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 instructions/nidhinjs/prompt-mini/claude-mdgit clone --depth 1 https://github.com/nidhinjs/prompt-miniWrote 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/instructions/nidhinjs/prompt-mini/claude-md)<a href="https://agentmods.dev/instructions/nidhinjs/prompt-mini/claude-md"><img src="https://agentmods.dev/badge/instructions/nidhinjs/prompt-mini/claude-md.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 5.1 | $0.01208 | $0.01208 |
| Opus 5 | $0.00604 | $0.00604 |
| Sonnet 5 | $0.00242 | $0.00242 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
prompt-mini CLAUDE.md 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 6d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prompt-mini
A Claude Code plugin that intercepts vague prompts via a UserPromptSubmit hook, classifies the user's skill level, asks at most 5 targeted questions, then forges a structured prompt tailored to the detected framework and task type — before Claude Code executes anything.
What this repo is
This is the source repository for the prompt-mini Claude Code plugin. It is not a web app, not a CLI tool, and not a library. It is a plugin that installs into Claude Code and modifies how prompts are processed at the hook level.
Project structure
.claude-plugin/
plugin.json plugin identity — name, version, author, license
.dev-marketplace/
.claude-plugin/
marketplace.json local dev install config — points source to repo root
hooks/
hooks.json registers UserPromptSubmit → scripts/evaluate-prompt.py
scripts/
evaluate-prompt.py the hook gate — clarity scoring, bypass logic, skill trigger
skills/
prompt-mini/
SKILL.md core skill brain — PAC zones, phase logic, reference table
references/
stacks.md 40+ framework entries with pitfalls, scope anchors, stop conditions
question-patterns.md max-5 question engine and credit-killing anti-patterns
templates.md 6 forged prompt templates (ReAct, File-Scope, Scaffold, Debug, Migrate, Review)
patterns.md 35 Claude Code prompt anti-patterns with fixes
tests/
test-prompts.md test cases for the hook — run before any changes to evaluate-prompt.py
assets/ demo GIFs and screenshots for README
CHANGELOG.md version history
README.md public documentation
How the plugin works
User types a prompt
↓
evaluate-prompt.py runs (UserPromptSubmit hook)
↓
Bypass? (* / # prefix) → pass through unchanged
Too short? (<12 chars) → pass through unchanged
Clear prompt? → pass through, inject prompt as additionalContext
Vague prompt? → inject evaluation wrapper → prompt-mini skill fires
↓
Skill: scan project files → classify skill level → load matching stack sections
↓
Ask ≤5 questions → assemble forged prompt → deliver as single copyable block
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.
- 6d ago First seen · 144 lines · 1,208 tokens per session scan A 1744de4726a8
prompt-mini CLAUDE.md is an instructions file published in the GitHub repository nidhinjs/prompt-mini (29 stars, last pushed 5mo ago), licensed MIT. It adds 1,208 tokens to every session, about $0.0060 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 instructions, from other repositories
claude-prompt AGENTS.md
Instructions for danielkremen818/claude-prompt, covering agents.md, purpose, structure map, invariants (keep green) and conventions.
prompt-analyzer CLAUDE.md
Claude Code instructions for rayapatiranjithai/prompt-analyzer, covering claude.md, what this is, commands, architecture — the three moving parts and data & privacy contract.
Awesome-Prompt-Engineering AGENTS.md
Instructions for natnew/Awesome-Prompt-Engineering, covering agents.md, repository north star, agent role, trust boundary and read order.
Awesome-Prompt-Engineering CLAUDE.md
Instructions for natnew/Awesome-Prompt-Engineering, covering claude.md, north star, claude's role, claude behaviour rule and always-loaded context.
prompt-engineering-skill GEMINI.md
Instructions for PhAlves23/prompt-engineering-skill, covering prompt engineering — gemini context, prompt engineering, operating principle, workflow and canonical structure (omit sections that don't add value).
Promptheus GEMINI.md
Instructions for abhichandra21/Promptheus, covering promptheus project context, 1. project overview, core features, architecture and 2. building and running.