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/jaqubowsky/prmpt/agents-mdgit clone --depth 1 https://github.com/jaqubowsky/prmptWrote 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/jaqubowsky/prmpt/agents-md)<a href="https://agentmods.dev/instructions/jaqubowsky/prmpt/agents-md"><img src="https://agentmods.dev/badge/instructions/jaqubowsky/prmpt/agents-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 | $0.00646 | $0.00646 |
| Opus 5 | $0.00323 | $0.00323 |
| Sonnet 5 | $0.00129 | $0.00129 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
prmpt AGENTS.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 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prmpt-cli
Project Overview
CLI tool that scaffolds AI-first development workflows for any project using Claude Code. One command (npx prmpt-cli) copies templates, installs plugins, runs an interactive interview skill, and generates comprehensive project documentation — so Claude Code has full context from day one.
Architecture Pattern
Template-based scaffolding CLI in pure ESM JavaScript — see @docs/ai/ARCHITECTURE.md for details.
Project Structure
bin/
cli.mjs # Entry point (Commander setup)
src/
commands/
init.mjs # Init command (scaffold + launch interview)
update.mjs # Smart template update (no overwrite of user edits)
installers/
superpowers.mjs # Plugin installation via execa
utils/
banner.mjs # ASCII art banner
copy-templates.mjs # Template copying + variable injection
detect.mjs # Project detection (git, package.json, etc.)
templates/ # Scaffolding templates (12 files)
claude/
settings.json
skills/project-setup/
SKILL.md # Interview skill definition
docs/ai/ # 6 doc templates
docs/ai/ # This project's own documentation
Data Layer
No database or external data — reads/writes local files and shells out to claude CLI.
AI Working Rules
ALWAYS
- Use context7 MCP to check documentation before using any library, framework, or tool — even familiar ones. Your training data may be outdated.
- Use LSP for code navigation:
goToDefinition,findReferences,hoverinstead of grep. RunfindReferencesbefore renaming or changing signatures. Check LSP diagnostics after edits. - Read the source file before proposing changes — understand existing patterns first.
- Keep templates/ in sync: if you change the structure of a generated file, update the template AND the SKILL.md that describes it.
- Test
initandupdateflows manually after changes — there are no automated tests yet.
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 · 63 lines · 646 tokens per session scan A 188dd8f11edd
prmpt AGENTS.md is an instructions file published in the GitHub repository jaqubowsky/prmpt (2 stars, last pushed 5mo ago), licensed MIT. It adds 646 tokens to every session, about $0.0032 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 instructions, from other repositories
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
zapo CLAUDE.md
Claude Code instructions for vinikjkkj/zapo: The contributor handbook for this repository lives in AGENTS.md. Read that file and follow it as your primary source of project conventions, architecture rules, performance constraints, and review anti-patterns.
Silex AGENTS.md
AGENTS.md instructions for silexlabs/Silex, covering agents.md, tech stack, run it locally, building the desktop app and when writing code for silex (editing source).
SoDam-WikiMate AGENTS.md
AGENTS.md instructions for sodam-ai/SoDam-WikiMate, covering wikimate 작업 규칙 (크로스툴 — claude code · codex · gemini 공용), 문체, 자동 동작 (자연어 트리거 — 강제 호출 불필요), 접근 규칙 (자동 감지 — 특정 도구에 한정하지 않음) and obsidian 규칙.
leclap CLAUDE.md
Instructions for heristop/leclap: This repository's agent guidance lives in AGENTS.md — read it first; it is the single source of truth for structure, commands, and conventions.
Library-First-Engineering copilot-instructions.md
Instructions for StChiotis/Library-First-Engineering: You are an AI agent operating in a Library-First Engineering (LFE) repository. This adapter is a pointer. Canonical rules live in human-readable docs.