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 skills/aropan/clist/safe-migrationnpx skills add aropan/clist --skill safe-migrationgit clone --depth 1 https://github.com/aropan/clistWrote 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/aropan/clist/safe-migration)<a href="https://agentmods.dev/skills/aropan/clist/safe-migration"><img src="https://agentmods.dev/badge/skills/aropan/clist/safe-migration.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 | $0.00076 | $0.00533 |
| Opus 5 | $0.00038 | $0.00267 |
| Sonnet 5 | $0.00015 | $0.00107 |
| Haiku 4.5 | $0.00008 | $0.00053 |
Grade A, and why
safe-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 5d 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.
What it actually says
Safe Django migrations in CLIST
Database changes are the highest-risk edits in this repo. The DB runs in the
db container and holds real data. Be conservative.
Procedure
- Inspect first. Read the target model in
src/<app>/models.pyand look at recent migrations insrc/<app>/migrations/to match style. - Find all usages of any field/table you plan to change or remove
(
grep/search acrosssrc/andlegacy/). Removing or renaming something still referenced will break the app. - Prefer additive changes. Add new nullable fields rather than renaming or dropping. For a rename, prefer add-new → backfill → switch readers → remove old, across separate migrations.
- Generate, don't hand-write:
Review the generated migration file before applying.docker compose exec dev ./manage.py makemigrations <app> - Apply:
docker compose exec dev ./manage.py migrate <app> - Verify the app still imports/serves and relevant tests pass
(
./manage.py test <app>).
Hard rules
- Never edit an already-applied historical migration unless explicitly asked. Add a new one instead.
- Never run
DROP/DELETE/TRUNCATEor an irreversible data migration without explicit user approval. - Don't rename or drop a column/table without first proving it's unused.
- If a data migration is needed, make it reversible (
RunPythonwith a reverse function) where feasible, and call out anything that isn't. - Treat
src/clist/,src/true_coders/,src/my_oauth/,src/ranking/models as high-traffic — extra care.
When done, report
The migration created, whether it was applied, backward-compatibility risks, and any manual backfill/cleanup step a human still needs to run.
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.
- 5d ago First seen · 54 lines · 76 tokens per session scan A 11d5d4985cef
safe-migration is a skill published in the GitHub repository aropan/clist (440 stars, last pushed 19d ago), licensed Apache-2.0. It adds 76 tokens to every session and 533 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 2026-08-30.
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.
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…
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…
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…
nw-ddd-eventsourcing
Event Sourcing and CQRS as DDD implementation patterns — when to use, aggregate event streams, projections, snapshots, sagas, upcasting, conflict resolution.
sql-translate
Translate SQL queries between database dialects (Snowflake, BigQuery, PostgreSQL, MySQL, etc.).