agent-help

A quick reference for a system that delegates work to specialized coding agents. It describes a reader agent for analysis and a maker agent for implementation, along with commands for planning and checking code reuse.

In plain words
What is it for?
It helps start repository analysis, implementation work, structured planning, reuse checks, and other delegation commands.
Why use it?
It helps developers choose the right delegated workflow instead of writing a request from scratch. The reader gathers findings, while the maker creates and integrates code.

Command for Claude Code

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/vibehat/claude-task-manager/agent-help
Clone the repo
git clone --depth 1 https://github.com/vibehat/claude-task-manager

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 773 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 $0.00000 $0.00773
Opus 5 $0.00000 $0.00387
Sonnet 5 $0.00000 $0.00155
Haiku 4.5 $0.00000 $0.00077

Measured 3d ago against content hash 48feb7d20ea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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.

.claude/commands/agent-help.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Help - Delegation System Reference

Quick reference for the specialized agent delegation system.

Usage: /agent-help

Available Agents

🔍 Reader Agent (Information Gathering)

  • Purpose: Analysis, research, pattern recognition
  • Command: /spawn-reader [analysis task]
  • Specialization: Cost-efficient analysis and documentation
  • Output: Structured findings with file references

🛠️ Maker Agent (Code Implementation)

  • Purpose: Feature implementation, code creation
  • Command: /spawn-maker [implementation task]
  • Specialization: High-quality code generation and integration
  • Output: Complete implementations with documentation

Quick Commands

Agent Spawning

  • /spawn-reader [task] - Launch analysis agent
  • /spawn-maker [task] - Launch implementation agent
  • /agent-help - Show this reference guide

Workflow Integration

  • /analyze-first [feature] - Analysis before planning
  • /structured-plan [request] - Full structured planning
  • /reuse-check [component] - Validation before creation

Common Workflows

📋 Standard Feature Development

1. /spawn-reader analyze existing [feature area] patterns
2. Review Reader findings
3. /spawn-maker implement [specific feature] using patterns
4. Integration and testing

🔄 Complex Multi-Step Implementation

1. /spawn-reader map current architecture for [area]
2. /spawn-maker create core [component] infrastructure
3. /spawn-reader analyze integration points
4. /spawn-maker build [feature] integration layer

🎯 Quick Implementation (when context is clear)

1. /spawn-maker implement [well-defined feature]
2. Follow existing patterns automatically

Agent Capabilities

Reader Agent Strengths

  • ✅ Architectural analysis and mapping
  • ✅ Pattern recognition and documentation
  • ✅ Dependency and integration point identification
  • ✅ Cost-efficient information gathering
  • ❌ Does not implement or modify code

Read the full file on GitHub · 130 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 · 130 lines · 0 tokens per session scan A 48feb7d20ea9

Subscribe to this mod's changes

agent-help is a command published in the GitHub repository vibehat/claude-task-manager (21 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 773 tokens. 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.