Borrowing it
Nothing to install: this file belongs to rafadorado/qrspiv. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rafadorado/qrspiv/main/CLAUDE.mdgit clone --depth 1 https://github.com/rafadorado/qrspivWrote 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/rafadorado/qrspiv/claude-md)<a href="https://agentmods.dev/instructions/rafadorado/qrspiv/claude-md"><img src="https://agentmods.dev/badge/instructions/rafadorado/qrspiv/claude-md/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/instructions/rafadorado/qrspiv/claude-md"><img src="https://agentmods.dev/badge/instructions/rafadorado/qrspiv/claude-md.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 | $0.00617 | $0.00617 |
| Opus 5 | $0.00309 | $0.00309 |
| Sonnet 5 | $0.00123 | $0.00123 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
qrspiv 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 10d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
QRSPIV is a Claude Code plugin (not a traditional software project). It contains no compiled code, no dependencies, and no build system. The entire project is markdown instruction files that guide Claude through 7 phases of structured feature development, evolving HumanLayer's RPI methodology.
Project Structure
commands/— 7 markdown files, one per pipeline phase (question, research, design, outline, plan, implement, validate).claude-plugin/plugin.json— plugin metadata (name, version, author, repository)README.md— overview and usage
There is no build, test, or lint step. Changes are validated by reading the markdown and ensuring instruction quality.
The QRSPIV Pipeline
Each command is a slash command (/qrspiv:<phase>) with under 40 instructions:
| Command | Phase | Output | Key Constraint |
|---|---|---|---|
question |
Q | task.md + questions.md |
Questions must NOT reveal the task (context isolation) |
research |
R | research.md |
Document what EXISTS, not what should change; spawns parallel sub-agents |
design |
S | design.md (~200 lines) |
All open questions must be resolved by human before proceeding |
outline |
P1 | outline.md (~60-80 lines) |
Phases must be testable end-to-end (vertical, not horizontal) |
plan |
P2 | plan.md |
Code snippets ~1:1 with actual code; every phase ends with human checkpoint |
implement |
I | Actual code changes | Follow plan checkpoints; pause after each phase for human confirmation |
validate |
V | validation.md |
Three layers: functional correctness, pattern compliance, code quality |
All artifacts live in thoughts/<id>-<title>/.
Core Design Principles
- Context isolation: The research phase receives only questions, never the task description, ensuring objective findings
- No model opinions: Present facts and options with tradeoffs; humans make strategic decisions
- Vertical phases: Each implementation phase cuts through all system layers (DB → service → API → frontend), never horizontal (all DB changes first, then all services, etc.)
- Human-in-the-loop: Design approval, outline approval, and phase checkpoints are human decisions
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.
- 10d ago First seen · 47 lines · 617 tokens per session scan A b6caa35ef344
qrspiv CLAUDE.md is an instructions file published in the GitHub repository rafadorado/qrspiv (6 stars, last pushed 5mo ago), licensed MIT. It adds 617 tokens to every session, about $0.0031 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.