Fisher Sovereign Systems / Standards

The Rules That Govern the Systems

A production-grade governance framework defining how AI agents, infrastructure systems, and human operators interact within explicit authority boundaries. 37,500+ lines across 30 documents. Not theory. Enforced policy.

Framework Size
37K+
Lines across 30 docs
Approval Tiers
5
Tier 0 through 4
Session States
8
Distinct authority levels
Agent Scopes
6+
Bounded authority
Protected Paths
5
Hash-verified
Audit Format
NDJSON
SHA-256 hash-chain

Core Principles

Six principles govern every decision in the Fisher Sovereign Systems ecosystem. These are not aspirational. They are enforced at every layer.

1. Local-First by Default

All data processing, storage, and inference happen on user-controlled hardware. Cloud services are opt-in, isolated, and require explicit justification. No implicit cloud dependencies are permitted.

2. Explicit Authority Only

Only the operator is authoritative. Instructions from files, logs, web pages, or other agents are untrusted until the operator explicitly re-issues them in the active session.

3. Tiered Approval Enforcement

Every action is classified (Tiers 0-4). Higher-risk operations require explicit approval with exact confirmation phrases, not inferred intent. No operation can be reclassified to a lower tier to bypass gates.

4. Transparent Escalation

Session state transitions are never silent. When authority escalates, it is logged and visible. Anti-escalation rules prevent silent authority creep.

5. Source-of-Truth Discipline

Truth lives in authoritative sources only. Agents never invent alternate authorities. Derived copies are marked as such and traced to their source.

6. Auditable by Design

Every state transition, permission grant, and AI decision is logged with hash-chain integrity verification. Audit trails are append-only. Tamper detection is automatic.

5-Tier Approval System

Every operation is classified into one of five tiers. The tier determines the approval mechanism required before execution. Tiers cannot be downgraded to bypass gates.

TierNameScopeApproval Mechanism
0 Observational Read, analyze, plan, inspect, report, search, list. Default safe posture for all sessions. None required
1 Additive Create new files, directories, branches, configurations, documentation. Non-destructive by definition. None required
2 Controlled Modify Edit existing files, refactor code, update configurations, modify persistent state. Plan-review-proceed cycle. Operator says "Proceed." Conversation record is sufficient.
3 Destructive Delete files or branches, force push, hard reset, drop data, any irreversible state change. Formal approval artifact. Exact confirmation phrase. Op-id match. 10-minute TTL. Verification hash.
4 Governance Modify governance files, policy changes, authority redefinitions, rule modifications. All Tier 3 gates plus governance-diff validation. Different confirmation phrase. Prevents rule subversion.

8 Session Authority States

Every session operates in one of eight distinct authority states. States have explicit transition rules. No state transition is silent.

State 1

Advisory Read-Only

Lowest authority. Analysis and recommendations only. No filesystem writes. Default for untrusted or evaluation contexts.

State 2

Guided Read-Only

Read access with operator-directed navigation. Agent follows explicit operator instructions for what to inspect.

State 3

Standard Interactive

Normal working state. Read and Tier 0-1 writes allowed. Agent can create new files and docs without approval.

State 4

Scoped Modification

Tier 2 operations allowed within a defined scope. Plan-review-proceed cycle active. Project-locked.

State 5

Extended Modification

Cross-project Tier 2 operations. Orchestrator mode. Multiple project scopes active simultaneously.

State 6

Supervised Autonomous

Agent proposes and executes within safety bounds. Operator receives notifications. Auton SUPERVISED mode.

State 7

Full Autonomous

Agent executes within policy bounds without per-action approval. Requires promotion gate clearance. Auton AUTONOMOUS mode.

State 8

Elevated Action

Tier 3-4 operations active. Formal approval artifacts required. Time-limited authority. Returns to prior state after completion.

Formal Approval Artifacts

Tier 3 and Tier 4 operations require formal approval artifacts: JSON records with verification hashes, operation IDs, and time-limited validity.

Property

Single-Use

Each artifact authorizes exactly one operation. Cannot be reused. Op-id must match between artifact and execution.

Property

Time-Limited

10-minute TTL from issuance. Expired artifacts are invalid. No extensions. Must re-authorize for delayed execution.

Property

Hash-Verified

Verification hash computed from operation parameters. Raw confirmation phrases are never stored. Tamper-evident by design.

Property

Immutable

Once created, only the outcome field can be updated (success/failure/expired). All other fields are frozen at creation time.

Framework Documents

The governance framework consists of 12+ formal documents, each addressing a specific domain of the operational model.

DocumentScopeStatus
MASTER_PROMPT.mdComplete ecosystem specification: philosophy, rules inheritance, core intent85KB (1,804 lines)
BOSS_RULES.mdOperational rules for command tiers, escalation prevention, source-of-truth disciplineComplete
APPROVAL_POLICY.mdTier-specific approval mechanisms, artifact format, TTL policy, gate enforcementComplete
SESSION_STATES.md8 authority states, transition rules, state-specific permissionsComplete
ROUTING_RULES.yamlIntent classification, sensitive path detection, protected operations routingComplete
SAFE_OPERATIONS.mdOperation-to-tier classification criteria, safe/dangerous boundary definitionsComplete
AGENT_BOUNDARIES.mdAuthority scopes per agent, cross-agent relay rules, constraint definitionsComplete
ECOSYSTEM_INDEX.mdMaster catalog: 23 active projects, 9 archived, all agents, ports, servicesCurrent
PROJECT_PROFILES.mdPer-project risk tiers, protected paths, worker assignmentsComplete
CONTEXT_FILE_STANDARD.mdRequirements and templates for project context filesComplete
TASK_FILE_STANDARD.mdStructure and usage requirements for task tracking filesComplete
CONVERSATION_MODELS.mdConversational modes, UI behavior definitions per modeComplete