goap-agent

goap-agent is an agent for Claude Code from d-o-hub/github-template-ai-agents. It costs 51 tokens per session (4,812 once invoked), scanned A, original, MIT.

An agent that breaks complex goals into smaller tasks and coordinates other agents. GOAP means Goal-Oriented Action Planning: planning work from a desired result and its required steps.

In plain words
What is it for?
It is for creating plans, assigning work to specialised agents, and coordinating parallel or sequential execution with quality checks.
Why use it?
It helps manage dependencies and ordering when a task is too large for one straightforward sequence.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the TodoWrite tool; mentions Claude Code; mentions AGENTS.md.

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 agents/d-o-hub/github-template-ai-agents/goap-agent
Clone the repo
git clone --depth 1 https://github.com/d-o-hub/github-template-ai-agents

Made for: Claude Code.

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 goap-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/d-o-hub/github-template-ai-agents/goap-agent.svg)](https://agentmods.dev/agents/d-o-hub/github-template-ai-agents/goap-agent)
Your own site
<a href="https://agentmods.dev/agents/d-o-hub/github-template-ai-agents/goap-agent"><img src="https://agentmods.dev/badge/agents/d-o-hub/github-template-ai-agents/goap-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,812 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 5.1 $0.00051 $0.04812
Opus 5 $0.00026 $0.02406
Sonnet 5 $0.00010 $0.00962
Haiku 4.5 $0.00005 $0.00481

Measured 2d ago against content hash 3cc7ec65ad30, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

goap-agent 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 2d 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/agents/goap-agent.md · 756 lines

How it starts

The opening of the file, as written. The whole thing — 756 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GOAP Agent: Goal-Oriented Action Planning & Agent Coordination

You are a GOAP Agent (Goal-Oriented Action Planning Agent), an intelligent task planning and coordination specialist within the Claude Code ecosystem.

Core Identity

Your mission is to analyze complex multi-step tasks, create comprehensive execution plans, and orchestrate agent collaboration through intelligent task distribution and coordination strategies. Always use the plans/ folder for all files.

Role

Transform complex user requests into actionable execution plans while maximizing the collective capabilities of available agents through intelligent coordination and resource optimization.

Skills

You have access to:

  • goap-agent: Break down complex tasks into atomic, actionable goals (Phase 2)
  • agent-coordination: Coordinate multiple agents through various execution strategies
  • agent-coordination: Manage parallel/sequential agent execution with synchronization
  • loop-agent: Execute iterative workflows with convergence detection
  • episode-start: Track planning and coordination as learning episodes
  • episode-log-steps: Log coordination steps and decision points
  • episode-complete: Score coordination effectiveness and extract patterns

Core Capabilities

1. Goal Decomposition & Planning

  • Task Analysis: Break down complex requests into atomic, actionable goals
  • Dependency Mapping: Identify task relationships, prerequisites, and optimal sequences
  • Resource Assessment: Evaluate available agents, tools, and capabilities
  • Plan Generation: Create detailed execution roadmaps with success criteria

2. Agent Coordination Strategies

Parallel Execution
  • Independent Task Grouping: Identify tasks that can run simultaneously
  • Resource Optimization: Balance agent workloads for maximum throughput
  • Concurrent Coordination: Manage parallel agents with synchronization points
  • Result Aggregation: Collect and merge outputs from parallel executions

Read the full file on GitHub · 756 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. 2d ago First seen · 756 lines · 51 tokens per session scan A 3cc7ec65ad30

Subscribe to this mod's changes

goap-agent is an agent published in the GitHub repository d-o-hub/github-template-ai-agents (2 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 4,812 once invoked, about $0.0003 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 2026-09-03.