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/kid-sid/codex-spellbook/databasenpx skills add kid-sid/codex-spellbook --skill databasegit clone --depth 1 https://github.com/kid-sid/codex-spellbookWhat 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 | $0.00043 | $0.00604 |
| Opus 5 | $0.00022 | $0.00302 |
| Sonnet 5 | $0.00009 | $0.00121 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
database 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Database
Model schemas for clarity, migrate in safe increments, and optimize queries around real access patterns rather than guesswork.
When to Activate
- Design a new schema or table
- Add or review a migration
- Diagnose slow queries or query explosions
- Decide whether an index is warranted
- Refactor a transaction boundary
- Choose data deletion semantics
- Review ORM usage for N+1 issues
Naming and Migrations
| Object | Convention |
|---|---|
| Tables | plural snake_case |
| Columns | singular snake_case |
| Primary keys | id |
| Foreign keys | <table>_id |
| Join tables | alphabetical plural pair, e.g. roles_users |
| Change | Safe Pattern | Avoid |
|---|---|---|
| Drop column | add replacement, backfill, dual-read, dual-write, drop later | destructive one-step drop |
| Rename column | add new column and migrate gradually | instant rename in hot path |
| Add constraint | backfill invalid rows first | applying constraint to dirty data |
BAD
ALTER TABLE users DROP COLUMN full_name;
GOOD
ALTER TABLE users ADD COLUMN display_name text;
UPDATE users SET display_name = full_name WHERE display_name IS NULL;
Indexing and Query Shape
| Query Pattern | Index |
|---|---|
| Equality on foreign key | single-column btree |
| Filter + sort | composite index ordered by filter then sort |
| Case-insensitive search | functional index matching query function |
| Signal | Fix |
|---|---|
| One query per row in a list view | eager load or batch fetch |
| Repeated lookup in serializer loop | prefetch related data |
| ORM debug logs showing repeated shapes | consolidate access path |
Transactions and Deletion
| Preferred | Avoid |
|---|---|
| Short transaction around consistent write set | Holding transaction open across network calls |
| Retry on known transient conflicts | Blind retries on all DB errors |
| Use Soft Delete When | Use Hard Delete When |
|---|---|
| Audit or recovery matters | Regulation or retention requires full erasure |
| References must remain historically intact | Data is ephemeral and unreferenced |
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 · 84 lines · 43 tokens per session scan A 28206170a8f4
database is a skill published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 604 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…