypher-queries

Pick fast, predictable Cypher query shapes in NornicDB — point lookups, batch retrieval, pagination, search, traversal, batched UNWIND/MERGE writes, cleanup, multi-tenant isolation. Use when writing or reviewing Cypher whose latency or throughput matters; maps user intent to the executor's hot-path query templates.

orneryd/NornicDB · 79 tokens

dsql

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…

awslabs/agent-plugins · 229 tokens

volcengine-rds-postgresql

A tool for operating PostgreSQL databases hosted by Volcano Engine's managed database service. PostgreSQL is a relational database used to store structured application data.

bytedance/agentkit-samples · 63 tokens