Agent skill

Behavior MCP

by putervision in putervision/state-memory-mcp

Teaches the agent to use the Behavior MCP server for ~60Hz in-browser behavior trees, triggers, and recordings.

MITAuto-check passedAgent Workflows

Install Behavior MCP

skills CLI
$ npx skills add putervision/state-memory-mcp --skill behavior-mcp -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install putervision/state-memory-mcp behavior-mcp --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/putervision/state-memory-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/behavior-mcp .claude/skills/behavior-mcp && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
behavior-mcp
GitHub stars
111
Token cost
~853 tokens
SKILL.md length
338 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Teaches the agent to use the Behavior MCP server for ~60Hz in-browser behavior trees, triggers, and recordings.

  • Works in 3 steps: Role in the PuterVision Pentad → Core Operational Sequence → Complete 10 Consolidated MCP Tools…
  • Tasks that involve MCP servers
  • SKILL.md covers 1. Role in the PuterVision…, 2. Core Operational Sequence and 3. Complete 10 Consolidated…
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Behavior MCP is an agent skill from putervision/state-memory-mcp. Teaches the agent to use the Behavior MCP server for ~60Hz in-browser behavior trees, triggers, and recordings.

Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The repository describes itself as: Persistent, branch-aware workflow state memory MCP server for AI coding assistants. Tracks tasks, accepted decisions, and active blockers to prevent session context bloat and… The licence is MIT.

When your agent uses it

  • Tasks that involve MCP servers

Example prompts

  • “Use the behavior-mcp skill to teach the agent to use the Behavior MCP server for ~60Hz in-browser behavior trees, triggers, and recordings”
  • “/behavior-mcp”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Role in the PuterVision Pentad
  2. Core Operational Sequence
  3. Complete 10 Consolidated MCP Tools Reference

What it can do on your machine

Read from SKILL.md and the folder at commit 0f60ae4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Behavior MCP loads about 853 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 338 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~853

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from putervision/state-memory-mcp at commit 0f60ae4, republished under its MIT licence (© putervision). 338 words, ~853 tokens.

Download SKILL.mdSave it as .claude/skills/behavior-mcp/SKILL.md (or your agent's skills folder).
name
behavior-mcp
description
Teaches the agent to use the Behavior MCP server for ~60Hz in-browser behavior trees, triggers, and recordings.

Behavior Runtime Engine (behavior-mcp)

This skill provides step-by-step guidance and operational patterns for interacting with @putervision/behavior-mcp with project slug "state-memory-mcp".


1. Role in the PuterVision Pentad

  • Workflow State (state-memory-mcp): Persistent task DAGs, decisions, milestones, and blockers.
  • Perception (vision-memory-mcp): Visual layout caching, screenshots, and visual specifications.
  • Spatial World (world-model-mcp): Persistent 3D/2D coordinates, bounding boxes, and topological relations.
  • Strategic Reasoning (agent-reasoning-mcp): Strategic BDI goals, utility scoring, and intention dispatch.
  • Tactical Execution (behavior-mcp): High-frequency (~60Hz) deterministic behavior tree execution directly in browser runtimes with reactive interrupts.

2. Core Operational Sequence

  1. Define or Load Behavior: Call load_behavior with action: "load" to inject and start tree execution.
  2. Register Reactive Triggers: Configure emergency preemption using register_trigger with priority and cooldown guards.
  3. Monitor Telemetry: Poll execution health, tick rates, and active traversal nodes with get_status.
  4. Runtime Blackboard: Read and mutate execution variables via manage_blackboard.
  5. Safety Guardrails: Immediately halt or pause rogue states using abort_behavior.

3. Complete 10 Consolidated MCP Tools Reference

Tool NameKey ActionsKey ParametersDescription
load_behaviorload, unload, swapbehavior_name, behavior_version, parameters, intention_idHot-swap, inject, or initialize behavior tree instances in browser runtime.
set_parametersset, get, resetexecution_id, parametersDynamically update or query execution parameters for the active tree.
get_statuscurrent, history, tree_stateexecution_id, limitQuery active behavior status, current node path, tick count, duration, and errors.
abort_behaviorabort, pause, resumeexecution_id, reasonImmediately halt, pause, or resume execution and disengage active inputs.
register_triggerregister, listname, condition_type, priority, cooldown_ms, behavior_nameConfigure reactive interrupt triggers with priority preemption and cooldowns.
replay_recordingcapture, listrecording_id, execution_id, frames, nameCapture or replay deterministic browser action sequences with adaptive timing.
get_metricscurrent, history, aggregate, compareexecution_id, behavior_name, limitRetrieve execution telemetry, tick durations, stuck events, and statistics.
manage_behaviorsregister, list, getname, version, tree, tree_json, descriptionCRUD operations for immutable JSON behavior trees with SHA-256 tree hash verification.
manage_blackboardget, setexecution_id, key, valueRead or write shared behavior tree blackboard state variables.
manage_runtime_dbstats, audit, snapshot, diff, restoreaction, name, descriptionDatabase maintenance, diagnostics, and SHA-256 Merkle audit verification.

© putervision, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/behavior-mcp of putervision/state-memory-mcp.

Open the folder on GitHubat commit 0f60ae4

Compare with similar skills

Behavior MCP next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Behavior MCP compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Behavior MCP this skillputervision/state-memory-mcp111—~853Automated safety check: PassMIT
Cesium Quickstartgaopengbin/cesium-mcp140—~354Automated safety check: PassMIT
Scenario Orbit Viewsscenario-labs/skills898—~2.3kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official37k11 repos~3.1kAutomated safety check: PassApache-2.0

Similar skills

  • Cesium Quickstart

    gaopengbin/cesium-mcp

    Guide users through their first interaction with the Cesium 3D globe via MCP tools

    140 GitHub stars~354 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Scenario Orbit Views

    scenario-labs/skills

    A skill your agent uses when a single image of a character, creature, prop, vehicle, or building must be seen from new camera angles through the Scenario MCP server: turnarounds, a 360 orbit, views…

    898 GitHub stars~2.3k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 62 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    37k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Fastmcp Client CLI

    PrefectHQ/fastmcp

    Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

    28k GitHub starsUsed in 1 repo~823 tokens
    Agent WorkflowsAuto-check passed

More from putervision/state-memory-mcp

  • State Memory MCP

    putervision/state-memory-mcp

    Teaches the agent to use the state-memory-mcp MCP server to track workflow state, tasks, decisions, blockers, artifacts, plans, milestones, and their semantic relationships in a persistent graph…

    111 GitHub stars~1.9k tokensUpdated 4 days ago
    Auto-check passed
  • Video Ingest

    putervision/state-memory-mcp

    Teaches the agent to process, ingest, analyze, and compare WebM, MP4, and GIF video recordings using vision-memory-mcp and state-memory-mcp.

    111 GitHub stars~902 tokensUpdated 4 days ago
    Auto-check passed
  • Webcrypt MCP

    putervision/state-memory-mcp

    Teaches the agent to use the WebCrypt MCP server for AES-256-GCM symmetric encryption, RSA-4096 hybrid encryption, key generation, digital signatures, hashing, and post-quantum cryptography.

    111 GitHub stars~847 tokensUpdated 4 days ago
    Auto-check passed
  • Agent Reasoning MCP

    putervision/state-memory-mcp

    Teaches the agent to use the Strategic Agent Reasoning MCP server for BDI goals, utility scoring, risk evaluation, and replanning.

    111 GitHub stars~889 tokensUpdated 4 days ago
    Auto-check passed
  • Vision Memory MCP

    putervision/state-memory-mcp

    Teaches the agent to use the Visual Memory MCP server to cache webpage and application screenshots, matching layout states and avoiding redundant LLM vision calls.

    111 GitHub stars~1.4k tokensUpdated 4 days ago
    Auto-check: notes
  • World Model MCP

    putervision/state-memory-mcp

    Teaches the agent to use the Spatial World Model MCP server to track entities, 3D/2D positions, spatial relationships, object permanence, and movement simulation.

    111 GitHub stars~804 tokensUpdated 4 days ago
    Auto-check passed

Questions about Behavior MCP

What does Behavior MCP do?

Teaches the agent to use the Behavior MCP server for ~60Hz in-browser behavior trees, triggers, and recordings. Behavior MCP is an agent skill from putervision/state-memory-mcp. Teaches the agent to use the Behavior MCP server for ~60Hz in-browser behavior trees, triggers, and recordings.

When should I use Behavior MCP?

Behavior MCP fits situations like: tasks that involve MCP servers.

How do I install Behavior MCP in Claude Code?

Run `npx skills add putervision/state-memory-mcp --skill behavior-mcp -a claude-code`. Or copy the skill folder (.agents/skills/behavior-mcp in putervision/state-memory-mcp) into .claude/skills/behavior-mcp in your project. Claude Code loads it when a task matches its description.

How do I install Behavior MCP in Codex?

Run `npx skills add putervision/state-memory-mcp --skill behavior-mcp -a codex`. Or copy the skill folder (.agents/skills/behavior-mcp in putervision/state-memory-mcp) into .agents/skills/behavior-mcp in your project. Codex loads it when a task matches its description.

Can I use Behavior MCP in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add putervision/state-memory-mcp --skill behavior-mcp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/behavior-mcp, .gemini/skills/behavior-mcp, .github/skills/behavior-mcp and .opencode/skills/behavior-mcp in your project.

What does Behavior MCP need to run?

SKILL.md names no scripts, command-line tools or credentials: Behavior MCP is instructions for the agent only.

Does Behavior MCP access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Behavior MCP safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Behavior MCP use?

Behavior MCP is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Behavior MCP use?

About 853 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Behavior MCP?

Skills that share tags, products or a category with Behavior MCP: Cesium Quickstart (gaopengbin/cesium-mcp, 140 stars), Scenario Orbit Views (scenario-labs/skills, 898 stars), MCP Server Builder (anthropics/skills, 180k stars) and MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Behavior MCP?

putervision (a GitHub organization) maintains it in putervision/state-memory-mcp, which has 111 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 3, 2026.

Source: putervision/state-memory-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.