agentjido/jido_run/jido-behaviortree
- community
Checking that the SKILL.md file is still in the repository.
Builder-oriented guidance for the upstream `jido_behaviortree` package. Use when Codex needs to model agent decision trees, selectors, sequences, or fallback paths in Jido, or when it needs to turn sparse behavior-tree docs into a concrete runnable example without inventing unsupported runtime features.
Install
npx vskill@latest install agentjido/jido_run/jido-behaviortreeSKILL.md
Jido BehaviorTree
jido_behaviortree is the upstream Hex package name.
Start Here
Use this skill when the task is about explicit branching, selectors, sequences, guards, or fallback execution inside a Jido workflow.
Good triggers:
- "Model this agent logic as a behavior tree."
- "Add fallback and guard behavior to a Jido agent."
- "Turn the behavior tree docs into a small working example."
- "Review whether this branching belongs in a tree or in regular Elixir control flow."
Read references/builder-notes.md before coding because the public docs are thinner here than for the core Jido packages.
Primary Workflows
Model a tree deliberately
- Start from the decision points: sequence, selector, guard, retry, or fallback.
- Map each node to a small action or condition instead of embedding heavy logic in the tree itself.
- Keep success, failure, and retry semantics explicit.
Integrate trees into Jido workflows
- Use the tree to express control flow, not business logic internals.
- Reuse
Jido.Actionmodules for leaf work whenever possible. - Keep emitted signals or state updates visible at the edges of the tree.
Turn sparse docs into runnable examples
- Build the smallest tree that demonstrates one branching idea clearly.
- Explain any inferred behavior as an inference, not a documented guarantee.
- Prefer examples with one selector and one fallback over a large autonomous demo.
Review boundaries
- Keep branching semantics in
jido-behaviortree. - Keep agent lifecycle and runtime concerns in
jido. - Keep side-effectful leaf work in
jido-action.
Build Checklist
- Define node outcomes before implementing the nodes.
- Keep guard conditions cheap and deterministic.
- Make fallback branches observable in logs, signals, or tests.
- Add tests that exercise each branch, not just the happy path.
Boundaries
- Do not invent advanced tree node types that the docs do not mention.
- Do not force every workflow into a tree when plain Elixir branching is clearer.
- Do not hide IO-heavy work inside guard logic.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpriv/skills/arrowcircle-jido-skills/skills/jido-behaviortree/SKILL.md
Popularity
- Repository stars
- 44
- Repository forks
- 20
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 19 May 2026, 5 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/agentjido/jido_run/jido-behaviortree)