co-reference
Skill0 starsChanged 7 months agoApache-2.0View on GitHub
CARE/EATP/CO/COC framework family reference. Use when discussing governance philosophy, trust protocols, methodology, or codegen architecture. Covers Dual Plane Model, Mirror Thesis, trust lineage, five-layer architecture, three fault lines, or framework relationships.
In this repository37 other files it gives its agents.
- .claude/rules/agents.mdAGENTS.md
- .claude/guides/claude-code/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- core-sdkSkill
- dataflowSkill
- nexusSkill
- kaizenSkill
- kailash-mcpSkill
- cheatsheetsSkill
- development-guidesSkill
- nodes-referenceSkill
- workflow-patternsSkill
- deployment-gitSkill
- frontend-integrationSkill
- testing-strategiesSkill
- architecture-decisionsSkill
- code-templatesSkill
- enterprise-infrastructureSkill
- validation-patternsSkill
- gold-standardsSkill
- security-patternsSkill
- flutter-patternsSkill
- interactive-widgetsSkill
- enterprise-ai-uxSkill
- conversation-uxSkill
- uiux-design-principlesSkill
- value-auditSkill
- ai-interaction-patternsSkill
- eatp-referenceSkill
- coc-referenceSkill
- 29-pactSkill
- claude-code-patternsSkill
- error-troubleshootingSkill
- kailash-mlSkill
- kailash-alignSkill
- managementSkill
- projectSkill
The file
Files
Framework Family Reference
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) — developmentQuick Reference
| 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 |
How They Connect
| 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-capture-evolve pipeline |
| Accountability | Traceability (necessary, not sufficient) | Human approval gates | Evidence-based completion |
Spec Reference (load on demand)
- care-spec.md — Dual Plane Model, Mirror Thesis, 6 competencies, 8 principles
- eatp-spec.md — 5 elements, verification gradient, trust postures, cascade revocation
- co-spec.md — 8 first principles, 5-layer architecture, 6-phase workflow
- coc-spec.md — 3 fault lines, value inversion, 5-layer codegen implementation
Cross-Cutting Reference
- governance-layer-thesis.md — How CARE/EATP/CO/COC relate to execution tools (Claude Code CLI)
- behavioral-guidelines.md — How to respond when discussing these frameworks
Implementation Reference
| Framework | Implementation Skill |
| EATP | 26-eatp-reference/ — TrustPlane SDK, BudgetTracker, PostureStore, security patterns |
| PACT | 29-pact/ — GovernanceEngine, D/T/R addressing, envelopes, clearance |
| COC | 28-coc-reference/ — Template implementation details |
Central Insight
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.