total-recall-brain 3.33.1 → 3.34.0

package/scaffold/.agent/skills/decision/references/integration.md

@@ -0,0 +1,25 @@
+# Decision integration
+
+Verified against primary documentation on 2026-10-01. Recheck alpha API contracts before implementation.
+
+## Discover and configure
+
+Use the installed decision plugin's manifest/help to discover supported commands. Its skill is the same `decision` capability; do not install an additional Jev skill. Plugin presence or documentation alone does not prove live dispatch or persistence. Validate the adapter before relying on it.
+
+Reuse the repository's credential and provider configuration. Prefer schema-validated portable defaults and repo-owned config/overlays. Use the existing layered skill contract where supported: plugin-owned `core/config.schema.json`, canonical repo-owned SSSS `skill_config`, disposable `config.json` projection. Do not invent those interfaces where no consumer exists. No personal paths/hosts, credentials or injected memory belong in shipped defaults.
+
+## Jev boundary
+
+OpenRouter documents `POST /api/alpha/decisions` for plain HTTP/OpenRouter SDK calls and `POST /api/v1/systemone` for the TypeSafe SDK format. Confirm the chosen surface's request schema; do not interchange formats blindly. Select the model in configuration and record the actual response version. The separate Jev Router selects chat models/reasoning effort; it does not implement skill selection.
+
+Use Choice for a bounded label set, Noul for probability of yes and Score for an ordered probability-weighted result. Choice and Score expose distributions and confidence; Noul does not expose a separate confidence value. Validate finite ranges, membership and required answer fields; missing confidence never becomes 1. A weighted Score is not a discrete level. Pin the actual adapter contract and fixture responses before wiring gates.
+
+## OpenAI Decisions preview
+
+OpenAI announced a Luna-powered Decisions API on 2026-09-29 for finite predefined answers from text or image context. It is in limited preview; the public endpoint, schema and this account's access are unverified. OpenRouter's `/api/alpha/decisions` currently documents Jev, and its public model catalog did not list OpenAI Decisions on 2026-10-01. Keep OpenAI as a configurable future engine in this one `decision` skill, without guessing a model slug or sending requests through the Jev endpoint. Use the deterministic path until the official contract and actual access are verified. [OpenAI announcement](https://openai.com/index/devday-2026-recap/) · [OpenRouter Jev contract](https://openrouter.ai/docs/guides/community/jev).
+
+## Evidence and fallback
+
+Tune gates with representative labelled cases, including ambiguous input, no matching option, label wording changes and incomplete state. Report false selections, missed selections, abstention, latency and cost. Typed validity does not establish semantic accuracy. Cache by task, catalog/content hashes and configuration/model version; invalidate on relevant changes. Network/configuration/parse failures preserve the deterministic path. Avoid unneeded outbound private data; log no secrets.
+
+Sources: [OpenRouter Jev guide](https://openrouter.ai/docs/guides/community/jev), [TypeSafe confidence](https://docs.typesafe.ai/confidence), [Choice](https://docs.typesafe.ai/primitives/choice), [Score](https://docs.typesafe.ai/primitives/score), [Noul](https://docs.typesafe.ai/primitives/noul).

package/scaffold/.agent/skills/decision/references/use-cases.md

@@ -0,0 +1,20 @@
+# Decision use cases
+
+Primary docs checked 2026-10-01. Recipes demonstrate designs; they are not verification of this repository's runtime.
+
+## Skill selection
+
+The official recipe uses two passes: rank the catalog and determine whether a skill is needed, then verify a shortlist with richer descriptions and brief instruction excerpts. It can return no skill. Treat the selected name as advice. Keep full manuals out of the main context until selected, and preserve required instructions independently. Ownership/scope filtering happens in code before selection.
+
+Evaluate against real and synthetic requests from the target catalog. Compare deterministic routing with assisted routing; measure wrong loads, needless loads and missed loads as well as latency/cost. The cookbook's published experiment used Jev 1.12 and was rendered 2026-07-31; its thresholds and results are not current-model guarantees. Do not copy its gates without calibration.
+
+[Skill suggestion recipe](https://docs.typesafe.ai/cookbooks/skill_suggestion)
+
+## Other applicable patterns
+
+- Intent routing and triage: choose a handler and ask independent urgency/status questions on shared state. [Intent routing](https://docs.typesafe.ai/patterns/intent-routing)
+- Large catalogs: hierarchical classification narrows categories before leaf selection. [Hierarchical classification](https://docs.typesafe.ai/cookbooks/hierarchical_classification)
+- Retrieval: score candidate passages, then filter in code; preserve source provenance. [RAG passage classification](https://docs.typesafe.ai/cookbooks/classifying_rag_passages)
+- Batch decisions: fan out independent questions about one state and compose the result in code. [Fan-out](https://docs.typesafe.ai/patterns/fan-out)
+
+Candidate matching, deduplication, citation checks and tool dispatch require their own validated decision definitions and tests. Use deterministic code for arithmetic, identifiers and access control. Periodic skill optimization can use advice to identify candidates, but it must preserve source, respect ownership, check drift and require review for semantic rewrites.

package/scaffold/.agent/skills/meta-harness/SKILL.md

@@ -1,113 +1,15 @@
 ---
 name: meta-harness
-description: Meta Harness & Agent Management Layer to orchestrate and delegate tasks across all connected IDE harnesses (Antigravity, Claude Code, Codex, Gemini, Ollama) and the computer generally.
+description: Inspect harnesses, agent processes and mesh execution when authorized.
+repo_scoped: false
 ---
 
-# Meta Harness & Agent Management Layer
+<!-- total-recall:skill-router:v1 -->
 
-The **Meta Harness** provides a unified agent management layer across all connected developer environments, CLI runtimes, and the computer generally.
+# Harness management
 
-## 🎯 Architectural Concept
+Resolve installed commands, authenticated accounts, permissions and recorded mesh access before execution. Dispatch or spawn agents only when authorized and supported by verified adapters. Read the selected CLI/process/mesh procedure; do not load every harness example.
 
-Total Recall connects to every major IDE, CLI harness, and local neural runtime:
-- **Google Antigravity (`agy`)**: Frontier multi-step reasoning, web grounding, and deep research on AI Ultra.
-- **Claude Code (`claude`)**: Direct terminal codebase refactoring, bash tool execution, and complex Unix tasks.
-- **OpenAI Codex (`codex`)**: Program synthesis, sandboxed workspace mutations, and isolated code generation.
-- **Google Gemini CLI (`gemini`)**: Fast utility completions and lightweight tool chaining.
-- **Ollama Local LLM (`ollama`)**: Zero-token-cost local neural reasoning (e.g. `gemma4:latest`) running non-interactively via standard input piping (`pipe_stdin`).
-- **IDE Surfaces**: Cursor (`.cursorrules`), Cline (`.clinerules`), VS Code (`copilot-instructions.md`), DeepSeek Harness (`dsh`).
+Track owned processes, await work, inspect real results and clean up. A catalog entry is not proof of an available integration. Use validated memory operations and preserve repository boundaries.
 
-### The Shared Brain Principle
-Because all harnesses operate over the **same portable brain**:
-- Every harness reads the same auto-compiled instruction surface (`AGENTS.md`, `GEMINI.md`, `CLAUDE.md`).
-- Every harness writes directly into the shared SSSS memory vault (`memory-vault/`).
-- Knowledge or solutions learned by one agent in one harness are immediately accessible to every other harness across the computer and mesh.
-
----
-
-## 🛠️ CLI Operations
-
-### 1. Inspect Active Harnesses
-Inspect all available developer harnesses and their local binary paths:
-```bash
-npx total-recall harness list
-```
-
-### 2. Headless Task Dispatch
-Dispatch a specific coding or research task to any external harness (locally or remotely over the mesh):
-```bash
-# Local dispatches
-npx total-recall harness dispatch claude "Inspect src/core/surface.mjs and run lint checks"
-npx total-recall harness dispatch agy "Analyze latest preprints on room temperature diamond NV registers"
-npx total-recall harness dispatch codex "Generate unit tests for src/core/context-cache.mjs"
-npx total-recall harness dispatch ollama "Summarize the core invariants of SSSS"
-
-# Cross-mesh remote dispatches
-npx total-recall harness dispatch ollama --node build-box "What is test-time compute scaling?"
-npx total-recall harness dispatch claude --node build-box "Run git status and lint tests"
-```
-
-### 3. Multi-Harness Council
-Run a task across multiple harnesses concurrently to obtain comparative solutions and consensus:
-```bash
-npx total-recall harness council "Propose architecture for decentralized research mesh"
-```
-
----
-
-## 🤖 Agent Process Management
-
-Manage background subagent tasks across the local machine and remote mesh nodes:
-
-### 1. Spawn a Background Agent
-```bash
-# Local background agent
-npx total-recall agent spawn claude "Refactor error handling in src/cli/harness.mjs" --name "Refactor Worker"
-
-# Remote background agent on a mesh node
-npx total-recall agent spawn agy --node build-box "Crawl recent preprints on quantum shuttling" --name "Quantum Scout"
-```
-
-### 2. Inspect Running Agents
-```bash
-npx total-recall agent list
-npx total-recall agent list --json
-```
-
-### 3. Stream Agent Logs
-```bash
-npx total-recall agent logs <agent-id> --tail 100
-```
-
-### 4. Terminate an Agent
-```bash
-npx total-recall agent kill <agent-id>
-```
-
----
-
-## 🌐 Headscale Mesh Diagnostics & Remote Execution
-
-The Meta Harness integrates directly with your private Headscale WireGuard mesh network:
-
-### 1. Cluster Capability Audit (`mesh doctor`)
-Concurrently audit reachability, developer runtimes (`node`, `docker`, `git`), and AI harnesses (`agy`, `claude`, `codex`, `gemini`, `ollama`) across all cluster nodes:
-```bash
-npx total-recall mesh doctor
-npx total-recall mesh doctor --json
-```
-
-### 2. Non-Interactive Remote Command Execution (`mesh exec`)
-Execute commands on remote nodes with automatic `$PATH` sanitization and structured outputs:
-```bash
-npx total-recall mesh exec build-box uname -m
-npx total-recall mesh exec cloud docker ps
-```
-
----
-
-## 💻 General Computer & OS Management
-The Meta Harness controls the computer generally:
-- **Activity Monitoring ("Follow the User")**: Tracks interaction timestamps and routes dispatches to the active device across the Headscale WireGuard mesh.
-- **Process Orchestration**: Spawns background worker loops, monitors task completion, and terminates runaway processes.
-- **Surface Sync**: Recompiles instruction surfaces across all IDE directories automatically upon graph updates.
+Before an operation, read its [task references](references/optimized/index.md), including prerequisites and constraints. If the applicable procedure is unclear, read the preserved original instead of guessing. Commands assume the skill root.

package/scaffold/.agent/skills/meta-harness/references/optimized/index.md

@@ -0,0 +1,20 @@
+# Task references
+
+Read only sections needed for the operation, including their prerequisites and constraints. Commands and plain paths assume the skill root. This index selects documentation, not permission or rule applicability.
+
+- [Overview](section-01.md)
+- [🎯 Architectural Concept](section-02.md)
+- [The Shared Brain Principle](section-03.md)
+- [🛠️ CLI Operations](section-04.md)
+- [1. Inspect Active Harnesses](section-05.md)
+- [2. Headless Task Dispatch](section-06.md)
+- [3. Multi-Harness Council](section-07.md)
+- [🤖 Agent Process Management](section-08.md)
+- [1. Spawn a Background Agent](section-09.md)
+- [2. Inspect Running Agents](section-10.md)
+- [3. Stream Agent Logs](section-11.md)
+- [4. Terminate an Agent](section-12.md)
+- [🌐 Headscale Mesh Diagnostics & Remote Execution](section-13.md)
+- [1. Cluster Capability Audit (`mesh doctor`)](section-14.md)
+- [2. Non-Interactive Remote Command Execution (`mesh exec`)](section-15.md)
+- [💻 General Computer & OS Management](section-16.md)

package/scaffold/.agent/skills/meta-harness/references/optimized/manifest.json

@@ -0,0 +1,79 @@
+{
+  "version": 1,
+  "source_sha256": "511f8c11043679b032b85c4a6ceca921d8ac17fc59be1cdb87572346e7e425b7",
+  "entrypoint_sha256": "56abd1e41c0c93292c1ea5dc02d9eed280ec0b68e51c3a34e2ab060c66ba5a2f",
+  "sections": [
+    {
+      "path": "references/optimized/section-01.md",
+      "sha256": "3d0dd724287d7de88d1bacd069f1eb2925b1fe2f128a15ee0d8baaf605f61e79"
+    },
+    {
+      "path": "references/optimized/section-02.md",
+      "sha256": "febe972174b649547733fb8c22fd6eee42b61f0834a0d18e48794c928c2381e8"
+    },
+    {
+      "path": "references/optimized/section-03.md",
+      "sha256": "d11f85b987516543e03b8ad6ac5752ed1efbfcd0a0aa9dacecaeb9c31f91501f"
+    },
+    {
+      "path": "references/optimized/section-04.md",
+      "sha256": "b0781872c9046f04a7beed3cd12e055bf82db184a8e9fb4e64ecc9cc494b7d01"
+    },
+    {
+      "path": "references/optimized/section-05.md",
+      "sha256": "4b7acbdf1f56ceb2aa9d77677e2c6ddd18407c115a67e62dbcd7d4f4ebe0c674"
+    },
+    {
+      "path": "references/optimized/section-06.md",
+      "sha256": "d5581f9390c9f1164884166b35dd1a9a59b3b23c9a03c351b1382f36282e8aeb"
+    },
+    {
+      "path": "references/optimized/section-07.md",
+      "sha256": "a430fe3f87eb1e99fe33570202a6e7e016faef343f7d89ee901bbc31e13c1868"
+    },
+    {
+      "path": "references/optimized/section-08.md",
+      "sha256": "c0ac4ceacdcfce39a72c9c4cb0ae41d466ab94d9e340c034a229e3686c14f90c"
+    },
+    {
+      "path": "references/optimized/section-09.md",
+      "sha256": "62d5a35716e489d5164e1bd6f541b92fe159a4a181ee99e1cd1acdf1dec53262"
+    },
+    {
+      "path": "references/optimized/section-10.md",
+      "sha256": "5ed4c289daae2a5c04f3d2e8d96715403ce0988a56feb89e73d7f83ff7c56473"
+    },
+    {
+      "path": "references/optimized/section-11.md",
+      "sha256": "f46d6aaabb132430bfe52e20e48ab7d4f9bb20e4548adf7b8ab2f3a122a9b382"
+    },
+    {
+      "path": "references/optimized/section-12.md",
+      "sha256": "ea3166d7ed898c766dc4f9fcbccbc35e43a0c63d65a081f4c81e95b4f0af6c0b"
+    },
+    {
+      "path": "references/optimized/section-13.md",
+      "sha256": "8f5b2410330d1773a8a801b91e6b66d471adaa9609a06720e27b5feb3e4b272c"
+    },
+    {
+      "path": "references/optimized/section-14.md",
+      "sha256": "92d093b8c5583b2eff82ffaf73cec094b4d087791427be3aa2382222db4c0605"
+    },
+    {
+      "path": "references/optimized/section-15.md",
+      "sha256": "24b6f085e0fa09dc25ef5e9d5b9b49d21adbe8c58ea7a835a38d3d9ac7272760"
+    },
+    {
+      "path": "references/optimized/section-16.md",
+      "sha256": "264af7d981ecbbdf060dd0d087eaca0bb15a17210ae4882d07fdbb45dbaddab3"
+    },
+    {
+      "path": "references/optimized/index.md",
+      "sha256": "ce64a33aed9e5987e917c83945ff7d54f14aed8a8c079142b053fddfac3e960b"
+    },
+    {
+      "path": "references/optimized/original.md",
+      "sha256": "511f8c11043679b032b85c4a6ceca921d8ac17fc59be1cdb87572346e7e425b7"
+    }
+  ]
+}

package/scaffold/.agent/skills/meta-harness/references/optimized/original.md

@@ -0,0 +1,113 @@
+---
+name: meta-harness
+description: Meta Harness & Agent Management Layer to orchestrate and delegate tasks across all connected IDE harnesses (Antigravity, Claude Code, Codex, Gemini, Ollama) and the computer generally.
+---
+
+# Meta Harness & Agent Management Layer
+
+The **Meta Harness** provides a unified agent management layer across all connected developer environments, CLI runtimes, and the computer generally.
+
+## 🎯 Architectural Concept
+
+Total Recall connects to every major IDE, CLI harness, and local neural runtime:
+- **Google Antigravity (`agy`)**: Frontier multi-step reasoning, web grounding, and deep research on AI Ultra.
+- **Claude Code (`claude`)**: Direct terminal codebase refactoring, bash tool execution, and complex Unix tasks.
+- **OpenAI Codex (`codex`)**: Program synthesis, sandboxed workspace mutations, and isolated code generation.
+- **Google Gemini CLI (`gemini`)**: Fast utility completions and lightweight tool chaining.
+- **Ollama Local LLM (`ollama`)**: Zero-token-cost local neural reasoning (e.g. `gemma4:latest`) running non-interactively via standard input piping (`pipe_stdin`).
+- **IDE Surfaces**: Cursor (`.cursorrules`), Cline (`.clinerules`), VS Code (`copilot-instructions.md`), DeepSeek Harness (`dsh`).
+
+### The Shared Brain Principle
+Because all harnesses operate over the **same portable brain**:
+- Every harness reads the same auto-compiled instruction surface (`AGENTS.md`, `GEMINI.md`, `CLAUDE.md`).
+- Every harness writes directly into the shared SSSS memory vault (`memory-vault/`).
+- Knowledge or solutions learned by one agent in one harness are immediately accessible to every other harness across the computer and mesh.
+
+---
+
+## 🛠️ CLI Operations
+
+### 1. Inspect Active Harnesses
+Inspect all available developer harnesses and their local binary paths:
+```bash
+npx total-recall harness list
+```
+
+### 2. Headless Task Dispatch
+Dispatch a specific coding or research task to any external harness (locally or remotely over the mesh):
+```bash
+# Local dispatches
+npx total-recall harness dispatch claude "Inspect src/core/surface.mjs and run lint checks"
+npx total-recall harness dispatch agy "Analyze latest preprints on room temperature diamond NV registers"
+npx total-recall harness dispatch codex "Generate unit tests for src/core/context-cache.mjs"
+npx total-recall harness dispatch ollama "Summarize the core invariants of SSSS"
+
+# Cross-mesh remote dispatches
+npx total-recall harness dispatch ollama --node build-box "What is test-time compute scaling?"
+npx total-recall harness dispatch claude --node build-box "Run git status and lint tests"
+```
+
+### 3. Multi-Harness Council
+Run a task across multiple harnesses concurrently to obtain comparative solutions and consensus:
+```bash
+npx total-recall harness council "Propose architecture for decentralized research mesh"
+```
+
+---
+
+## 🤖 Agent Process Management
+
+Manage background subagent tasks across the local machine and remote mesh nodes:
+
+### 1. Spawn a Background Agent
+```bash
+# Local background agent
+npx total-recall agent spawn claude "Refactor error handling in src/cli/harness.mjs" --name "Refactor Worker"
+
+# Remote background agent on a mesh node
+npx total-recall agent spawn agy --node build-box "Crawl recent preprints on quantum shuttling" --name "Quantum Scout"
+```
+
+### 2. Inspect Running Agents
+```bash
+npx total-recall agent list
+npx total-recall agent list --json
+```
+
+### 3. Stream Agent Logs
+```bash
+npx total-recall agent logs <agent-id> --tail 100
+```
+
+### 4. Terminate an Agent
+```bash
+npx total-recall agent kill <agent-id>
+```
+
+---
+
+## 🌐 Headscale Mesh Diagnostics & Remote Execution
+
+The Meta Harness integrates directly with your private Headscale WireGuard mesh network:
+
+### 1. Cluster Capability Audit (`mesh doctor`)
+Concurrently audit reachability, developer runtimes (`node`, `docker`, `git`), and AI harnesses (`agy`, `claude`, `codex`, `gemini`, `ollama`) across all cluster nodes:
+```bash
+npx total-recall mesh doctor
+npx total-recall mesh doctor --json
+```
+
+### 2. Non-Interactive Remote Command Execution (`mesh exec`)
+Execute commands on remote nodes with automatic `$PATH` sanitization and structured outputs:
+```bash
+npx total-recall mesh exec build-box uname -m
+npx total-recall mesh exec cloud docker ps
+```
+
+---
+
+## 💻 General Computer & OS Management
+The Meta Harness controls the computer generally:
+- **Activity Monitoring ("Follow the User")**: Tracks interaction timestamps and routes dispatches to the active device across the Headscale WireGuard mesh.
+- **Process Orchestration**: Spawns background worker loops, monitors task completion, and terminates runaway processes.
+- **Surface Sync**: Recompiles instruction surfaces across all IDE directories automatically upon graph updates.

package/scaffold/.agent/skills/meta-harness/references/optimized/section-01.md

@@ -0,0 +1,5 @@
+
+# Meta Harness & Agent Management Layer
+
+The **Meta Harness** provides a unified agent management layer across all connected developer environments, CLI runtimes, and the computer generally.
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-02.md

@@ -0,0 +1,10 @@
+## 🎯 Architectural Concept
+
+Total Recall connects to every major IDE, CLI harness, and local neural runtime:
+- **Google Antigravity (`agy`)**: Frontier multi-step reasoning, web grounding, and deep research on AI Ultra.
+- **Claude Code (`claude`)**: Direct terminal codebase refactoring, bash tool execution, and complex Unix tasks.
+- **OpenAI Codex (`codex`)**: Program synthesis, sandboxed workspace mutations, and isolated code generation.
+- **Google Gemini CLI (`gemini`)**: Fast utility completions and lightweight tool chaining.
+- **Ollama Local LLM (`ollama`)**: Zero-token-cost local neural reasoning (e.g. `gemma4:latest`) running non-interactively via standard input piping (`pipe_stdin`).
+- **IDE Surfaces**: Cursor (`.cursorrules`), Cline (`.clinerules`), VS Code (`copilot-instructions.md`), DeepSeek Harness (`dsh`).
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-03.md

@@ -0,0 +1,8 @@
+### The Shared Brain Principle
+Because all harnesses operate over the **same portable brain**:
+- Every harness reads the same auto-compiled instruction surface (`AGENTS.md`, `GEMINI.md`, `CLAUDE.md`).
+- Every harness writes directly into the shared SSSS memory vault (`memory-vault/`).
+- Knowledge or solutions learned by one agent in one harness are immediately accessible to every other harness across the computer and mesh.
+
+---
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-04.md

@@ -0,0 +1,2 @@
+## 🛠️ CLI Operations
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-05.md

@@ -0,0 +1,6 @@
+### 1. Inspect Active Harnesses
+Inspect all available developer harnesses and their local binary paths:
+```bash
+npx total-recall harness list
+```
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-06.md

@@ -0,0 +1,14 @@
+### 2. Headless Task Dispatch
+Dispatch a specific coding or research task to any external harness (locally or remotely over the mesh):
+```bash
+# Local dispatches
+npx total-recall harness dispatch claude "Inspect src/core/surface.mjs and run lint checks"
+npx total-recall harness dispatch agy "Analyze latest preprints on room temperature diamond NV registers"
+npx total-recall harness dispatch codex "Generate unit tests for src/core/context-cache.mjs"
+npx total-recall harness dispatch ollama "Summarize the core invariants of SSSS"
+
+# Cross-mesh remote dispatches
+npx total-recall harness dispatch ollama --node build-box "What is test-time compute scaling?"
+npx total-recall harness dispatch claude --node build-box "Run git status and lint tests"
+```
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-07.md

@@ -0,0 +1,8 @@
+### 3. Multi-Harness Council
+Run a task across multiple harnesses concurrently to obtain comparative solutions and consensus:
+```bash
+npx total-recall harness council "Propose architecture for decentralized research mesh"
+```
+
+---
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-08.md

@@ -0,0 +1,4 @@
+## 🤖 Agent Process Management
+
+Manage background subagent tasks across the local machine and remote mesh nodes:
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-09.md

@@ -0,0 +1,9 @@
+### 1. Spawn a Background Agent
+```bash
+# Local background agent
+npx total-recall agent spawn claude "Refactor error handling in src/cli/harness.mjs" --name "Refactor Worker"
+
+# Remote background agent on a mesh node
+npx total-recall agent spawn agy --node build-box "Crawl recent preprints on quantum shuttling" --name "Quantum Scout"
+```
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-10.md

@@ -0,0 +1,6 @@
+### 2. Inspect Running Agents
+```bash
+npx total-recall agent list
+npx total-recall agent list --json
+```
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-11.md

@@ -0,0 +1,5 @@
+### 3. Stream Agent Logs
+```bash
+npx total-recall agent logs <agent-id> --tail 100
+```
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-12.md

@@ -0,0 +1,7 @@
+### 4. Terminate an Agent
+```bash
+npx total-recall agent kill <agent-id>
+```
+
+---
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-13.md

@@ -0,0 +1,4 @@
+## 🌐 Headscale Mesh Diagnostics & Remote Execution
+
+The Meta Harness integrates directly with your private Headscale WireGuard mesh network:
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-14.md

@@ -0,0 +1,7 @@
+### 1. Cluster Capability Audit (`mesh doctor`)
+Concurrently audit reachability, developer runtimes (`node`, `docker`, `git`), and AI harnesses (`agy`, `claude`, `codex`, `gemini`, `ollama`) across all cluster nodes:
+```bash
+npx total-recall mesh doctor
+npx total-recall mesh doctor --json
+```
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-15.md

@@ -0,0 +1,9 @@
+### 2. Non-Interactive Remote Command Execution (`mesh exec`)
+Execute commands on remote nodes with automatic `$PATH` sanitization and structured outputs:
+```bash
+npx total-recall mesh exec build-box uname -m
+npx total-recall mesh exec cloud docker ps
+```
+
+---
+

package/scaffold/.agent/skills/meta-harness/references/optimized/section-16.md

@@ -0,0 +1,5 @@
+## 💻 General Computer & OS Management
+The Meta Harness controls the computer generally:
+- **Activity Monitoring ("Follow the User")**: Tracks interaction timestamps and routes dispatches to the active device across the Headscale WireGuard mesh.
+- **Process Orchestration**: Spawns background worker loops, monitors task completion, and terminates runaway processes.
+- **Surface Sync**: Recompiles instruction surfaces across all IDE directories automatically upon graph updates.

package/scaffold/.agent/skills/plugins/SKILL.md

@@ -1,58 +1,15 @@
 ---
 name: plugins
-description: Create, validate, install, run, and share Total Recall plugins. Use when a user wants a plugin that adds a useful command, scheduled task, agent context, or SSSS memory category.
+description: Create, validate, install or share Total Recall plugins.
+repo_scoped: false
 ---
 
-# Total Recall plugins
+<!-- total-recall:skill-router:v1 -->
 
-Build a plugin for a concrete user job. Start by stating the command, context, task, or memory category it adds and how a user will tell that it works. Do not add a plugin solely to populate a gallery.
+# Plugins
 
-## Where to work
+Use the plugin workspace and current `plugin.json`/extension contracts. Keep optional capabilities in plugins rather than portable memory core. Every claimed command, schedule, UI/API action or memory extension needs a real handler and validation.
 
-Run `total-recall plugin create <id> --name "..." --description "..." --use-case <tag> --with-cli` to scaffold an installed plugin. The CLI creates a directory under the current project's `.agent/skills/total-recall/plugins/`; `--global` creates a machine-wide plugin. A plugin is a folder containing `plugin.json` and the files its manifest names. For a plugin intended to ship with Total Recall itself, use the package's `plugins/<id>/` folder and add a real install and use test.
+Read implementation or installation references for that operation. Verify scopes, invalid input, canonical SSSS writes, failure reporting and actual execution. Sharing requires explicit authorization; public bundles exclude credentials, private vault content and runtime state. Read sharing procedures only when sharing is requested.
 
-Inspect the installed package's `metadata.plugin.schema.json` and `src/core/plugin-loader.mjs` for the current executable contract before changing a manifest. The schema supports:
-
-```json
-{
-  "id": "example-plugin",
-  "name": "Example Plugin",
-  "version": "1.0.0",
-  "description": "The specific job this plugin does.",
-  "author": "Author name",
-  "license": "MIT",
-  "use_cases": ["research"],
-  "cli": {
-    "command": "example-plugin",
-    "handler": "./cli.mjs",
-    "subcommands": [{ "name": "status", "description": "Show current status" }]
-  }
-}
-```
-
-An ID is lowercase kebab case, starts with a letter, and is 2–64 characters. `use_cases` are descriptive kebab-case tags. Keep the manifest honest: declare only features the plugin implements. `README.md` should explain the user job, prerequisites, commands, outputs, and any data or network access.
-
-## Implement a capability
-
-- **Command:** export `async function run(argv)` from the `cli.handler` module. It receives `['node', 'total-recall', '<command>', '<subcommand>', ...]`. A default-exported function is also supported and receives arguments after the command. Return a result or set `process.exitCode` on failure. The runner isolates the handler in a child process, with a timeout and output cap.
-- **Scheduled task:** add `tasks: [{ "intent": "...", "schedule": "*/15 * * * *", "command": "sample" }]`. `command` is a subcommand implemented by the plugin's CLI handler. The daemon runs it once per due minute slot and records the outcome as a `plugin.task_run` event. Keep tasks bounded and idempotent.
-- **Agent context:** add `compile: { "generator": "./generator.mjs", "auto": true }` and export `generateContext()` from that file. Only include information useful to the agent; avoid secrets and noisy telemetry.
-- **Memory category:** declare it under `ssss_schemas.categories` using the current manifest schema. Preserve SSSS Markdown and operation-contract writes; do not write vault documents directly.
-
-- **Repo-customized skill:** a layered skill (plugin-owned `core/`, repo-owned files beside it) declares its repo config contract as `core/config.schema.json`, a JSON Schema whose root is an object. Annotate an array with `"x-collection": "<noun>"` (and optionally `"x-key"`, default `name`) to get `<noun> list|add|remove`. An optional `core/detect.mjs` exports `detect({ repoRoot, skillDir })` and returns a proposed config. Users customize the repo layer with `total-recall skill config <id> config set …`, `detect --apply`, or `init`, or with a repo command generated by `total-recall command create <name> --config-for-skill <id>`. Every write validates the whole config and commits a `skill_config` record to the repo's project vault; `config.json` is rebuilt from it. Never tell users to edit `config.json` by hand: `config validate` reports hand edits as drift, and `config import` adopts a pre-existing file. Mark gate-command string fields `"x-command": true`; `skill config <id> check`, `skill status <id>`, and `app verify` confirm each one resolves without running it.
-
-- **App-runtime CLI:** declare `app_cli` in `plugin.json`: `name`, `api: { base_url_env, default_base_url }` (loopback only; operators override it with the env var or `--base-url`), optional `auth: { type: "bearer", token_env }`, and `commands: [{ name, method, path, args }]`. Args are typed (`string|integer|number|boolean`, `choices`, `default`, `required`, `positional`); `{name}` in `path` must be a required arg, other args go to the query (GET/DELETE) or JSON body. `total-recall app cli <plugin> --lang node|python` (or `--adapter flask|nextjs|react|ssss-app`) prints a self-contained file; `--out <file>` writes it. The file runs without Total Recall: exit 0 ok, 1 the app returned an error, 2 usage, 3 unreachable; `--json` prints `{ ok, status, data | error }`. Regenerate after changing the spec; never hand-edit the output.
-- **UI elements:** author each element once as a self-contained custom element: an ES module under the plugin (e.g. `ui/<id>.js`) that imports nothing, calls `customElements.define('<tag>', …)` exactly once, and styles itself only with design-token variables (`var(--color-…)`, `--spacing-…`, `--radius-…`, `--typography-<style>-…`, `--font-family-…`; `--_name` for private ones). No literal colors, not even as `var()` fallbacks. Declare it in `plugin.json` `ui.elements[]`: `id`, `kind` (`panel|form|list|detail|settings|widget`), `tag`, `module`, optional `slot`, typed `props` (set as DOM properties), `events`, the `tokens` it requires and `optional_tokens` it uses with a token fallback; `ui.design_tokens` may point at a neutral default `DESIGN.md`. `total-recall app ui <plugin> --ui web-components|react` (or `--adapter flask|ssss-app|nextjs|react`) with `--tokens <app DESIGN.md>` checks the required tokens and generates `tokens.css`, `elements/<id>.js`, `index.js`, React wrappers (`--typescript` for `.tsx` plus `.d.ts`), and `ui-manifest.json`; `--out <dir>` writes `<dir>/<plugin-id>/`. An app restyles elements by editing its `DESIGN.md` and regenerating; the element files do not change.
-
-## Validate the actual job
-
-1. Validate `plugin.json` against the installed schema and `total-recall plugin info <id>`.
-2. Install in a clean temporary project, then run the declared command through `total-recall <command> <subcommand>`. For tasks, verify one due run and its event. For context generators, compile and inspect the resulting block.
-3. Exercise failure paths: missing prerequisite, invalid input, timeout, and any network failure. A plugin that installs but cannot do its advertised job is unfinished.
-4. Review the plugin's file set before sharing. Plugin code has the recipient's process permissions when run. Never bundle secrets, browser profiles, vault data, or machine-specific paths.
-
-## Share with another user
-
-`total-recall plugin share <id>` marks an installed plugin shareable. Configure `TR_PUBLIC_BASE_URL` as the node's externally reachable HTTPS origin; the command and dashboard then show a direct link ending in `#sha256=<content hash>`. Send that link to the recipient. They install with `total-recall plugin install '<link>'`. The installer requires HTTPS, rejects private destination addresses and redirects, caps the bundle size, and verifies the pinned SHA-256 before writing files. There is no central catalog. The hosting node must actually be reachable at its configured HTTPS origin.
-
-`total-recall plugin unshare <id>` stops serving the bundle. Existing installations remain on recipients' machines. Users on one private mesh may also use `peer:<host>/<id>`; mesh membership is not required for public sharing.
+Before an operation, read its [task references](references/optimized/index.md), including prerequisites and constraints. If the applicable procedure is unclear, read the preserved original instead of guessing. Commands assume the skill root.

package/scaffold/.agent/skills/plugins/references/optimized/index.md

@@ -0,0 +1,9 @@
+# Task references
+
+Read only sections needed for the operation, including their prerequisites and constraints. Commands and plain paths assume the skill root. This index selects documentation, not permission or rule applicability.
+
+- [Overview](section-01.md)
+- [Where to work](section-02.md)
+- [Implement a capability](section-03.md)
+- [Validate the actual job](section-04.md)
+- [Share with another user](section-05.md)