Borrowing it
Nothing to install: this file belongs to karlng279/ai-ready-product-workflow-v2. 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/karlng279/ai-ready-product-workflow-v2/develop/CLAUDE.mdgit clone --depth 1 https://github.com/karlng279/ai-ready-product-workflow-v2Wrote 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/karlng279/ai-ready-product-workflow-v2/claude-md)<a href="https://agentmods.dev/instructions/karlng279/ai-ready-product-workflow-v2/claude-md"><img src="https://agentmods.dev/badge/instructions/karlng279/ai-ready-product-workflow-v2/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/karlng279/ai-ready-product-workflow-v2/claude-md"><img src="https://agentmods.dev/badge/instructions/karlng279/ai-ready-product-workflow-v2/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 | $0.01990 | $0.01990 |
| Opus 5.5 | $0.00796 | $0.00796 |
| Sonnet 5.5 | $0.00398 | $0.00398 |
| Haiku 4.5 | $0.00199 | $0.00199 |
Grade A, and why
ai-ready-product-workflow-v2 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 1mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI-Ready Product Workflow v2 — always-on rules
Rules only. Knowledge lives in PRD.md (meaning) and ARCHITECTURE.md (mechanism). Do not read either end
to end — use docs/INDEX.md to find the sections you need.
This repo follows docs/multi-session-repo-playbook.md. Sessions do not share memory; the repository is the
only channel between them. A stale document is worse than a missing one.
Session protocol
- Read
docs/STATE.md— what is claimable, what is blocked, what is waiting on the owner. - Pick one card from
tasks/BACKLOG.md. Read that card file only. If the row has no card file, write it first from the row plus the sections it cites. - Read only the sections the card names. Use
docs/INDEX.md. - Run both test files before touching anything — an already-red suite is not yours to inherit silently.
- Claim: on
develop, add the card ID to the in-flight table indocs/STATE.mdand commit that line before starting. That commit is the lock. Then create your card branch fromdevelop. Verify your file set is disjoint from everything else in flight.
python3 tests/test_docs.py && python3 tests/test_prohibitions.py
Prohibitions
Each is something a context-free session does by default because it is locally the obvious move.
| Never | Why |
|---|---|
Write features/*/design/WF-XXX.md |
Wireframes are ## WF-XXX sections inside one design/wireframes.md (PRD 3.2) |
Write artifact: PM-STRATEGY or PM-DISCOVERY |
Those are conceptual names. Real values are in PRD 5.2 |
| Write a count of skills or commands as a number in a test or assertion | Assert the set. Counts outlive their truth (ARCHITECTURE 7.1) |
Edit AGENTS.md, GEMINI.md or .cursorrules without editing its skills/ twin |
They must stay byte-identical (ARCHITECTURE 2.2) |
Sync README.md or GETTING_STARTED.md with its skills/ twin |
These two pairs differ by design (ARCHITECTURE 2.2) |
| Add a skill without walking all 11 surfaces | ARCHITECTURE 3.3. Items 7, 10 and 11 are caught by no test |
| Say the stack uses TanStack Query | It uses TanStack Table + native fetch (PRD 2.4) |
| Invent a ShadCN component name | Check design-framework/stage2-component-specs/shadcn-component-catalog.md |
| Regenerate an artifact wholesale to fix a small change | That is what artifact-sync / /sync-check are for |
Renumber a PRD/ARCHITECTURE section, or an artifact ID |
Breaking change. Every citation and downstream reference dies |
Merge into main without the owner confirming it in this session |
main is the protected trunk; work integrates on develop (ARCHITECTURE 6.5) |
| Claim an enforcement mechanism you have not written | Ship the test with the rule, or say plainly it is on discipline |
| Trust a count, table or path in a doc without checking disk | This repo's docs have drifted before. Verify, then assert |
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.
- 1mo ago Changed · -26 lines · +464 tokens per session 0f00813b6c02
- 1mo ago Changed · +2 lines · +53 tokens per session 49ecb2ac9f22
- 1mo ago First seen · 163 lines · 1,473 tokens per session scan A d09e40e8f734
ai-ready-product-workflow-v2 CLAUDE.md is an instructions file published in the GitHub repository karlng279/ai-ready-product-workflow-v2 (6 stars, last pushed 1mo ago), licensed MIT. It adds 1,990 tokens to every session, about $0.0080 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.