Borrowing it
Nothing to install: this file belongs to ljucask/pureinn-product-development. 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/ljucask/pureinn-product-development/main/CLAUDE.mdgit clone --depth 1 https://github.com/ljucask/pureinn-product-developmentWrote 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/ljucask/pureinn-product-development/claude-md)<a href="https://agentmods.dev/instructions/ljucask/pureinn-product-development/claude-md"><img src="https://agentmods.dev/badge/instructions/ljucask/pureinn-product-development/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/ljucask/pureinn-product-development/claude-md"><img src="https://agentmods.dev/badge/instructions/ljucask/pureinn-product-development/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 | $0.06306 | $0.06306 |
| Opus 5 | $0.03153 | $0.03153 |
| Sonnet 5 | $0.01261 | $0.01261 |
| Haiku 4.5 | $0.00631 | $0.00631 |
Grade B, and why
pureinn-product-development CLAUDE.md scanned grade B with 1 finding 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 9d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Never tell the user to go do research and return. Offer Path B immediately. How it starts
The opening of the file, as written. The whole thing — 414 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 when working in this repository.
What this repository is
The Pureinn product development framework published as a Claude Code plugin. Contains 51 active skills and 2 commands covering the full product lifecycle (FDD+SDD hybrid with JIT per-feature design, intuitive Feature Card lifecycle states, Figma MCP integration, a cross-phase pm-prototype engine that compiles tool-ready prototype specs for Lovable/v0/Figma Make, a cross-phase pm-stress-test adversarial stakeholder-pushback simulator, a cross-phase pm-root-cause diagnostic engine for in-flight anomalies, a reconciliation-based Rebuild playbook for onboarding existing products, a pm-audit workspace health check, a re-runnable pm-prioritize backlog engine, pm-process-flows user-type + process/user-flow mapping, a client discovery layer for commissioned builds (Discovery Interview Kit field material, pm-discovery-interview session prep, pm-meeting Client Discovery capture with directive/hypothesis reference classification, incremental client-facing pm-discovery-report, and pm-scope-brief as the Phase 3b definition alternative to the PRD with a Business Capabilities downstream contract), stage-keyword shortcuts (/pureinn define, /pureinn model...) that enter the framework at any phase and scaffold a workspace on the fly, and a universal --agent execution mode (every skill tagged synthesis/decision/never) that drafts an artifact autonomously in a subagent with an anti-hallucination input guard, review-after for decisions, and interactive-only for dialogue skills).
Plugin repo is the master copy. The AI Workflow/.claude/commands/ folder in the personal framework repo is secondary. Always edit here first.
Repository structure
.claude-plugin/
plugin.json - Package metadata (name, version, author, paths)
marketplace.json - Marketplace registration metadata
commands/
pureinn/ - Main orchestrator (entry point, routing, exit gates)
pureinn-resume/ - Resume paused project
skills/
[skill-name]/
SKILL.md - Skill content + frontmatter (name, description, triggers, metadata)
scripts/
release.sh - Versioning + CHANGELOG automation (run before every release)
assets/
pureinn-banner.png
README.md - Public-facing documentation
FRAMEWORK_GUIDE.md - Detailed playbook and skill reference
CHANGELOG.md - Version history
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.
- 9d ago First seen · 414 lines · 6,306 tokens per session scan B 4aa2d5af9753
pureinn-product-development CLAUDE.md is an instructions file published in the GitHub repository ljucask/pureinn-product-development (2 stars, last pushed 29d ago), licensed MIT. It adds 6,306 tokens to every session, about $0.0315 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). 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.