clone-resume

clone-resume is a command for Claude Code from Varalix-Digitech-Solutions/clone-team. It costs 45 tokens per session (598 once invoked), scanned A, original, MIT.

A command for continuing an interrupted clone-team run, a workflow that recreates a website or application in sections. It checks the project files and resumes unfinished or unverified sections from the saved state.

In plain words
What is it for?
Reconciling saved progress with files on disk, revalidating sections that need testing, restarting the workflow, and continuing from handoff documents.
Why use it?
It avoids losing progress or repeating completed work after a pause, interruption, or usage limit.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the clone-team plugin — 1 skill, 5 commands, 5 agents shipped together

Good fit Reconciling saved progress with files on disk, revalidating sections that need testing…

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/varalix-digitech-solutions/clone-team/clone-resume
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/Varalix-Digitech-Solutions/clone-team

Made for: Claude Code.

Or install clone-team, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 5 agents.

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 clone-resume

README.md
[![agentmods](https://agentmods.dev/badge/commands/varalix-digitech-solutions/clone-team/clone-resume.svg)](https://agentmods.dev/commands/varalix-digitech-solutions/clone-team/clone-resume)
Your own site
<a href="https://agentmods.dev/commands/varalix-digitech-solutions/clone-team/clone-resume"><img src="https://agentmods.dev/badge/commands/varalix-digitech-solutions/clone-team/clone-resume.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 598 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00045 $0.00598
Opus 5 $0.00023 $0.00299
Sonnet 5 $0.00009 $0.00120
Haiku 4.5 $0.00005 $0.00060

Measured 7d ago against content hash 8310ef46d656, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

clone-resume 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 7d 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.

commands/clone-resume.md · 42 lines

What it actually says

Resume the clone-team run. Follow references/state-and-resume.md and references/orchestration.md.

  1. Resolve the project dir ($ARGUMENTS or cwd) and read <projectDir>/.clone-team/state.json. Re-establish full context: goal, target, stack, creds file path, paths, run-config.
  2. Reconcile with disk. Run node <skill>/scripts/state.mjs reconcile --dir <projectDir> — it keeps done sections whose targetFile exists, marks on-disk-but-unverified files built for test-first re-validation, demotes done-without-file to pending, and clears any stale WRAP_UP/HARD_STOP usage sentinels the drained run left behind (so the relaunched loop isn't immediately re-tripped). When unsure whether a half-finished section is trustworthy, prefer re-verification — re-testing is cheap insurance. 2.5. Restart the usage watchdog — a resume is a fresh Workflow, so it needs its own watchdog: node "<skill>/scripts/usage-watchdog.mjs" start --dir <projectDir> as a background Bash. Sections deferred by a prior usage-cutoff resume from their docs/research/components/<slug>.handoff.md files automatically.
  3. Relaunch the loop:
    • Same session with a still-valid lastRunId → call the Workflow tool with { scriptPath: "<skill>/workflows/clone-build-loop.js", resumeFromRunId: "<lastRunId>" }. Cached agent calls return instantly.
    • Otherwise (new session / cutoff) → compute remaining work with node <skill>/scripts/state.mjs remaining --dir <projectDir> and launch the Workflow fresh with args.sections set to only those not-done sections (the durable, journal-independent path). Re-pass goal, stack, creds path, personas (read agents/*.md), and run-config in args.
  4. Record the new runId (state.mjs set-run), set the phase, and let it run. If the backend doc is incomplete, ensure that track resumes too.
  5. Tell the user what's resuming and roughly what's left.
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. 7d ago First seen · 42 lines · 45 tokens per session scan A 8310ef46d656

Subscribe to this mod's changes

clone-resume is a command published in the GitHub repository Varalix-Digitech-Solutions/clone-team (20 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 598 once invoked, about $0.0002 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.

Related

Other commands, from other repositories

frontend-e2e

Perform a thorough live E2E test of a frontend web application using browser-bridge MCP tools. Tests every page, interactive element, form, navigation flow, responsive breakpoint, and accessibility rule through real browser interaction.

intellegix/intellegix-code-agent-toolkit · 0 tokens

health-check

Perform a comprehensive, read-only end-to-end review of any portfolio app across three layers — Frontend (E2E), Database integrity, and Audit Log & User Activity — and produce a structured, observations-only report. Optionally, on explicit opt-in, generate (never apply) the infrastructure provisions needed so future…

intellegix/intellegix-code-agent-toolkit · 0 tokens

spreadsheet-audit

Perform a 6-step audit of an Excel spreadsheet for formula correctness, formatting consistency, data integrity, boss-auditable simplicity, and spec compliance. Uses the excel-screenshot MCP server tools — no Excel installation required.

intellegix/intellegix-code-agent-toolkit · 0 tokens

stub-check

Perform a thorough 3-phase audit of the current project's codebase to find code that is unfinished, shallow, skeletal, or not production-ready. Phase 0.5 runs a Perplexity research reconnaissance using GitHub connectors (runs in parallel with Phase 1). Phase 1 uses local scanning (Grep/Glob/Read) independently. Phase…

intellegix/intellegix-code-agent-toolkit · 0 tokens

orchestrator-new

YOU ARE A PROJECT ARCHITECT. You take a project idea from the user, research the optimal architecture via Perplexity, generate a comprehensive BLUEPRINT.md with all phases and sub-phases, then route to /orchestrator or /orchestrator-multi for execution. You do NOT implement code yourself — you design and delegate.

intellegix/intellegix-code-agent-toolkit · 0 tokens

council-extract

Extract a completed Perplexity Model Council response from the current browser tab, converting it to structured markdown with model attribution, and save to disk.

intellegix/intellegix-code-agent-toolkit · 0 tokens