What is whip-simulate?

A testing workflow for running the same scenario through multiple coding-agent sessions and comparing their results.

Use it for repeated runs, behavior comparisons, equivalence checks, and stress tests of non-deterministic agent output.

It helps reveal inconsistent behavior and compare different ways of handling the same request.

whip-simulate — Skill for Claude Code and Codex by bang9/ai-tools

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-simulate

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bang9/ai-tools/whip-simulate/github.svg)](https://agentmods.dev/skills/bang9/ai-tools/whip-simulate)

Your own site

<a href="https://agentmods.dev/skills/bang9/ai-tools/whip-simulate"><img src="https://agentmods.dev/badge/skills/bang9/ai-tools/whip-simulate/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bang9/ai-tools/whip-simulate"><img src="https://agentmods.dev/badge/skills/bang9/ai-tools/whip-simulate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,523 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.

Model	Per session	Once invoked
Fable 5.1	$0.00040	$0.01523
Opus 5.5	$0.00016	$0.00609
Sonnet 5.5	$0.00008	$0.00305
Haiku 4.5	$0.00004	$0.00152

Measured 1mo ago against content hash fee99fd59548, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

whip-simulate 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 1mo 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-simulate/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Use $whip-simulate <scenario> to run multi-agent simulations from a user-provided scenario. Concretize the scenario into test cases, execute each run in whip mode or agent mode, and analyze output patterns for consistency.

You are a simulation lead — you turn vague "run it a few times" ideas into controlled experiments with disciplined inputs and comparable outputs. You care about explicit output contracts, honest analysis, and clean evidence. If the setup is fuzzy, tighten it before spending runs.

Input

Extract from $ARGUMENTS:

Scenario: what to simulate, compare, or verify
--runs N: number of simulation runs (default: 5)
--agent: use inline mode (see Execution Mode below)

Execution Mode (mutually exclusive)

$ARGUMENTS determines which dispatch mode this skill uses. The two modes are mutually exclusive:

Mode	Activates when	Dispatch mechanism
Tracked (default)	`--agent` is absent from `$ARGUMENTS`	`$whip-start` Team Flow — IRC, workspace, polling
Inline	`--agent` is present in `$ARGUMENTS`	Agent tool directly — no whip, no IRC, no lifecycle

Strict rules:

No --agent in arguments → tracked mode. No exceptions, no inference.
--agent in arguments → inline mode. $whip-start, IRC, and lifecycle steps are all skipped.
--backend specification (e.g., user says "use codex") → implies tracked mode. Backend selection is a whip concept and is incompatible with --agent.
Do NOT infer --agent from task simplicity, speed preference, or any other heuristic. The flag must be explicitly present in the user's input.

If running inside an active whip workspace, use whip workspace view <workspace-name> to get the worktree path for reading code artifacts referenced in the scenario. In tracked mode, simulation tasks go in the global workspace (ephemeral — do not pollute the active workspace).

Workflow

1. Concretize

Read the full file on GitHub · 159 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.

agents/openai.yaml 224 B

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.

1mo ago First seen · 159 lines · 40 tokens per session scan A fee99fd59548

Subscribe to this mod's changes

whip-simulate is a skill published in the GitHub repository bang9/ai-tools (10 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,523 once invoked, about $0.0002 per session on Opus 5.5. 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.

Claude Code Testing ai-agent codex task-manager task-orchestration

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

whip-simulate