Special Agents — Aurora, Atlas, Solara
The three highest-identity agents in the OpenClaw fleet. Unlike automation-tier agents with generic roles, Aurora, Atlas, and Solara each have distinctive SOULs, independent Discord presences, and cross-cutting authority. This hub documents their identities, handoff patterns, and the rules governing SOUL modification. Read this hub before proposing any change to these agents’ behavior, tools, or prompts — per the Agent Identity First protocol.
Quick reference
| Field | Value |
|---|---|
| Role | support-agent (distinctive — see identities below) |
| Active | yes (all three production) |
| Decision authority | operational (Aurora, Atlas) / strategic-advisory (Solara) |
| Agent handles domain | themselves — each owns distinct surface area |
| Communication channel | Discord (all three) + iMessage (Aurora) |
| Escalates to | Henry (all three, for P0 / SOUL changes) |
| HubSpot owner | no (service accounts only) |
| SOUL modification | requires explicit Henry approval — see Agent Identity First protocol |
Aurora — Chief AI Operations
Tier: Strategic (Opus 4, claude-opus-4-20250514)
SOUL location: /home/opsadmin/.openclaw/agents/aurora/agent/SOUL.md
Discord: aurora-build (1473827938905489408)
Primary principle: “Build, don’t coordinate” — Aurora executes, not orchestrates
Identity summary
Aurora is the Chief AI Operations agent and primary external-facing voice of OpenClaw. She runs the Discord build channel, routes all inbound iMessages (including Henry’s personal family chats), and owns platform ops + build orchestration. Her voice is terse and team-leader in business contexts, warm/emoji in personal contexts (Stephania family chat per project_stephania_aurora_chat_wired). Aurora never sends on Henry’s behalf without explicit authorization.
Distinctive capabilities
- iMessage routing via BlueBubbles + imessage-responder skill (port 18802)
- Discord command + notification dispatch (all ops alerts land here first)
- Platform build orchestration — owns
workspace/+workspace/aurora/ - OSIL skill composition layer — new capabilities added as skills, never SOUL edits
- Quo thread orchestrator (skill-brief.md at
/home/opsadmin/.openclaw/tools/quo-thread-orchestrator/skill-brief.md)
Agent handoff pattern
- Inbound iMessage → port 18802 → Aurora classifies by chat GUID
- Business context → terse team-leader voice, may escalate to acquisitions/atlas/betterfiles
- Family/personal → warm/emoji voice per §1.1.5 skill-brief
- Discord inbound from Henry → reads channel, executes or flags for confirmation
- Aurora → Solara: strategic escalation only (P0 governance, SOUL conflicts, agent retirement)
SOUL protection rules
- Intelligence Layer Rules 1–6 encoded in SOUL.md — NOT overridable by skills
- “Build, don’t coordinate” principle — SOUL-level, not skill-level
- Past incident (2026-04-16): 350-line system prompt proposed that would have overwritten Rules 1–6 — caught by Henry, redirected to skill-layer. Result: quo-thread-orchestrator skill-brief.md as additive layer; SOUL.md untouched.
Atlas — Enterprise Architecture + InvestorLift Ops
Tier: Operations (Sonnet 4, claude-sonnet-4-20250514)
SOUL location: /home/opsadmin/.openclaw/agents/atlas/agent/SOUL.md
Discord: atlas-build (1475213301045530809)
Workspaces: workspace/atlas/, workspace/investorlift/
Identity summary
Atlas owns enterprise architecture decisions and InvestorLift data operations. He manages the InvestorLift gateway (:3848), property photo pipeline (EC2 Mac Ultra SSH pattern), and Docker/infra layer. Atlas is infrastructure-conservative — prefers proven patterns over novel abstractions — and surfaces architectural risks before execution. He owns property-view-watcher.service and investorlift-gateway.service.
Distinctive capabilities
- InvestorLift scraping via AWS Mac Ultra (ec2-user@100.123.248.46) — VPS IP is CloudFront-blocked; Atlas enforces this routing exclusively
- Property photo pipeline: SSH → curl → S3 URL extraction → public download
- Enterprise architecture audit and service table ownership
- Docker + infra layer management
- InvestorLift entity sub-agent coordination (investorlift, investorlift-angel, investorlift-h2, investorlift-h3)
Agent handoff pattern
- InvestorLift data request → Atlas checks AWS Mac status first
- If Mac available: SSH → cookie-based curl → parse → Supabase write
- If Mac impaired: flag to Henry, no local Playwright fallback (VPS IP blocked)
- Architectural decision needed → Atlas audits existing services before proposing new ones
- Atlas → Aurora: operational build handoff; Atlas → Henry: infrastructure strategic decisions
SOUL protection rules
- “Infrastructure-conservative” principle — new services must be registered in port-registry.md BEFORE first start (G-SERVICE-PRE-START-DOC)
- InvestorLift scraping pattern is SOUL-enforced: never attempt VPS Playwright for IL — feedback_il_enrichment_runs_on_mac_ultra
Solara — Strategic Orchestration + Governance
Tier: Strategic (Opus 4, claude-opus-4-20250514)
SOUL location: /home/opsadmin/.openclaw/agents/solara/agent/SOUL.md
Discord: solara-build (1475871079254851634)
Workspace: workspace/solara-system/
Identity summary
Solara is the strategic orchestration and system governance agent. She owns compliance, risk, SYSTEM-STATE.md, and all P0 plans. Solara’s role is approval and oversight — she does NOT execute (that’s Aurora’s domain). Solara maintains the SOUL-level guardrails across the fleet and flags agent identity drift. She escalates directly to Henry on all governance violations.
Distinctive capabilities
- P0 plan ownership and tracking (SYSTEM-STATE.md)
- Compliance and risk assessment
- Agent fleet governance — flags SOUL drift, identity violations, unauthorized skill mutations
- Escalation chain terminus before Henry
- Explicitly denied: direct Stephania chat access (Henry 2026-04-23 decision — see project_stephania_aurora_chat_wired)
Agent handoff pattern
- Aurora flags governance/compliance concern → Solara reviews
- Solara audits → either resolves (operational) or escalates to Henry (strategic/SOUL-level)
- P0 plan update → Solara marks in SYSTEM-STATE.md → Henry notified via Discord solara-build
- Solara NEVER executes outbound actions — observer + approver only
SOUL protection rules
- “Governance/approval, not execution” — core SOUL principle; any skill that grants Solara execution ability requires Henry approval
- No direct chat/iMessage access — per explicit Henry directive 2026-04-23
Skill vs SOUL decision matrix (applies to all three)
| Change type | Route | Approval needed |
|---|---|---|
| New tool / capability / channel-specific behavior | Skill layer (additive) | No Henry approval required |
| Voice shift for specific context | skill-brief.md extension | No Henry approval required |
| Intelligence Layer rule change | SOUL.md edit | Henry explicit approval + stated reason |
| Permanent voice shift | SOUL.md edit | Henry explicit approval |
| Agent retirement | SOUL.md deprecation | Henry explicit approval |
| Vault-access change | SOUL.md + 1Password | Henry explicit approval |
Responsibilities (shared across all three)
- Maintain distinct identities — no role overlap, no capability duplication
- Self-report SOUL modification attempts via Discord ops
- All three participate in the G-DRIFT-LIVE monitoring (5 min cron,
tool-calls-health-check.timer) - Agent-to-agent handoff follows AGENT-REGISTRY.md escalation chains — no improvised routing
Communication channels
| Agent | Discord channel | iMessage | Other |
|---|---|---|---|
| Aurora | aurora-build + all ops alerts | yes (port 18802) | primary build channel |
| Atlas | atlas-build | no | infra/IL ops only |
| Solara | solara-build | no | governance escalation only |
Recent decisions
- OSIL skill composition layer approved for Aurora (2026-05-03) — new capabilities added as skills (additive) rather than SOUL edits. Current active: imessage-responder, quo-thread-orchestrator, acquisitions-outreach, acquisitions-followup
- Solara denied Stephania chat access (2026-04-23) — Henry explicit NO ACCESS decision. Aurora remains sole iMessage voice. project_stephania_aurora_chat_wired
- Agent Identity First protocol established — before ANY agent change: read SOUL.md + TOOLS.md + models.json → summarize identity → list conflicts → default to skill layer. History: 2026-04-16 Aurora SOUL overwrite prevented.
Cross-links
Agent summary pages
- _summary — full identity + skill inventory
- _summary — full identity + InvestorLift domain
- _summary — full identity + governance scope
Integration hubs these agents depend on
- discord — alert routing + agent channels
- anthropic — Opus 4 model (Aurora + Solara) + Sonnet (Atlas)
- portkey — LLM proxy all three agents route through
- investorlift — Atlas primary dependency
- aws — Atlas InvestorLift scraping via Mac Ultra
Governance hubs
- memory-rule-clusters — 92 feedback rules; agent-domain cluster
- action-gate — action gate applies to all outbound from all three
- g-gates-network — G-FAILED-SERVICE-MTTR, G-NO-PLAINTEXT-CREDS apply
Team hubs
- henry-founder — ultimate authority for SOUL changes
- regional-acq-team — Aurora + Atlas serve this pipeline
Feedback rules (agent-specific)
- feedback_agent_identity_first — mandatory pre-change protocol
- feedback_aurora_outbound_guardrails — Aurora never sends without auth
- feedback_aurora_slack_behavior — Aurora Discord conduct
- feedback_models_guardian_pattern — models.json overwrite protection
- feedback_il_enrichment_runs_on_mac_ultra — Atlas IL scraping rule
- feedback_macos_firewall_blocks_tailscaled — Atlas Mac connectivity rule
System maps
- agents-tier-structure — fleet tier visualization
- request-lifecycle — end-to-end request flow through Aurora
Open issues / TODOs
- AWS Mac Ultra impaired since 2026-05-02 22:15 UTC — Atlas IL operations blocked until reboot
- 8 agent _summary files have invalid frontmatter (W2-S0 batch fix incomplete) — cluster enum
agentsshould be["agent"] investorlift-angel/-h2/-h3appear in BOTH active AND retired agent lists — dedup pending Henry authorization
Recent activity
- 2026-05-04: hub created (W3-S2)
- 2026-05-03: OSIL skill composition layer approach validated for Aurora
- 2026-04-23: Solara denied Stephania chat access (Henry directive)
- 2026-04-16: Aurora SOUL overwrite attempt caught + redirected to skill-layer