qrspi-orchestrator: Instructions file for Claude Code

CLAUDE.md

qrspi-orchestrator CLAUDE.md is an instructions file for Claude Code from Vvlladd/qrspi-orchestrator. It costs 1,908 tokens per session, scanned A, original, MIT.

A staged workflow for developing features with multiple agents and human approval between phases. It covers questions, codebase research, and design, with written reports at each stage.

In plain words
What is it for?
Turning a feature request into requirements, exploring relevant files and dependencies, documenting risks, and producing an implementation design before coding.
Why use it?
It prevents an agent from moving ahead while requirements or design decisions are still unclear. The approval checkpoints make assumptions and risks visible before implementation.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is Vvlladd/qrspi-orchestrator's own configuration. It tells Claude Code how to work on qrspi-orchestrator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything qrspi-orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Vvlladd/qrspi-orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Vvlladd/qrspi-orchestrator/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Vvlladd/qrspi-orchestrator

Made for: Claude Code.

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-orchestrator CLAUDE.md

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

agentmods 80×15 button for qrspi-orchestrator CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vvlladd/qrspi-orchestrator/claude-md"><img src="https://agentmods.dev/badge/instructions/vvlladd/qrspi-orchestrator/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,908 This file is loaded in full into every session.
When invoked 1,908 The same file — it is already loaded in full.
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 $0.01908 $0.01908
Opus 5 $0.00954 $0.00954
Sonnet 5 $0.00382 $0.00382
Haiku 4.5 $0.00191 $0.00191

Measured 10d ago against content hash 85154f4e7d1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

qrspi-orchestrator 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.

CLAUDE.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QRSPI Pipeline

Multi-agent orchestration for feature development with human-in-the-loop checkpoints.

Pipeline Phases

Execute phases in order. STOP after each phase and wait for human approval before proceeding. Never auto-proceed.

Phase 1: Questions

  • Read the feature request
  • Scan the codebase for relevant patterns, files, and conventions (max 10 file reads)
  • Identify ambiguities, edge cases, unstated assumptions
  • Write reports/01-requirements.md with: Summary, Acceptance Criteria (specific, testable), Edge Cases, Out of Scope, Open Questions, Existing Code Context
  • Present summary and ask: "Approve, request changes, or reject?"

Phase 2: Research

Explore the codebase in depth:

  • Map all relevant files (models, protocols, engines, configs, tests)
  • Analyze existing patterns and conventions
  • Identify dependencies (internal modules, external packages, APIs)
  • Assess risks and complexity
  • Write reports/02-exploration.md with: File Map, Existing Patterns, Dependencies, Architecture Notes, Risks, Suggested Approach
  • Cite file paths and line numbers for every claim
  • Present summary and ask for approval

Phase 3: Design

Produce a clear, actionable design:

  • Read requirements and exploration report
  • Design component boundaries, interfaces, data flow
  • Define test strategy per component
  • Write reports/03-design.md with: Overview, Components (files, responsibility, interface, dependencies), Data Flow, Interface Contracts, Error Handling, Test Strategy, Migration/Breaking Changes

Then challenge your own design:

  • Is this the simplest approach? What's simpler?
  • What happens at scale, under load, with concurrent users?
  • What are the failure modes?
  • Are interfaces over-engineered or under-specified?
  • Any security concerns? (auth, injection, data exposure, input validation)

Revise the design based on self-critique. Present summary and ask for approval.

Phase 4: Plan

Decompose the design into ordered tasks:

  • Each task: 2-5 minutes of implementation work
  • One concern per task (don't mix implementation with tests)
  • Tests are separate tasks
  • Include setup tasks (packages, migrations, configs)
  • Final task is always integration verification
  • Write tasks.json with: id, title, description, files, acceptance_criteria, depends_on, estimated_minutes, status
  • Write reports/04-plan.md with human-readable table
  • Present task breakdown and ask for approval (human can reorder, split, merge, remove)

Read the full file on GitHub · 155 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. 10d ago First seen · 155 lines · 1,908 tokens per session scan A 85154f4e7d1a

Subscribe to this mod's changes

qrspi-orchestrator CLAUDE.md is an instructions file published in the GitHub repository Vvlladd/qrspi-orchestrator (6 stars, last pushed 9d ago), licensed MIT. It adds 1,908 tokens to every session, about $0.0095 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens