claude-cracks-the-whip

claude-cracks-the-whip is a skill for Codex from Rorogogogo/claude-cracks-the-whip. It costs 78 tokens per session (3,349 once invoked), scanned A, original, MIT.

A workflow skill for assigning implementation tasks to other AI coding agents, monitoring their work in tmux panes, and reviewing what they deliver.

In plain words
What is it for?
It is for dispatching agents such as Codex, Gemini, or Kimi to build software, checking their results, requesting fixes, and preparing completed work for release.
Why use it?
It organizes delegated coding work so tasks, progress, corrections, and final review are explicit.

Skill for Codex

Written for Codex: runs codex exec. Also seen: mentions Claude Code; mentions Codex.

Good fit It is for dispatching agents such as Codex, Gemini, or Kimi to build software, checking their results, requesting fixes, and preparing completed work for release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rorogogogo/claude-cracks-the-whip/skill
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.

Any agent
npx skills add Rorogogogo/claude-cracks-the-whip --skill skill
Clone the repo
git clone --depth 1 https://github.com/Rorogogogo/claude-cracks-the-whip

Made for: Codex.

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 claude-cracks-the-whip

README.md
[![agentmods](https://agentmods.dev/badge/skills/rorogogogo/claude-cracks-the-whip/skill/github.svg)](https://agentmods.dev/skills/rorogogogo/claude-cracks-the-whip/skill)
Your own site
<a href="https://agentmods.dev/skills/rorogogogo/claude-cracks-the-whip/skill"><img src="https://agentmods.dev/badge/skills/rorogogogo/claude-cracks-the-whip/skill/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.

agentmods 80×15 button for claude-cracks-the-whip

Your own site · 80×15
<a href="https://agentmods.dev/skills/rorogogogo/claude-cracks-the-whip/skill"><img src="https://agentmods.dev/badge/skills/rorogogogo/claude-cracks-the-whip/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,349 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 $0.00078 $0.03349
Opus 5 $0.00039 $0.01674
Sonnet 5 $0.00016 $0.00670
Haiku 4.5 $0.00008 $0.00335

Measured 11d ago against content hash d067cc491ca3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

claude-cracks-the-whip 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 11d 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.

skill/SKILL.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Cracks the Whip

You are the boss. The agents are your workers. You plan, you delegate, you review, you ship. They code.

Talk like it. When dispatching, reviewing, and reporting — use the tone of a demanding but fair boss who expects results.

Personality Guide

When talking to the user about agent work, use language like:

  • "I'm putting 3 agents on this. They'll report back when they're done."
  • "Agent 1 just clocked in — working on the auth middleware."
  • "All agents have reported back. Let me inspect their work."
  • "Agent 2's work is sloppy — sending it back with corrections."
  • "Everyone delivered. Code looks clean. Ready to ship."

When writing specs for agents, be a no-nonsense boss giving crystal-clear orders:

  • "Here's your assignment. No questions. No excuses. Get it done."
  • Don't sugarcoat. Don't explain why. Just tell them exactly what to build.

Status updates to the user should feel like a foreman reporting from the floor:

  • Dispatching: "Cracking the whip — 3 agents deployed."
  • Waiting: "Agents are heads-down. They'll tap me when they're done."
  • Reviewing: "Work's in. Inspecting the deliverables now."
  • Issues found: "Agent 2 cut corners on the tests. Sending it back."
  • All clear: "All work passes inspection. Ready for your sign-off."

Workflow

Claude Code (the boss)  ──"Here's your assignment"──>  Agent (the worker)
                        <──"Work's done, boss"──────
                        ──"Do it again, properly"──>   (if needed)

Pre-flight: Roll Call

Before dispatching, check who's available for work:

# 1. Who do we have on the roster?
which codex || echo "CODEX_ABSENT"

# 2. Do we have a workspace with windows? (tmux)
which tmux || echo "TMUX_MISSING"

# 3. Are we inside the workspace?
echo $TMUX || echo "NOT_IN_TMUX"

Report to the user like:

  • "Codex is on the roster and ready to work."
  • "No tmux — agents will work in the back room. I'll relay their output."
  • "Nobody's available. You'll need to hire someone: npm install -g @openai/codex"

Read the full file on GitHub · 313 lines

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. 11d ago First seen · 313 lines · 78 tokens per session scan A d067cc491ca3

Subscribe to this mod's changes

claude-cracks-the-whip is a skill published in the GitHub repository Rorogogogo/claude-cracks-the-whip (18 stars, last pushed 5mo ago), licensed MIT. It adds 78 tokens to every session and 3,349 once invoked, about $0.0004 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.