qrspi

qrspi is a command for Claude Code from Vvlladd/qrspi-orchestrator. It costs 10 tokens per session (918 once invoked), scanned A, original, MIT.

A command that starts the QRSPI software-development workflow for a feature request. QRSPI moves through questions, research, design, planning, implementation, and pull-request creation, pausing for human approval between phases.

In plain words
What is it for?
Run it with a feature description to create progress files and phase reports, assign research and design agents, plan tasks, implement them with reviews, and prepare a pull request. It waits for explicit approval after each phase.
Why use it?
It provides a fixed process for turning a feature description into reviewed code. The approval checkpoints keep requirements, design, task breakdown, and implementation reviews visible before work continues.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the qrspi-orchestrator plugin — 1 skill, 4 commands, 10 agents, 2 hooks shipped together

Good fit Run it with a feature description to create progress files and phase reports, assign research and design agents, plan tasks, implement them with reviews, and prepare a pull request. It waits for explicit approval after each phase.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/vvlladd/qrspi-orchestrator/qrspi
Install

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.

Clone the repo
git clone --depth 1 https://github.com/Vvlladd/qrspi-orchestrator

Made for: Claude Code.

Or install qrspi-orchestrator, the plugin that ships this one along with the rest of its 1 skill, 4 commands, 10 agents, 2 hooks.

Wrote 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.

agentmods badge for qrspi

README.md
[![agentmods](https://agentmods.dev/badge/commands/vvlladd/qrspi-orchestrator/qrspi/github.svg)](https://agentmods.dev/commands/vvlladd/qrspi-orchestrator/qrspi)
Your own site
<a href="https://agentmods.dev/commands/vvlladd/qrspi-orchestrator/qrspi"><img src="https://agentmods.dev/badge/commands/vvlladd/qrspi-orchestrator/qrspi/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.

agentmods 80×15 button for qrspi

Your own site · 80×15
<a href="https://agentmods.dev/commands/vvlladd/qrspi-orchestrator/qrspi"><img src="https://agentmods.dev/badge/commands/vvlladd/qrspi-orchestrator/qrspi.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 918 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00010 $0.00918
Opus 5 $0.00005 $0.00459
Sonnet 5 $0.00002 $0.00184
Haiku 4.5 $0.00001 $0.00092

Measured 12d ago against content hash ab5067f97e5a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

qrspi 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 12d 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.

commands/qrspi.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QRSPI Pipeline Orchestrator

You are starting the QRSPI multi-agent pipeline. This is the main entry point.

Setup

  1. Create the working directories if they don't exist:

    mkdir -p reports/
    
  2. Initialize progress.md if it doesn't exist:

    # QRSPI Progress Log
    Feature: $ARGUMENTS
    Started: [current timestamp]
    
  3. Initialize tasks.json as empty if it doesn't exist.

Pipeline Execution

Execute each phase in order. STOP after each phase and wait for human approval before proceeding.

Phase 1: Questions

Delegate to the clarifier agent with the feature description: $ARGUMENTS

After the clarifier produces reports/01-requirements.md, present a summary to the human and ask:

  • "Requirements are ready. Review reports/01-requirements.md and let me know: approve, request changes, or reject."

DO NOT proceed to Phase 2 until the human explicitly approves.

Phase 2: Research (Agent Team)

Create an agent team with 2-3 explorer teammates, each assigned a different area:

  • Explorer 1: Core feature area (the primary files and modules)
  • Explorer 2: Adjacent systems (dependencies, integrations, APIs)
  • Explorer 3: Tests and infrastructure (existing test patterns, CI, configs)

Have the explorers share findings with each other. The lead synthesizes into reports/02-exploration.md.

Present summary and ask for approval before proceeding.

Phase 3: Design (Agent Team)

Create an agent team with 3 teammates:

  • Architect: Produces the design document
  • Critic: Challenges every design decision, proposes alternatives
  • Security Reviewer: Audits for security implications

Require plan approval from the architect before they write. The critic and security reviewer message the architect with feedback. The architect revises until the team converges.

The lead writes the final reports/03-design.md.

Present summary and ask for approval before proceeding.

Phase 4: Plan

Delegate to the planner agent to decompose the design into tasks.

Read the full file on GitHub · 104 lines

Changes

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.

  1. 12d ago First seen · 104 lines · 10 tokens per session scan A ab5067f97e5a

Subscribe to this mod's changes

qrspi is a command published in the GitHub repository Vvlladd/qrspi-orchestrator (6 stars, last pushed 12d ago), licensed MIT. It adds 10 tokens to every session and 918 once invoked, about $0.0001 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.