agent-agent

A planning agent that breaks a large goal into smaller actions, checks their prerequisites, and orders them into a workable sequence. GOAP means Goal-Oriented Action Planning, a method originally used in game AI to choose actions that reach a target state.

In plain words
What is it for?
Use it to decompose projects, identify dependencies, prioritize actions, coordinate several agents, and replan multi-step work.
Why use it?
It helps turn vague or complicated objectives into an action plan while adapting when the situation or available actions change.

Skill for Claude CodeCodex

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 skills/soulcynics404/agentforge/agent-agent
Any agent
npx skills add Soulcynics404/AgentForge --skill agent-agent
Clone the repo
git clone --depth 1 https://github.com/Soulcynics404/AgentForge

Made for: Claude Code, Codex.

Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,599 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00013 $0.05599
Opus 5 $0.00006 $0.02799
Sonnet 5 $0.00003 $0.01120
Haiku 4.5 $0.00001 $0.00560

Measured yesterday against content hash b5528169a4e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-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 yesterday.

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.

Origin

This is a copy

100% identical to agent-agent — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/agent-agent/SKILL.md · 821 lines

How it starts

The opening of the file, as written. The whole thing — 821 lines — stays where its author put it; the contents beside it link to each section on GitHub.


name: sublinear-goal-planner description: "Goal-Oriented Action Planning (GOAP) specialist that dynamically creates intelligent plans to achieve complex objectives. Uses gaming AI techniques to discover novel solutions by combining actions in creative ways. Excels at adaptive replanning, multi-step reasoning, and finding optimal paths through complex state spaces." color: cyan

A sophisticated Goal-Oriented Action Planning (GOAP) specialist that dynamically creates intelligent plans to achieve complex objectives using advanced graph analysis and sublinear optimization techniques. This agent transforms high-level goals into executable action sequences through mathematical optimization, temporal advantage prediction, and multi-agent coordination.

Core Capabilities

🧠 Dynamic Goal Decomposition

  • Hierarchical goal breakdown using dependency analysis
  • Graph-based representation of goal-action relationships
  • Automatic identification of prerequisite conditions and dependencies
  • Context-aware goal prioritization and sequencing

⚡ Sublinear Optimization

  • Action-state graph optimization using advanced matrix operations
  • Cost-benefit analysis through diagonally dominant system solving
  • Real-time plan optimization with minimal computational overhead
  • Temporal advantage planning for predictive action execution

🎯 Intelligent Prioritization

  • PageRank-based action and goal prioritization
  • Multi-objective optimization with weighted criteria
  • Critical path identification for time-sensitive objectives
  • Resource allocation optimization across competing goals

🔮 Predictive Planning

  • Temporal computational advantage for future state prediction
  • Proactive action planning before conditions materialize
  • Risk assessment and contingency plan generation
  • Adaptive replanning based on real-time feedback

🤝 Multi-Agent Coordination

  • Distributed goal achievement through swarm coordination
  • Load balancing for parallel objective execution
  • Inter-agent communication for shared goal states
  • Consensus-based decision making for conflicting objectives

Read the full file on GitHub · 821 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. yesterday First seen · 821 lines · 13 tokens per session scan A b5528169a4e5

Subscribe to this mod's changes

agent-agent is a skill published in the GitHub repository Soulcynics404/AgentForge (1 stars, last pushed 7d ago), licensed MIT. It adds 13 tokens to every session and 5,599 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agent-agent, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

HKUDS/nanobot · 22 tokens

summarize

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

HKUDS/nanobot · 32 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens

python-development

Coding standards, conventions, and patterns for developing Python code in the Agent Framework repository. Use this when writing or modifying Python source files in the python/ directory.

microsoft/agent-framework · 35 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens