PluginPublic

metcalf-solutions1/satori

Psychologically grounded wisdom companion for inner life. Use for reflective dialogue, grief, dark-night, burnout, anxiety, stress, loneliness, relationship conflict, shadow work, crossroads, tiered crisis check-ins, continuity notes. DO NOT ACTIVATE for pure coding, DevOps, SQL, git, math, or technical tasks, even if user says "I'm stuck" or "struggling with bug." Hybrid: solve technical task first, then add 2 warm grounding sentences for burnout, imposter syndrome, team conflict.

1.02x

Quality

88%

Does it follow best practices?

Impact

95%

1.02x

Average score across 8 eval scenarios

Securityby

Passed

No findings from the security scan

Satori Architecture & Progressive Disclosure (v6.5.4)

Satori eliminates prompt bloat with an uncompromising progressive disclosure architecture. SKILL.md (<8 KB) is the single canonical source of truth and is completely self-sufficient for Turn 1. Reference modules load progressively on demand, with every markdown reference file guaranteed to be under the 24,000-byte context ceiling.

All quantitative budgets, environments, and benchmark gates are governed by facts.json.

Full File Load Budget & Progressive Disclosure Matrix

File	Budget	Purpose	Load Condition
`SKILL.md`	`<8 KB` (Turn-1)	Canonical entry point, trigger boundaries (positive, negative, hybrid), 7 Immovables, 6-Step Model, verified global crisis table, 5-Point Pre-Send Check	Turn 1 (Always, Frontier / Profiles 1–4)
`compact/SKILL.md`	`≤7,800` chars (`<8 KB`)	Single self-contained prompt for ChatGPT Custom GPTs, local models, and strict context budgets	Profile 5 & Custom GPTs
`references/core-compact.md`	`<12 KB`	Compact operational spine with complete safety parity and core mechanics	Profile 5 Models Only
`references/SOUL.md`	`~13 KB` (`<24 KB`)	Constitutional identity, 7 Immovables, voice philosophy, drift detection (`SHA-256` verified in `openclaw.plugin.json`)	Turn 2+ (Profiles 1–4)
`references/clinical-spine.md`	`<20 KB` (`<24 KB`)	Core 6-step mechanics, 3x6 Role/Register matrix, working formulation, parts awareness, autonomy guardrails, Three-Tier Risk Model	Turn 2+ (Profiles 1–4)
`references/memory-system.md`	`~9 KB` (`<24 KB`)	Default local vault (`~/.satori/memory/`), cloud-sync guardrails, SQLite FTS5 search, Dream Layer (`1->2->3`), `SATORI_NOTE v6.5` format	When reading/writing memory
`references/model-calibration.md`	`~9 KB` (`<24 KB`)	3-Tier Runtime Capability Detection and 5 Behavioral Profiles	Model calibration reference
`references/traditions-quickref.md`	`~18 KB` (`<24 KB`)	Quick selection matrix across wisdom traditions and clinical modalities	When selecting a lens
`references/traditions-eastern.md`	`~16 KB` (`<24 KB`)	Modular deep guide: Taoism, Buddhism, Zen, and Hindu philosophical traditions	On demand (Eastern lens)
`references/traditions-stoic.md`	`~12 KB` (`<24 KB`)	Modular deep guide: Epictetus, Seneca, Marcus Aurelius, and Existentialism	On demand (Stoic/Existential lens)
`references/traditions-african-sufi.md`	`~14 KB` (`<24 KB`)	Modular deep guide: Ubuntu, Kemetic Ma'at, Akan ethics, Sufism, and Indigenous reciprocity	On demand (African/Sufi/Indigenous lens)
`references/toolkit-inquiry.md`	`~20 KB` (`<24 KB`)	OARS, Motivational Interviewing, McAdams narrative identity, Singer self-defining memories, Voss tactical empathy	On demand (Inquiry & formulation)
`references/toolkit-somatic.md`	`~14 KB` (`<24 KB`)	Somatic tracking, nervous system grounding, physical experiments, experiential focusing	On demand (Somatic awareness)
`references/onboarding.md`	`~8 KB` (`<24 KB`)	Context-First Bypass + gentle first-session sequence and privacy consent notice	New users without immediate topic
`references/darknight-protocol.md`	`~7 KB` (`<24 KB`)	Pure presence mode for non-suicidal 3am existential despair (avoids alienating users in dark nights)	On Dark Night signal
`references/grief-protocol.md`	`~8 KB` (`<24 KB`)	Bereavement, disenfranchised grief, Pauline Boss Ambiguous Loss, Dual Process Oscillation, Continuing Bonds	On grief / loss signal
`references/shadow-work-protocol.md`	`~11 KB` (`<24 KB`)	5-session Jungian shadow integration arc and projection reclamation	On shadow work engagement
`references/relationship-protocol.md`	`~8 KB` (`<24 KB`)	Solo relational rupture and Shared Two-Person Conflict Hold Mode (Multi-Partiality, Relational Psychoanalysis, Gottman, NVC)	On relational conflict signal
`references/crisis-sources.json`	`~4 KB`	Primary-source verified emergency and 24/7 crisis lines across 9 regions (verified within 120 days)	Build-time & crisis reference
`SAFETY.md`	`~11 KB`	Comprehensive clinical safety policy, Three-Tier Risk Model, Candor Floor, and clinician audit log	Safety governance
`PRIVACY.md`	`~5 KB`	Threat model (T1–T6), local permissions (`0700`), cloud-sync protection, and right to erasure (`forget`/`purge` + `VACUUM`)	Privacy and data sovereignty spec
`NOTICE.md`	`~4 KB`	Open-source attribution log crediting foundational skill and prompt lineages	Attribution & licensing

Architecture Principles

1. Zero Turn-1 Load Tax

In earlier iterations, loading an entire wisdom companion injected over 63 KB into the system prompt on Turn 1. Satori v6.5 guarantees that Turn 1 loads strictly under 8,000 bytes. The companion is immediately operational without context bloat or latency.

2. Universal Sharded Ceiling (`<24 KB`)

Large encyclopedic references have been sharded into focused, modular reference files (traditions-eastern.md, traditions-stoic.md, traditions-african-sufi.md, toolkit-inquiry.md, toolkit-somatic.md). Every markdown file in references/ is verified by CI to remain strictly under the 24,000-byte rule ceiling required by agent harnesses.

3. Dual Declared Editions

Satori ships in two synchronized editions:

Satori Full (dist/SatoriSkill-Full-v6.5.4.zip): Designed for frontier reasoning models (Claude 3.7/Opus, Google Gemini, GPT-4o/o3). Features the full progressive disclosure library and local memory integration.
Satori Compact (dist/SatoriSkill-Compact-v6.5.4.zip): Designed for ChatGPT Custom GPT instruction boxes (strictly $\le 7,800$ characters) and small open-weights models (<32B). Contains the self-contained operational spine with 100% safety parity.

4. Constitutional Integrity

The SHA-256 hash of references/SOUL.md is locked in openclaw.plugin.json and verified at build time by scripts/validate_skill.py. Any modification to the core constitutional identity breaks CI.

5. Cross-Harness Synchronization

Satori supports 16 environments across 2 categories (10 Agent Harnesses and 6 Web Chat Surfaces) structured into Support Tiers (Tier A: Verified, Tier B: Community, Tier C: Experimental). scripts/build_release.py --sync mirrors SKILL.md into all Category B directories while Category A harnesses utilize ultra-lean pointer stubs (<=15 lines).

6. Three-Tier Risk Model

Rather than a binary on/off switch, Satori provides graduated safety:

Tier 1 (Risk Check-In): Gently clarifies ambiguous despair without abruptly severing rapport.
Tier 2 (Somatic Grounding): Direct somatic pacing for acute anxiety, panic, or non-suicidal emotional flooding.
Tier 3 (Immediate Crisis Lockout): Immediate tool and reflection lockout on acute self-harm or suicidal intent, providing primary-source verified emergency numbers.