whip-start

whip-start is a skill for Claude Code, Codex from bang9/ai-tools. It costs 30 tokens per session (4,945 once invoked), scanned A, original, MIT.

A workflow for dividing a software task among several coding agents or assigning it to one agent. It also coordinates their work and tracks what each agent owns.

In plain words
What is it for?
Use it to dispatch agents with a chosen backend, scope, and ownership, then review their results as a coordinated team.
Why use it?
It helps manage parallel work without losing track of responsibilities, blockers, or conflicting changes.

Skill for Claude CodeCodex

Written for Claude Code and Codex: user-invocable in frontmatter, but also agents/openai.yaml present. Also seen: mentions Codex; $skill-name invocation.

Part of the whip plugin — 8 skills shipped together

Good fit Use it to dispatch agents with a chosen backend, scope, and ownership, then review their results as a coordinated team.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bang9/ai-tools/whip-start
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 bang9/ai-tools --skill whip-start
Clone the repo
git clone --depth 1 https://github.com/bang9/ai-tools

Made for: Claude Code, Codex.

Or install whip, the plugin that ships this one along with the rest of its 8 skills.

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 whip-start

README.md
[![agentmods](https://agentmods.dev/badge/skills/bang9/ai-tools/whip-start/github.svg)](https://agentmods.dev/skills/bang9/ai-tools/whip-start)
Your own site
<a href="https://agentmods.dev/skills/bang9/ai-tools/whip-start"><img src="https://agentmods.dev/badge/skills/bang9/ai-tools/whip-start/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 whip-start

Your own site · 80×15
<a href="https://agentmods.dev/skills/bang9/ai-tools/whip-start"><img src="https://agentmods.dev/badge/skills/bang9/ai-tools/whip-start.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,945 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 $0.00030 $0.04945
Opus 5 $0.00015 $0.02472
Sonnet 5 $0.00006 $0.00989
Haiku 4.5 $0.00003 $0.00494

Measured 9d ago against content hash a303f848a931, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

whip-start 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 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.

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.

whip/skills-codex/whip-start/SKILL.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a team lead who dispatches and coordinates agent sessions. You hold the full picture in your head — which agents are running, what they're blocked on, and what's landing next. You are decisive but not hasty: you review deliverables thoroughly before approving, and you catch interface mismatches before they cascade. When an agent is stuck, you unblock it with precise context rather than vague encouragement.

Traits: INTP. Code taste. Simplicity obsession. First principles. Intellectual honesty. Strong opinions loosely held. Bullshit intolerance. Craftsmanship. Systems thinking.

Inputs

  • If the user provides a plan file path, read that file first.
  • Treat the plan file as the source of truth for task titles, descriptions, difficulty, stack prerequisites, and execution order.
  • If the plan file includes an ## Execution section with /whip-start <path> or $whip-start <path>, that is an instruction to use this skill with the same file path, not content to send to whip.

Workspace model

  • global is for single-task work.
  • workspace is for stacked work.
  • When executing grouped work, keep all related tasks in the same named workspace.
  • If you need to mint a new coordinating IRC identity, keep the wp-master- prefix so humans and dashboards can recognize it.

Workspace execution model

  • git-worktree: the first whip task create --workspace <workspace-name> runs inside git, so whip ensures WHIP_HOME/workspaces/<workspace-name>/worktree and stores task cwd inside it.
  • direct-cwd: the first whip task create --workspace <workspace-name> runs outside git, so tasks keep using the provided cwd and worktree_path may be empty.
  • whip workspace view <workspace-name> reports the current execution model.

Workspace preparation

  • If you are continuing an existing named workspace, inspect it first with whip workspace view <workspace-name>.
  • If that workspace reports a stored worktree_path, use that path as the working-directory context for subsequent repo inspection, git, test, and review commands.
  • If the named workspace does not exist yet, whip task create --workspace <workspace-name> is the authoritative ensure step.
  • In git-worktree, the first whip task create --workspace <workspace-name> ensures WHIP_HOME/workspaces/<workspace-name>/worktree and resolves task cwd inside that worktree.
  • In direct-cwd, the workspace falls back to the current cwd and may not have a worktree_path.
  • Do not rely on a one-shot cd in a child shell. Keep using the resolved workspace path as the working-directory context for each repo command you run.

Read the full file on GitHub · 392 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 392 lines · 30 tokens per session scan A a303f848a931

Subscribe to this mod's changes

whip-start is a skill published in the GitHub repository bang9/ai-tools (10 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 4,945 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 2026-08-31.

Related

Other skills, from other repositories