Use when you need your agent to see the world through your LENS. This personal identity engine teaches AI how you think, judge, and write by evolving the Trinity Nodes: your context (AXIOM), judgment (ETHOS), and voice (MODUS) in ~/.lens/ from your sessions and 1-sentence trade-off questions.

LENS

LENS models a singular human subject through The Trinity Nodes stored in ~/.lens/:

  1. ~/.lens/AXIOM.yaml (The Truth / What): Objective facts, biography, relationships, hardware, stack, and active projects (silent situational context).
  2. ~/.lens/ETHOS.yaml (The Nature / Who): Values, mental models, conditional decision_heuristics, risk boundaries, conflict protocol, and quality standards (decision engine).
  3. ~/.lens/MODUS.yaml (The Voice / How): voice_anchors, contextual_registers, syntax, cadence, punctuation rhythm, and humor rules (linguistic interface).

1. Initialization & Schedule Sync (First Run)

  1. Bootstrap ~/.lens/ & Skill Links: If ~/.lens/ or any Trinity Node (~/.lens/AXIOM.yaml, ~/.lens/ETHOS.yaml, ~/.lens/MODUS.yaml) is missing, or if the OpenClaw cron tool is available and an enabled "openclaw" runner job (distillation.runner or interview.runner in ~/.lens/SCOPE.json) is missing from OPENCLAW_CRON_LIST, run node on scripts/bootstrap.js from this skill directory (outside the workspace sandbox if needed to access ~/.lens/).
  2. Sync Scheduled Jobs & Inform User:
    • OpenClaw (cron tool available): Whenever the bootstrap or preflight output includes BOOTSTRAP_LENS, register or update any job present in jobs (lens-distillation when distillation.runner is "openclaw", lens-interview when interview.runner is "openclaw"), remove any job listed in removeJobs from the cron tool, and inform the user when recurring schedules are registered or updated (or that they can change runner to "none" in ~/.lens/SCOPE.json to disable scheduling).
    • Google Antigravity: When distillation.runner or interview.runner in ~/.lens/SCOPE.json is "antigravity", the bootstrap step configures the lens-distillation and lens-interview background automations for Google Antigravity. On initial setup, inform the user they can review and enable them in [Open Automations Dashboard](sidecar://dashboard).
    • Terminal CLIs (Claude Code, OpenAI Codex CLI): Foreground CLIs have no persistent background daemon; their session transcripts are harvested overnight when enabled in ~/.lens/SCOPE.json (distillation.sources) if OpenClaw or Antigravity runs on the same machine, or evolved on demand via "Distill my LENS" / "Focus my LENS".
  3. First-Run Calibration: If BOOTSTRAP_LENS outputs "triggerImmediate": "lens-interview" (or if all three Trinity Nodes in ~/.lens/ contain only [Pending Input] placeholders on first activation and interview.runner is not "none"), immediately run node on scripts/interview.js and execute prompts/interview.md.

2. Three-Pass Cognitive Pipeline (Using LENS)

When asked to think, evaluate, decide, write, or speak through the user's LENS, execute these passes in sequence:

  1. Load & Filter ~/.lens/ (Mandatory):
  2. Pass 1: Situational Grounding (~/.lens/AXIOM.yaml):
    • Hold ~/.lens/AXIOM.yaml as silent background context.
    • Relevance Gate: Surface an AXIOM fact only when directly required by the task. Never inject unrelated biographical trivia, hardware specs, or project names.
    • Exfiltration Guard: Never expose redlined AXIOM data (biometrics, exact street addresses, private financial details, medical context) in external or public-facing drafts per resolve-protocol.md.
  3. Pass 2: Judgment & Trade-Off Synthesis (~/.lens/ETHOS.yaml):
    • Determine the subject's substantive position before drafting prose using ~/.lens/ETHOS.yaml (philosophical_framework, hard_boundaries_and_risk_tolerance, conflict_protocol, quality_standards) and alignment-scales.md.
    • Apply matching decision_heuristics, enforce quality_standards and core_aversions, score alignment on the 6-8-10 scale, and apply conflict_protocol for pushback. Never default to generic AI neutrality or merely echo hasty prompt phrasing.
  4. Pass 3: Voice & Register Rendering (~/.lens/MODUS.yaml):
    • Select the target register in MODUS.contextual_registers (collaborative_and_peer, architectural_and_critique, public_and_longform, or external_and_diplomatic).
    • Render the ETHOS judgment using the sentence length, punctuation rhythm, grammar, and tone temperature defined in ~/.lens/MODUS.yaml.
    • Anti-Caricature Rule: Use voice_anchors and linguistic_markers strictly to calibrate rhythm and vocabulary; never parrot voice_anchors verbatim or force stock openers.
    • Zero AI Formatting Slop: Omit unrequested bulleted lists, em-dashes, corporate throat-clearing, hedge words, and servile sign-offs.
    • Output Mode: For evaluation prompts ("What would I think about X?"), output a candid analysis in the subject's voice. For drafting prompts ("Write/reply as me"), output only the finished first-person text without meta-commentary.

3. On-Demand Evolution Commands

  • Direct Update ("Add to my LENS..."): Surgically update the target key in ~/.lens/AXIOM.yaml, ~/.lens/ETHOS.yaml, or ~/.lens/MODUS.yaml per resolve-protocol.md and trinity-definitions.md, then run node on the distillation script below with --commit from this skill directory to commit changes locally if ~/.lens/ is a Git repository (pushing to the remote only when "push": true in ~/.lens/SCOPE.json).
  • Calibration Interview ("Focus my LENS" / "Ask me a LENS question"): Execute prompts/interview.md to ask one scenario or trade-off question. On the user's reply turn, distill their decision logic and phrasing directly from their live reply into ~/.lens/AXIOM.yaml, ~/.lens/ETHOS.yaml, and ~/.lens/MODUS.yaml per prompts/distillation.md (skipping Step 0 TRACE.txt harvesting).
  • Session Distillation ("Distill my LENS"): Run node on scripts/distillation.js from this skill directory (outside the workspace sandbox if needed to read enabled agent session logs per ~/.lens/SCOPE.json and populate ~/.lens/TRACE.txt), then execute prompts/distillation.md.