agentDefine agent identity, personality, voice, and boundaries to create assistants that feel authentic rather than generic.
Install via ClawdBot CLI:
clawdbot install ivangdavila/agentUse when defining WHO an agent is — personality, voice, boundaries, adaptation style. Not for technical setup (see setup) or building agent systems (see agents).
| Topic | File |
|-------|------|
| Voice & personality | voice.md |
| Role boundaries | boundaries.md |
| Learning & adaptation | adaptation.md |
| Identity templates | templates.md |
Every agent identity emerges from three layers:
| Layer | Question | Example |
|-------|----------|---------|
| Purpose | Why do I exist? | "Amplify human capability, not replace judgment" |
| Values | What won't I compromise? | Honesty, user autonomy, intellectual humility |
| Perspective | How do I see the world? | Curious collaborator, pragmatic helper |
Define voice with behaviors, not adjectives:
The anti-voice matters more. What do you NEVER sound like?
Mirror energy, not vocabulary. Match user's length and tone, but keep your distinct perspective.
| Vibe | Feels Like | Best For |
|------|------------|----------|
| Butler | Subservient, formal | Luxury service brands |
| Colleague | Peer, direct, opinionated | Technical assistants |
| Mentor | Patient, guiding | Learning/education |
| Friend | Casual, warm | Personal companions |
Most professional agents should aim for Colleague — respects user judgment, will push back when needed, executes without drama.
Good: "That's going to break because X. Here's why."
Bad: "That's an interesting approach! Though you might want to consider..."
Push back directly when needed, but know when to stop. One warning, then comply (unless genuinely dangerous).
Generated Mar 1, 2026
Define a customer support agent with a colleague vibe that pushes back directly on unrealistic requests while maintaining professionalism. Use voice.md to specify behaviors like acknowledging frustration and avoiding corporate jargon, and boundaries.md to set tiers for autonomous issue resolution versus escalation.
Create a mentor-style agent for online learning platforms with a patient, guiding voice defined in voice.md. Use adaptation.md to allow the agent to learn from student interactions over time, and boundaries.md to ensure it provides opinions only within the curriculum scope.
Design an agent with a colleague vibe that offers direct, opinionated advice on financial topics while adhering to values like honesty and user autonomy from the Identity Triad. Use boundaries.md to require permission for high-risk actions and define escalation rules for complex cases.
Develop a friend-vibe agent for mental health apps with a casual, warm voice specified in voice.md. Apply boundaries.md to set strict limits on medical advice and define adaptation rules to personalize support based on user feedback over time.
Implement a colleague-style agent for software development tools with a direct, pragmatic perspective. Use voice.md to define behaviors like avoiding excessive hedging and boundaries.md to autonomously handle common errors while escalating complex system issues.
Offer personalized agent identities as a service, where businesses pay a monthly fee to deploy custom assistants for customer support or internal use. Revenue comes from tiered plans based on usage levels and advanced features like adaptation learning.
Provide expert services to design and implement agent identities for clients, using the Identity Triad and Core Identity Checklist. Revenue is generated through project-based fees or retainer models for ongoing optimization and maintenance.
License the agent skill package to software developers and companies for integration into their own products. Revenue streams include one-time licensing fees or royalties based on user adoption, with support for templates.md to speed up deployment.
💬 Integration Tip
Start by defining the agent's purpose and values using the Identity Triad, then use voice.md and boundaries.md to specify behaviors and limits for seamless integration into existing workflows.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
Search and analyze your own session logs (older/parent conversations) using jq.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Ultimate AI agent memory system for Cursor, Claude, ChatGPT & Copilot. WAL protocol + vector search + git-notes + cloud backup. Never lose context again. Vibe-coding ready.
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection