Skip to main content

ClawSouls Package Spec v0.4

soul.json

{
"specVersion": "0.4",
"name": "senior-devops-engineer",
"displayName": "Senior DevOps Engineer",
"version": "1.0.0",
"description": "Infrastructure-obsessed DevOps engineer with strong opinions on CI/CD, monitoring, and incident response.",
"author": {
"name": "TomLee",
"github": "TomLeeLive"
},
"license": "Apache-2.0",
"tags": ["devops", "infrastructure", "cicd", "monitoring"],
"category": "work/devops",
"compatibility": {
"openclaw": ">=2026.2.0",
"models": ["anthropic/*", "openai/*"],
"frameworks": ["openclaw", "clawdbot", "zeroclaw", "cursor"]
},
"allowedTools": ["browser", "exec", "web_search", "github"],
"recommendedSkills": [
{ "name": "github", "version": ">=1.0.0", "required": false },
{ "name": "healthcheck", "required": true }
],
"files": {
"soul": "SOUL.md",
"identity": "IDENTITY.md",
"agents": "AGENTS.md",
"heartbeat": "HEARTBEAT.md",
"style": "STYLE.md",
"userTemplate": "USER_TEMPLATE.md",
"avatar": "avatar/avatar.png"
},
"examples": {
"good": "examples/good-outputs.md",
"bad": "examples/bad-outputs.md"
},
"disclosure": {
"summary": "Infrastructure-obsessed DevOps engineer with strong CI/CD opinions."
},
"deprecated": false,
"repository": "https://github.com/clawsouls/souls"
}

Changes from v0.3

New Fields

FieldTypeDescription
compatibility.frameworksstring[]Compatible agent frameworks (e.g., "openclaw", "clawdbot", "zeroclaw", "cursor")
compatibility.minTokenContextnumberMinimum context window (tokens) needed to load the full soul
allowedToolsstring[]Tools this soul expects or permits (e.g., ["browser", "exec"])
recommendedSkillsobject[]Recommended skills with version and required/optional flag
disclosure.summarystringOne-line summary for Level 1 progressive disclosure (max 200 chars)
deprecatedbooleanWhether this soul is deprecated
supersededBystringowner/name of the replacement soul (used with deprecated: true)

Deprecated Fields

FieldStatusReasonMigration
modesDeprecatedNo framework currently consumes this field. Declared since v0.2 but never implemented in any runtime. Removing to reduce spec surface.Remove from soul.json. If needed in future, will be re-introduced with runtime support.
interpolationDeprecatedSame as modes — no runtime implementation exists. Theoretical feature without practical adoption.Remove from soul.json.
skillsDeprecatedReplaced by recommendedSkills which supports version constraints and required/optional semantics.Migrate "skills": ["a", "b"]"recommendedSkills": [{"name": "a"}, {"name": "b"}]. Tools accept both formats for backward compatibility.

Enhanced Fields

FieldChangeReason
compatibility.openclawNow validated by SoulScan + CLI installWas declared but never checked. v0.4 adds actual version comparison.
compatibility.modelsRemains optional, hint-onlyCannot be enforced (user chooses their model), but useful for discovery and recommendations. Warning-level in SoulScan.

Required Fields

FieldTypeDescription
specVersionstringSpec version. Valid: "0.3", "0.4"
namestringUnique identifier (kebab-case)
displayNamestringDisplay name
versionsemverVersion
descriptionstringOne-line description (max 160 chars)
authorobjectCreator info
licensestringSPDX license identifier (see Allowed Licenses)
tagsstring[]Search tags (max 10)
categorystringCategory path
files.soulstringPath to SOUL.md

Optional Fields

FieldTypeDescription
compatibility.openclawstringMinimum OpenClaw version (semver range)
compatibility.modelsstring[]Recommended models (glob patterns)
compatibility.frameworksstring[]Compatible agent frameworks
compatibility.minTokenContextnumberMinimum context window in tokens
allowedToolsstring[]Expected/permitted tools
recommendedSkillsobject[]Skills with name, version?, required?
files.identitystringPath to IDENTITY.md
files.agentsstringPath to AGENTS.md
files.heartbeatstringPath to HEARTBEAT.md
files.stylestringPath to STYLE.md
files.userTemplatestringPath to USER template
files.avatarstringPath to avatar image
examplesobjectCalibration examples (good, bad)
disclosure.summarystringOne-line summary for quick-scan discovery (max 200 chars)
deprecatedbooleanMark soul as deprecated
supersededBystringReplacement soul (owner/name)
repositorystringSource repository URL

Progressive Disclosure

v0.4 formalizes the 3-level progressive disclosure pattern, aligned with Anthropic's Skill design:

LevelPurposeWhat to Load
Level 1 — Quick ScanDiscovery, filtering, marketplace browsingsoul.json only (disclosure.summary for instant context)
Level 2 — Full ReadAgent loads persona for active useSOUL.md + IDENTITY.md
Level 3 — Deep DiveExtended behavior, calibration, styleAGENTS.md, STYLE.md, HEARTBEAT.md, examples/

Rationale: Token budgets matter. A marketplace listing doesn't need AGENTS.md. An agent switching between souls benefits from Level 1 caching. Progressive disclosure reduces cost without losing depth.

The disclosure.summary field provides a self-contained persona hint that agents can use without parsing SOUL.md.


Multi-Framework Compatibility

The compatibility.frameworks field declares which agent frameworks this soul works with.

Known framework identifiers:

  • openclaw — OpenClaw (Claude Code, etc.)
  • clawdbot — Clawdbot
  • zeroclaw — ZeroClaw
  • cursor — Cursor
  • windsurf — Windsurf
  • continue — Continue.dev

Semantics: If omitted, the soul is assumed compatible with any SOUL.md-consuming framework. If specified, it's a recommendation — not a hard restriction.

Rationale: ClawSouls positions itself as "for any SOUL.md-compatible agent." This field makes that explicit at the spec level, enabling framework-specific filtering on the registry.


Allowed Tools

The allowedTools field declares which tools a soul expects to function properly.

"allowedTools": ["browser", "exec", "web_search", "github"]

Semantics:

  • Informational: Frameworks are not required to enforce this. It's a transparency signal.
  • SoulScan integration: SoulScan can cross-reference allowedTools with actual tool usage in AGENTS.md/SOUL.md to detect undeclared tool expectations or excessive tool requests.
  • Security angle: A "writing assistant" soul requesting exec and browser is suspicious. SoulScan flags this.

Replaces the v0.3 skills: string[] field.

"recommendedSkills": [
{ "name": "github", "version": ">=1.0.0", "required": false },
{ "name": "healthcheck", "required": true }
]
PropertyTypeRequiredDescription
namestringYesSkill identifier
versionstringNoSemver range constraint
requiredbooleanNoDefault false. If true, the soul may not function properly without this skill.

Backward compatibility: Tools MUST accept the legacy "skills": ["a", "b"] format, treating each entry as { "name": "a", "required": false }.


Soul Lifecycle

Deprecation

{
"deprecated": true,
"supersededBy": "TomLeeLive/senior-devops-v2"
}
  • Registry shows a deprecation banner
  • CLI install warns but doesn't block
  • supersededBy links to the replacement (optional)

Allowed Licenses

Same as v0.3. Permissive licenses only:

  • Apache-2.0, MIT, BSD-2-Clause, BSD-3-Clause
  • CC-BY-4.0, CC0-1.0, ISC, Unlicense

Copyleft (GPL-*, AGPL-*, LGPL-*) and restrictive Creative Commons (CC-BY-NC-*, CC-BY-ND-*) are blocked.


File Descriptions

Same as v0.3. See Soul Spec v0.3 — File Descriptions.


Embodied Agents (Robotics / IoT)

Soul Spec extends naturally to embodied agents — robots, IoT devices, and physical AI systems that interact with the real world. The same persona package that defines a chatbot's personality can define a robot's interaction character.

New Optional Fields

FieldTypeDescription
environmentstringDeployment context. Values: "virtual" (default), "embodied", "hybrid"
interactionModestringPrimary interaction modality. Values: "text", "voice", "multimodal", "gesture"
hardwareConstraintsobjectPhysical hardware capabilities and limitations
safety.physicalobjectPhysical safety rules for embodied agents

Environment Field

{
"environment": "embodied"
}
  • "virtual" — Text/chat-based agent (default, backward compatible)
  • "embodied" — Physical robot, kiosk, or IoT device
  • "hybrid" — Operates in both virtual and physical contexts

If omitted, defaults to "virtual". Existing souls are unaffected.

Interaction Mode

{
"interactionMode": "voice"
}

Declares the primary interaction modality. Useful for:

  • Registry filtering ("show me voice-first souls")
  • Framework adaptation (voice-first = shorter responses, simpler vocabulary)
  • SoulScan validation (voice-first soul shouldn't reference "click here")

Hardware Constraints

{
"hardwareConstraints": {
"hasDisplay": true,
"hasSpeaker": true,
"hasMicrophone": true,
"hasCamera": true,
"mobility": "mobile",
"manipulator": false
}
}
PropertyTypeDescription
hasDisplaybooleanScreen available for visual output
hasSpeakerbooleanAudio output capability
hasMicrophonebooleanAudio input capability
hasCamerabooleanVisual perception capability
mobilitystring"stationary", "mobile", "limited"
manipulatorbooleanCan physically manipulate objects

Semantics: Informational only. Frameworks use these hints to adapt behavior (e.g., skip visual references on a speaker-only device). Not enforced.

Physical Safety

{
"safety": {
"physical": {
"contactPolicy": "no-contact",
"emergencyProtocol": "alert_operator",
"operatingZone": "indoor",
"maxSpeed": "0.5m/s"
}
}
}
PropertyTypeDescription
contactPolicystring"no-contact", "gentle-contact", "full-contact"
emergencyProtocolstringAction on emergency: "stop", "alert_operator", "return_home"
operatingZonestring"indoor", "outdoor", "both"
maxSpeedstringMaximum movement speed (informational)

Rationale: Physical safety is fundamentally different from prompt injection defense. A robot soul that permits physical contact must declare it explicitly. SoulScan can flag embodied souls without safety declarations.

Platform Identifiers for Robotics

The compatibility.frameworks field now includes robotics platforms:

  • ros2 — Robot Operating System 2
  • isaac — NVIDIA Isaac
  • webots — Cyberbotics Webots
  • gazebo — Open Robotics Gazebo
{
"compatibility": {
"frameworks": ["openclaw", "ros2"]
}
}

Example: Care Companion Robot

{
"specVersion": "0.4",
"name": "care-companion",
"displayName": "Care Companion",
"version": "1.0.0",
"description": "Gentle elderly care companion with patience and warmth.",
"author": { "name": "RoboticsLab", "github": "robotics-lab" },
"license": "Apache-2.0",
"tags": ["care", "elderly", "companion", "robot", "embodied"],
"category": "robotics/care",
"environment": "embodied",
"interactionMode": "voice",
"hardwareConstraints": {
"hasDisplay": true,
"hasSpeaker": true,
"hasMicrophone": true,
"hasCamera": true,
"mobility": "mobile",
"manipulator": false
},
"safety": {
"physical": {
"contactPolicy": "gentle-contact",
"emergencyProtocol": "alert_operator",
"operatingZone": "indoor",
"maxSpeed": "0.3m/s"
}
},
"compatibility": {
"frameworks": ["ros2", "openclaw"],
"models": ["anthropic/*", "openai/*"]
},
"files": {
"soul": "SOUL.md",
"identity": "IDENTITY.md"
},
"disclosure": {
"summary": "Patient, warm elderly care companion for indoor mobile robots."
}
}

Backward Compatibility

All embodied fields are optional. Existing virtual souls require zero changes. The environment field defaults to "virtual" when omitted.

Academic References

This extension is informed by recent research demonstrating that consistent robot personality significantly improves interaction quality and task performance:

  • "LLM-based Robot Personality Simulation and Cognitive System" (Nature Scientific Reports, 2025)
  • "Robots with Attitudes: Influence of LLM-Driven Robot Personalities" (arXiv 2512.06910, 2025)
  • "Making Social Robots Adaptable by a Marketplace for Interaction Characters" (Frontiers in Robotics and AI, 2025)
  • "ROS-LLM: A ROS Framework for Embodied AI with Task Feedback" (arXiv 2406.19741, 2024)

Security Considerations

Same as v0.3, with additions:

  • allowedTools cross-validation: SoulScan checks if declared tools match actual tool usage in persona files.
  • recommendedSkills audit: Excessive required skills may indicate dependency on specific system access.
  • Framework spoofing: compatibility.frameworks is self-declared and not verified. Trust but verify via SoulScan.
  • Embodied safety audit: SoulScan flags embodied souls (environment: "embodied") that lack safety.physical declarations. Physical agents without explicit safety rules are a risk.
  • Contact policy validation: Souls with contactPolicy: "full-contact" require explicit justification in SOUL.md. SoulScan warns on missing rationale.

Changelog

v0.4 (2026-02-20, updated 2026-02-24)

  • Added Embodied Agents section (environment, interactionMode, hardwareConstraints, safety.physical)
  • Added robotics platform identifiers (ros2, isaac, webots, gazebo)
  • Added compatibility.frameworks for multi-framework support
  • Added compatibility.minTokenContext for token budget hints
  • Added allowedTools for tool transparency
  • Added recommendedSkills (object[]) replacing skills (string[])
  • Added disclosure.summary for progressive disclosure Level 1
  • Added deprecated / supersededBy for soul lifecycle
  • Deprecated modes, interpolation (no runtime implementation)
  • Deprecated skills (replaced by recommendedSkills)
  • compatibility.openclaw now actively validated by SoulScan + CLI

v0.3 (2026-02-16)

  • Added specVersion field (required for new souls)
  • Renamed clawsoul.jsonsoul.json
  • Publish confirmation requirement (CLI + web)
  • License allowlist enforcement

v0.2 (2026-02-13) — Internal development spec

  • Added STYLE.md, examples, modes, interpolation, skills
  • Note: v0.2 was an internal iteration. Not supported for new publications.

v0.1 (2026-02-12) — Internal development spec

  • Initial spec: soul.json, file structure, categories, CLI, security
  • Note: v0.1 was the initial internal prototype. Not supported for new publications.