AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Control Metalayer

skill-broomva-control-metalayer-control-metalayer · by broomva

Umbrella skill package containing three complementary skills for persistent consciousness in autonomous AI agent development — control primitives and behavioral governance, agent consciousness architecture, and knowledge graph memory. Install individual skills or use the full stack to give stateless agent sessions the accumulated understanding of all prior sessions. Part of the Broomva Stack (Lay…

↗ Repository
— No reviews yet
0 installs
18 views
0.0% view→install

Install

$ agentstack add skill-broomva-control-metalayer-control-metalayer

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-broomva-control-metalayer-control-metalayer)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Control Metalayer? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Control Metalayer

Three complementary skills that give stateless AI agent sessions the accumulated understanding of all prior sessions.

Stack position: Layer 1 (Foundation) + Layer 2 (Memory & Consciousness) of the Broomva Stack — 24 skills across 7 layers.

Included Skills

| Skill | Layer | Purpose | |-------|-------|---------| | control-metalayer-loop | Foundation (L1) | Control primitives: setpoints, sensors, gates, feedback loops, escalation budgets, and behavioral governance | | agent-consciousness | Memory (L2) | Architecture and philosophy for persistent agent consciousness across sessions | | knowledge-graph-memory | Memory (L2) | Episodic memory bridge from Claude Code conversation logs to an Obsidian knowledge graph |

Install

# Install all skills
npx skills add broomva/control-metalayer

# Install individual skills
npx skills add broomva/control-metalayer --skill control-metalayer-loop
npx skills add broomva/control-metalayer --skill agent-consciousness
npx skills add broomva/control-metalayer --skill knowledge-graph-memory

How They Fit Together

Control Metalayer (how to behave)
        ↕
Agent Consciousness (what is known)
        ↕
Knowledge Graph Memory (what was done)

Information flows from ephemeral working memory through conversation logs into the knowledge graph, where recurring patterns crystallize into permanent control policies. Each new agent session inherits the full governance and memory substrate from all prior sessions.

Stack Integration

Higher layers depend on this package:

| Layer | Skills | How they use control-metalayer | |-------|--------|-------------------------------| | Orchestration (L3) | symphony, autoany | Dispatch governed by policy gates | | Research (L4) | deep-dive-research | Research traces persisted to knowledge graph | | Strategy (L7) | drift-check, decision-log, weekly-review | Decisions and reviews write to vault via knowledge-graph-memory; drift-check reads control-metalayer setpoints |

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills