Borrowing it
Nothing to install: this file belongs to build-with-dhiraj/ai-workflow-framework-portability-kit. 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/build-with-dhiraj/ai-workflow-framework-portability-kit/main/CLAUDE.mdgit clone --depth 1 https://github.com/build-with-dhiraj/ai-workflow-framework-portability-kitWrote 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/build-with-dhiraj/ai-workflow-framework-portability-kit/claude-md)<a href="https://agentmods.dev/instructions/build-with-dhiraj/ai-workflow-framework-portability-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/build-with-dhiraj/ai-workflow-framework-portability-kit/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/build-with-dhiraj/ai-workflow-framework-portability-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/build-with-dhiraj/ai-workflow-framework-portability-kit/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 | $0.05516 | $0.05516 |
| Opus 5 | $0.02758 | $0.02758 |
| Sonnet 5 | $0.01103 | $0.01103 |
| Haiku 4.5 | $0.00552 | $0.00552 |
Grade B, and why
ai-workflow-framework-portability-kit 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `settings.json` | Snapshot of `~/.claude/settings.json` (plugins, permissions, env) | `~/.claude/settings.json` | How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Agents and Skills — Master Configuration
This folder is a portable, self-contained snapshot of the operator's Claude Code agent + skill setup. Drop it on any new Mac, follow BOOTSTRAP.md, and the orchestration logic, specialist agents, and skill library are restored exactly as on the source machine.
Snapshotted on: 2026-08-13 Source machine settings live at:
~/.claude/(mirrored here)
1. What lives in this folder
| Path | What it is | Source on the Mac |
|---|---|---|
CLAUDE.md (this file) |
Master orchestration logic, precedence rules, org chart | — |
MEMORY.md |
Memory-system design + restoration guide | — |
BOOTSTRAP.md |
Step-by-step new-Mac install procedure | — |
CLAUDE-global.md |
Snapshot of your global ~/.claude/CLAUDE.md |
~/.claude/CLAUDE.md |
SPEC-KIT-global.md |
Snapshot of your global ~/.claude/SPEC-KIT.md (greenfield spec-driven phase mapping) |
~/.claude/SPEC-KIT.md |
settings.json |
Snapshot of ~/.claude/settings.json (plugins, permissions, env) |
~/.claude/settings.json |
Agents/ |
All 36 custom specialist agents + dispatch logic (README inside) | ~/.claude/agents/ |
Skills/ |
All 148 active skills (symlinks resolved into real content; README inside) | ~/.claude/skills/ |
MCP/ |
Local MCP server template (secrets redacted) + full MCP roster | ~/.claude/mcp.json |
Plugins/ |
Installed-plugins snapshot + marketplace registry + Vercel cache + reinstall guide | ~/.claude/plugins/* + ~/.cache/plugins/github.com-vercel-vercel-plugin/ |
Connectors/ |
Account-bound integrations inventory (Gmail, Drive, Supabase, Slack, etc.) | claude.ai → Settings → Connectors (no local file) |
Automations/ |
The loop-heartbeat layer (Osmani "Loop Engineering") — harness scheduling stack, hooks/statusLine policy, and the human-in-the-loop kit-maintenance loop (README inside) | harness/account-bound (/loop, /goal, /schedule; no local file) |
Tooling/ |
Brewfile + npm globals snapshot + restore.sh (one-prompt end-to-end restore script) |
system-level (Homebrew, npm) |
Private/ |
🔒 Gitignored. The 7 work-specific skills held back from the public repo + the second config root (~/.claude-jove). Present in the kit folder, absent from the kit repo. (README inside) |
~/.claude/skills/* + ~/.claude-jove/ |
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 · 333 lines · 5,516 tokens per session scan B 242a0dfb7efe
ai-workflow-framework-portability-kit CLAUDE.md is an instructions file published in the GitHub repository build-with-dhiraj/ai-workflow-framework-portability-kit (4 stars, last pushed 27d ago), licensed MIT. It adds 5,516 tokens to every session, about $0.0276 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.