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/openai-apinpx skills add kid-sid/codex-spellbook --skill openai-apigit 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 | $0.00056 | $0.01295 |
| Opus 5 | $0.00028 | $0.00647 |
| Sonnet 5 | $0.00011 | $0.00259 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
openai-api 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 3d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAI API
Use the OpenAI API through the Responses API by default, choose models intentionally, and keep integration code explicit about validation, retries, and cost boundaries.
When to Activate
- Add OpenAI API calls to an application or service
- Choose a model for coding, agentic, or general reasoning work
- Build a Codex-like coding workflow against the API
- Implement streaming or tool-calling behavior
- Add structured outputs or schema validation
- Review API key handling, retries, or rate-limit behavior
- Refactor an older Chat Completions integration to a newer pattern
Model Selection
As of April 18, 2026, current official docs indicate:
gpt-5.4is the flagship general model for complex reasoning and coding.gpt-5.4-miniis the lower-latency lower-cost GPT-5.4 variant.gpt-5.3-codexis the current most capable agentic coding model for Codex-like environments.codex-mini-latestis optimized for the Codex CLI; the docs recommend starting withgpt-4.1for direct general API use of that class.
Sources:
- https://developers.openai.com/api/docs/models
- https://developers.openai.com/api/docs/models/gpt-5.3-codex
- https://developers.openai.com/api/docs/models/codex-mini-latest
| Need | Start With | Notes |
|---|---|---|
| General app logic, strong reasoning, coding | gpt-5.4 |
Best default when quality matters most |
| Lower latency or cheaper general workloads | gpt-5.4-mini |
Good cost/perf default |
| Agentic coding in Codex-like workflows | gpt-5.3-codex |
Supports reasoning effort settings |
| Codex CLI tuning reference | codex-mini-latest |
CLI-oriented, not the default general API pick |
API Surface
| Situation | Preferred | Avoid |
|---|---|---|
| New integrations | Responses API | Starting new work on legacy patterns by default |
| Need multimodal, tools, or stateful interaction | Responses API | Rebuilding these features manually |
| Existing stable legacy integration | Migrate deliberately | Blind rewrites with no regression plan |
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.
- 3d ago First seen · 168 lines · 56 tokens per session scan A 5732b7d59b4d
openai-api is a skill published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,295 once invoked, about $0.0003 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…