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/promptbasenpx skills add kid-sid/codex-spellbook --skill promptbasegit clone --depth 1 https://github.com/kid-sid/codex-spellbookWrote 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/kid-sid/codex-spellbook/promptbase)<a href="https://agentmods.dev/skills/kid-sid/codex-spellbook/promptbase"><img src="https://agentmods.dev/badge/skills/kid-sid/codex-spellbook/promptbase.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 | $0.00039 | $0.02087 |
| Opus 5 | $0.00019 | $0.01043 |
| Sonnet 5 | $0.00008 | $0.00417 |
| Haiku 4.5 | $0.00004 | $0.00209 |
Grade A, and why
promptbase 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 4d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PromptBase Skill Publishing
Patterns for writing Claude Code skills that pass PromptBase review and sell well.
When to Activate
- Writing a new skill intended for sale on PromptBase
- Reviewing an existing skill before submission
- Adapting a rejected skill after a "too specific" or "too simple" ruling
- Writing listing copy — title, description, examples, setup instructions
- Deciding whether a skill idea is worth submitting at all
The Core Test: Would a Stranger Pay For This?
Before writing a single line, answer three questions:
| Question | Green light | Red light |
|---|---|---|
| Who is the buyer? | Any Python/TS/Go developer | Users of one specific internal platform |
| What problem does it solve? | A hard, non-obvious problem they hit often | Something a quick search answers |
| Could they reproduce it from the title alone? | No — the value is in the patterns | Yes — the title explains everything |
If any answer is red, fix the concept before writing the skill.
Rejection Reasons and Fixes
Too Specific (most common rejection)
What it means: The skill only works for users of a niche platform, private SDK, or internal framework. The audience is too small to justify listing it.
Signs your skill is too specific:
- It imports from a private package (
from mycompany.lib import ...) - It references internal tool names, ports, config files, or env vars no outsider would know
- It combines more than 3 niche ideas (e.g. "LangGraph + Agentex + custom state machine")
- The target framework has fewer than ~5k GitHub stars
Fix: generalize the layer
REJECTED: Temporal + Agentex ADK + adk.state + adk.messages + FastACP
APPROVED: Temporal + Python temporalio SDK — standard patterns any developer can use
Strip the platform-specific layer. Keep the hard, transferable patterns underneath.
Too Simple / Guessable
What it means: A buyer could recreate the skill by reading the title and thinking for 30 seconds. The value isn't there.
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.
- 4d ago First seen · 212 lines · 39 tokens per session scan A c1b184c833ff
promptbase is a skill published in the GitHub repository kid-sid/codex-spellbook (21 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 2,087 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.
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…