Borrowing it
Nothing to install: this file belongs to Varalix-Digitech-Solutions/clone-team. 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/Varalix-Digitech-Solutions/clone-team/main/CLAUDE.mdgit clone --depth 1 https://github.com/Varalix-Digitech-Solutions/clone-teamWrote 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/varalix-digitech-solutions/clone-team/claude-md)<a href="https://agentmods.dev/instructions/varalix-digitech-solutions/clone-team/claude-md"><img src="https://agentmods.dev/badge/instructions/varalix-digitech-solutions/clone-team/claude-md.svg" alt="Measured on agentmods" 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 | $0.02979 | $0.02979 |
| Opus 5 | $0.01489 | $0.01489 |
| Sonnet 5 | $0.00596 | $0.00596 |
| Haiku 4.5 | $0.00298 | $0.00298 |
Grade A, and why
clone-team 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 6d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — clone-team skill repository
This repo is a Claude Code skill: clone-team. It orchestrates a team of
agents to clone any website into a pixel-perfect UI and produce thorough
architecture documentation. It's intended to be installed into
~/.claude/skills/clone-team/ and published open-source.
If you're Claude working on this repo (developing the skill), read this. If
you're Claude using the skill to clone a site, the entry point is SKILL.md.
What this skill is, in one breath
The Manager (the main-thread Claude running SKILL.md) gathers requirements
and credentials interactively, does recon + foundation, then launches a
deterministic background Workflow that enforces, per section:
extract → spec → develop → full-regression-test → fix → re-test … until the
Tester gate passes — with a Backend Architect documenting the system in
parallel. The whole run is pausable and resumable (even across sessions /
after usage-limit cutoffs) via a durable state.json.
The two deliverables, always: (1) an exact UI clone, (2) ARCHITECTURE.md.
Why a Workflow (the core design decision)
The loop is a JS Workflow script, not Manager discretion, so the Tester gate
cannot be silently skipped. The script is the process: the Tester check is a
while-loop condition. This is the single most important property of the skill —
don't "simplify" it back into "spawn some agents and iterate," which is exactly
the failure mode (skipped tests, accepted "looks fine" sections) it prevents.
A Workflow runs in the background and can't talk to the user mid-run, so the division is deliberate:
- Interactive (creds, requirements, clarifications, checkpoint sign-off,
resume decisions, human final regression) → the Manager in
SKILL.md. - Autonomous grind (the build/test loop, backend docs) → the Workflow.
File map
SKILL.md # the Manager playbook (entry point)
agents/
frontend-developer.md # builder persona (canonical)
interaction-motion-analyst.md # motion-spec author (canonical)
motion-developer.md # sequential motion polish pass (canonical)
tester.md # the gate persona (canonical)
backend-architect.md # docs persona (canonical)
workflows/
clone-build-loop.js # the enforced loop (the engine)
references/
orchestration.md # team model + how to launch/steer the Workflow
state-and-resume.md # state.json schema, creds pattern, pause/resume/recovery
extraction-playbook.md # recon/extraction scripts + spec template
motion-playbook.md # motion taxonomy, state-matrix/token templates, drive-to-verify recipe
backend-doc-template.md # ARCHITECTURE.md structure
scripts/
state.mjs # durable state CLI (init/status/mark-section/remaining/…)
capacity.mjs # host-capacity probe -> recommended waveSize (check before launch)
usage-watchdog.mjs # zero-token 5h-usage-window poller -> WRAP_UP(≥80%)/HARD_STOP(≥90%) sentinels (graceful soft/hard stop + auto-wake)
install-deps.sh # idempotent dep bootstrap: agent-browser CLI + companion skills (run at Preflight)
vendor/
ui-pack/SKILL.md # the vendored ui-pack wrapper skill (installer copies it to ~/.claude/skills)
commands/
clone-status.md / clone-pause.md / clone-resume.md
evals/
evals.json # skill-creator test cases
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.
- 6d ago First seen · 198 lines · 2,979 tokens per session scan A 3349556a2d28
clone-team CLAUDE.md is an instructions file published in the GitHub repository Varalix-Digitech-Solutions/clone-team (20 stars, last pushed 2mo ago), licensed MIT. It adds 2,979 tokens to every session, about $0.0149 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 2026-08-30.
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.
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.