メニュー
CARE/EATP/CO/COC reference — governance, trust protocols, Dual Plane, Mirror Thesis.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Claude Code architecture — artifact design, context, agentic patterns. For CC audit/build.
Conformance Walk — freeze-then-judge on the source→delivered→live axis: one cw_core + Source/Delivered/Live adapter families, coverage vs pass-rate, discrete verdicts. Use for any testable surface.
Kailash security (Python) — validation, secrets, injection, authn/z. Hardcoded secrets BLOCKED.
/onboard procedure: read roster + team-memory + posture + claims + codify lease + rules-changed for a new operator joining a multi-operator COC repo.
/certify procedure: brief → probe → gate at 100%; loops failed questions until pass. NO Claude-assistance during gate phase. Curated bank, not LLM-generated.
/ecosystem-init procedure — write the D6 ecosystem-config, run the disclosure scan before write, establish genesis via runEnrollmentCeremony, scaffold non-Kailash STACK.md.
| name | co-reference |
| description | CARE/EATP/CO/COC reference — governance, trust protocols, Dual Plane, Mirror Thesis. |
| allowed-tools | ["Read","Glob","Grep"] |
The Terrene Foundation's governance and methodology stack:
CARE (Philosophy: What is the human for?)
├── EATP (Protocol: How do we keep the human accountable?)
└── CO (Methodology: How does the human structure AI's work?)
├── COC (Codegen) — production
├── COR (Research) — production
├── COG (Governance) — production
├── COE (Education) — analysis
├── COComp (Compliance) — sketch
└── COL (Learners) — development
| Framework | What It Is | Core Contribution |
|---|---|---|
| CARE | Governance philosophy | Dual Plane Model, Mirror Thesis, 6 human competencies, 8 principles |
| EATP | Trust verification protocol | 5 elements (genesis→delegation→constraint→attestation→audit), verification gradient, trust postures |
| CO | Domain-agnostic methodology | 8 first principles, 5-layer architecture, 6-phase workflow |
| COC | CO for codegen | 3 fault lines (amnesia, convention drift, security blindness), value inversion, autonomous execution |
| CARE Concept | EATP Operationalization | CO Manifestation | COC Implementation |
|---|---|---|---|
| Trust Plane | Genesis + Delegation Records | Layer 2 (Context) + Layer 3 (Guardrails) | Rules + CLAUDE.md |
| Execution Plane | Constraint Envelopes | Layer 1 (Intent agents) | Agents + Skills |
| Human-on-the-Loop | Trust Postures + Verification Gradient | Layer 4 (Instructions) | 7-phase workflow + quality gates |
| Evolutionary Trust | Audit Anchors | Layer 5 (Learning) | Observe-digest-codify pipeline |
| Accountability | Traceability (necessary, not sufficient) | Human approval gates | Evidence-based completion |
| Framework | Implementation Skill |
|---|---|
| EATP | 26-eatp-reference/ — TrustPlane SDK, BudgetTracker, PostureStore, security patterns |
| PACT | 29-pact/ — GovernanceEngine, D/T/R addressing, envelopes, clearance |
Trust is human. Execution is shared. The system reveals what only humans can provide.
Raw model capability is becoming a commodity. Institutional knowledge — the context, guardrails, and methodology surrounding the model — is the differentiator.