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 skills add jneaimi/evaluate-before-you-build --skill prebuildgit clone --depth 1 https://github.com/jneaimi/evaluate-before-you-buildWrote 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/jneaimi/evaluate-before-you-build/prebuild)<a href="https://agentmods.dev/skills/jneaimi/evaluate-before-you-build/prebuild"><img src="https://agentmods.dev/badge/skills/jneaimi/evaluate-before-you-build/prebuild/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jneaimi/evaluate-before-you-build/prebuild"><img src="https://agentmods.dev/badge/skills/jneaimi/evaluate-before-you-build/prebuild.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00099 | $0.02437 |
| Opus 5 | $0.00049 | $0.01218 |
| Sonnet 5 | $0.00020 | $0.00487 |
| Haiku 4.5 | $0.00010 | $0.00244 |
Grade A, and why
prebuild 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 9d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Build Checkpoint (/prebuild)
A fast, focused checkpoint that ensures you evaluate before you build. This is the discipline layer for vibe coding — 6 questions via interactive prompts, ~10 minutes, then you code with clarity instead of guessing.
Core principle: Never generate implementation code until the human has confirmed the checkpoint. Use the AskUserQuestion tool to make confirmation fast and interactive — not a wall of text.
How It Differs from /think
| /prebuild | /think | |
|---|---|---|
| Focus | Code generation only | Any domain |
| Duration | ~10 minutes | 30-60+ minutes |
| Interaction | AskUserQuestion with selectable options | Free-form Q&A |
| AI role | Proposes answers, human picks/adjusts | Asks questions, waits |
| Output | Build spec → code generation | Full Bloom level progression |
| Saves to vault | No (unless asked) | Yes (Level 1) |
Use /prebuild for features and implementation tasks.
Use /think for architecture decisions, new projects, or non-code problems.
The Flow
┌──────────────────────────────────────────────────────────┐
│ 1. DETECT — What is being built? (silent) │
│ 2. SCAN — Read codebase for patterns (silent) │
│ 3. ROUND 1 — AskUserQuestion: Purpose, Reuse, Risks, │
│ Alternatives (4 interactive questions) │
│ 4. ROUND 2 — AskUserQuestion: Success Criteria, │
│ Documentation (2 interactive questions) │
│ 5. SPEC — Compile confirmed answers (internal) │
│ 6. BUILD — Generate code from spec │
└──────────────────────────────────────────────────────────┘
Step 1: Detect (Silent)
Parse what the user wants to build. Identify:
- Feature type: API endpoint, UI component, background job, integration, refactor, migration
- Scope signal: New feature, extension, or fix?
- Complexity signal: Single file or multi-file?
Output one line before starting the scan:
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.
- 9d ago First seen · 278 lines · 99 tokens per session scan A b4e94639dfa5
prebuild is a skill published in the GitHub repository jneaimi/evaluate-before-you-build (2 stars, last pushed 4mo ago), licensed MIT. It adds 99 tokens to every session and 2,437 once invoked, about $0.0005 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.
Other skills, from other repositories
think
Structured thinking skill implementing Bloom's AI Collaboration Framework v3. Auto-scales depth from stakes (reversibility + reliance): quick 3-question framing for reversible exploration, standard 6-question protocol for real decisions, deep mode with epistemics + teach-back + independent audit for binding one-way…
textbook-outline
A planning guide for designing a textbook before its chapters are written. It uses backward design, which starts with what learners should understand and do, then plans assessments, chapters, and examples around those goals.
textbook-init
A setup assistant for starting a textbook project or a workspace for several textbooks. It asks about the project, creates the directory structure, and can add version control and a README.
科研可视化工具
A research-visualisation workflow for examining data and producing publication-ready charts for scientific papers.
textbook
A workflow for writing a complete, multi-chapter textbook or structured course material. It plans the learning goals and chapter sequence, writes chapters with exercises, tracks progress, and performs a final review.
math-modeling
A workflow for mathematical modelling, where real-world questions are represented with mathematics and solved with code or analysis.