help

help is a command for coding agents from bacchus-labs/wrangler. It costs 8 tokens per session (2,040 once invoked), scanned A, original, MIT.

A command reference and project-governance guide for Wrangler, a framework that organizes software work with specifications, tracked issues, reusable workflows, and project rules.

In plain words
What is it for?
Use it to look up a command, understand brainstorming and planning workflows, break specifications into issues, implement planned work, or view project status.
Why use it?
It gives developers one place to learn Wrangler commands and its working rules, including writing tests before code and keeping evidence of progress.

Command

Part of the wrangler plugin — 25 skills, 16 commands, 16 agents shipped together

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.

agentmods
npx agentmods add commands/bacchus-labs/wrangler/help
Clone the repo
git clone --depth 1 https://github.com/bacchus-labs/wrangler

Or install wrangler, the plugin that ships this one along with the rest of its 25 skills, 16 commands, 16 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 help

README.md
[![agentmods](https://agentmods.dev/badge/commands/bacchus-labs/wrangler/help.svg)](https://agentmods.dev/commands/bacchus-labs/wrangler/help)
Your own site
<a href="https://agentmods.dev/commands/bacchus-labs/wrangler/help"><img src="https://agentmods.dev/badge/commands/bacchus-labs/wrangler/help.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,040 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00008 $0.02040
Opus 5 $0.00004 $0.01020
Sonnet 5 $0.00002 $0.00408
Haiku 4.5 $0.00001 $0.00204

Measured 3d ago against content hash 898adff0ab67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

help 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 3d 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/help.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wrangler Help

Comprehensive documentation for the Wrangler project governance plugin.

Arguments

Parse $ARGUMENTS for one optional positional argument:

  • $1 (optional) — command-name: Show help for a specific command
Argument Shows
(none) Full help documentation
brainstorm Brainstorming workflow details
write-plan Plan creation details
generate-plan-for-spec Spec-to-issues breakdown
implement Autonomous implementation
issues Status display details

Overview

Wrangler is a project governance framework and skills library for Claude Code. It provides:

  • Specification documents for planning features and changes
  • MCP-based issue tracking for discrete, completable tasks
  • Skills library with proven workflows and patterns
  • Session hooks for automatic workspace initialization
  • Constitutional governance for consistent decision-making

Core Principles

  1. MCP tools are the source of truth — Issues and specs managed via MCP
  2. Skills are mandatory when available — If a skill exists, use it
  3. TDD is non-negotiable — Write tests first, always
  4. Evidence over claims — Verify before declaring success
  5. Files in .wrangler/ — Centralized workspace directory

Commands

/wrangler:brainstorm

Refine rough ideas into fully-formed designs using Socratic method.

Usage
/wrangler:brainstorm
/wrangler:brainstorm "I want to add user authentication"
What It Does
  • Asks clarifying questions to understand requirements
  • Explores alternatives and trade-offs
  • Produces a validated design ready for specification
  • Invokes the brainstorming skill

/wrangler:write-plan

Create detailed implementation plans with bite-sized tasks.

Usage
/wrangler:write-plan
/wrangler:write-plan .wrangler/specifications/SPEC-000001-feature.md
What It Does
  • Analyzes specification or requirements
  • Breaks down into discrete MCP issues
  • Each issue includes TDD steps and exact file paths
  • Optionally creates architecture reference document
  • Invokes the writing-plans skill

Read the full file on GitHub · 356 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. 3d ago First seen · 356 lines · 8 tokens per session scan A 898adff0ab67

Subscribe to this mod's changes

help is a command published in the GitHub repository bacchus-labs/wrangler (4 stars, last pushed 6mo ago), licensed MIT. It adds 8 tokens to every session and 2,040 once invoked, about $0.0000 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.