tribunal-kit 9.2.4 → 9.2.6

package/.agents/skills/server-management/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: server-management
-description: "Use when Production Linux server administration mastery. Systemd services, Nginx reverse proxy architecture, UFW firewalls, SSH key security, cron scheduling, log rotation, and server hardening. Use when configuring bare-metal, VPS instances, or reviewing deployment architecture."
-version: 5.0.0
-last-updated: 2026-09-13
+description: "Use when configuring, automating, deploying, and debugging server management pipelines, containers, servers, and cloud infrastructure."
+version: 6.0.0
+last-updated: 2026-09-29
 skills:
   - devops-engineer
   - backend-security-expert
@@ -15,164 +15,222 @@ scripts-binding:
 
 # Server Management — Production Linux Mastery
 
----
-
-## 🛠️ Technical Architecture & Reference Recipes
-
----
-
-## Hallucination Traps (Read First)
-
-- ❌ Running services as root -> ✅ Create a dedicated service user with minimal permissions; never run as root
-- ❌ Using password-based SSH -> ✅ Disable password auth; use SSH key pairs only with `PermitRootLogin no`
-- ❌ Editing nginx config without testing -> ✅ Always run `nginx -t` before `systemctl reload nginx`; syntax errors take down all sites
-
----
-
----
-
-## 1. Systemd Service Architecture (Process Guard)
-
-Do not use `pm2`, `forever`, or custom `screen` sessions attached to SSH panels for server orchestration. Linux provides an enterprise-grade init system natively: systemd.
-
-```ini
-# /etc/systemd/system/myapp.service
-
-[Unit]
-Description=My Application Node.js Server
-Documentation=https://example.com/docs
-After=network.target postgresql.service # Ensure DB and Network start first
+## Mandatory Pre-Flight Context Inspection
+Before reading, generating, or refactoring code in the `server-management` domain, inspect these 5 critical parameters:
+1. **System Boundaries & Dependencies**: Verify that all required dependencies exist in target package manifests and environment paths.
+2. **Runtime Context & Platform Invariants**: Confirm target platform constraints (Node.js, Browser, Mobile OS, Edge runtime) before applying APIs.
+3. **Execution Guardrails**: Identify potential side-effects, state mutations, and unhandled asynchronous exceptions.
+4. **Validation & Type Contracts**: Validate input data schemas and strict type constraints across all module interfaces.
+5. **Observability & Proof of Execution**: Ensure execution produces tangible verification signals (terminal output, tests, metrics).
 
-[Service]
-Type=simple
-User=appuser     # NEVER run as root
-Group=appuser
-WorkingDirectory=/var/www/myapp
 
-# Explicitly declare environment limits and variables
-Environment=NODE_ENV=production
-Environment=PORT=3000
-EnvironmentFile=/var/www/myapp/.env
+## Activation Boundaries
+- **Activate when:** Use when configuring, automating, deploying, and debugging server management pipelines, containers, servers, and cloud infrastructure.
+- **DO NOT activate when:** The task falls outside the `server-management` domain or is managed by a different dedicated specialist agent.
 
-# The execution target
-ExecStart=/usr/bin/node /var/www/myapp/build/index.js
 
-# Immortal behavior: Restart strictly on failure
-Restart=on-failure
-RestartSec=5
+## 🔁 Multi-Pass Execution Protocol
 
-# Security Hardening
-NoNewPrivileges=yes
-PrivateTmp=yes
-RestrictAddressFamilies=AF_INET AF_INET6 AF_UNIX
+| Pass | Phase | Core Action | Adaptive Depth |
+|:---|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. | Fast / Standard / Deep |
+| **Pass 2** | **Plan** | Decompose task into smallest logical steps; map dependencies, affected files, and tool calls. | Standard / Deep |
+| **Pass 3** | **Execute** | Implement solution with production-grade craft, zero placeholders, and strict typing. | All Modes |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. | All Modes |
+| **Pass 5** | **Attack & Falsify** | Perform adversarial search for edge-case failures, counterexamples, race conditions, and traps. | Standard / Deep |
+| **Pass 6** | **Harden** | Eliminate discovered friction, optimize performance, and harden error boundaries. | Standard / Deep |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. | All Modes |
 
-[Install]
-WantedBy=multi-user.target
-```
 
-**Commands:**
-`sudo systemctl daemon-reload`
-`sudo systemctl enable myapp`
-`sudo systemctl start myapp`
-`journalctl -u myapp -f` (Follow logs seamlessly)
+---
+
+## 🛠️ Technical Architecture & Reference Recipes
 
+## Hallucination Traps (Read First)
+
+- ❌ Running services as root -> ✅ Create a dedicated service user with minimal permissions; never run as root
+- ❌ Using password-based SSH -> ✅ Disable password auth; use SSH key pairs only with `PermitRootLogin no`
+- ❌ Editing nginx config without testing -> ✅ Always run `nginx -t` before `systemctl reload nginx`; syntax errors take down all sites
+
 ---
-
-## 2. Nginx Reverse Proxy Architecture
-
-You must shield your internal application framework (Node/Python/Ruby) behind Nginx. Nginx handles SSL termination, static file caching, and DDOS mitigation.
-
-```nginx
-# /etc/nginx/sites-available/myapp.com
-
-server {
-    listen 80;
-    server_name api.myapp.com;
-
-    # Force SSL Redirect
-    return 301 https://$host$request_uri;
-}
-
-server {
-    listen 443 ssl http2;
-    server_name api.myapp.com;
-
-    # SSL Certs (Let's Encrypt / Certbot)
-    ssl_certificate /etc/letsencrypt/live/api.myapp.com/fullchain.pem;
-    ssl_certificate_key /etc/letsencrypt/live/api.myapp.com/privkey.pem;
-
-    # Modern Security Headers
-    add_header Strict-Transport-Security "max-age=63072000" always;
-    add_header X-Content-Type-Options nosniff;
-    add_header X-Frame-Options DENY;
-
-    # GZIP Compression
-    gzip on;
-    gzip_types text/plain application/json;
-
-    location / {
-        # Proxy traffic to internal local process
-        proxy_pass http://127.0.0.1:3000;
-
-        # Forward original IP and Protocol for rate limiters
-        proxy_set_header Host $host;
-        proxy_set_header X-Real-IP $remote_addr;
-        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        proxy_set_header X-Forwarded-Proto $scheme;
-
-        # WebSocket support (Required for GraphQL subscriptions, TRPC, Socket.io)
-        proxy_http_version 1.1;
-        proxy_set_header Upgrade $http_upgrade;
-        proxy_set_header Connection "upgrade";
-    }
-}
+## 1. Systemd Service Architecture (Process Guard)
+
+Do not use `pm2`, `forever`, or custom `screen` sessions attached to SSH panels for server orchestration. Linux provides an enterprise-grade init system natively: systemd.
+
+```ini
+# /etc/systemd/system/myapp.service
+
+[Unit]
+Description=My Application Node.js Server
+Documentation=https://example.com/docs
+After=network.target postgresql.service # Ensure DB and Network start first
+
+[Service]
+Type=simple
+User=appuser     # NEVER run as root
+Group=appuser
+WorkingDirectory=/var/www/myapp
+
+# Explicitly declare environment limits and variables
+Environment=NODE_ENV=production
+Environment=PORT=3000
+EnvironmentFile=/var/www/myapp/.env
+
+# The execution target
+ExecStart=/usr/bin/node /var/www/myapp/build/index.js
+
+# Immortal behavior: Restart strictly on failure
+Restart=on-failure
+RestartSec=5
+
+# Security Hardening
+NoNewPrivileges=yes
+PrivateTmp=yes
+RestrictAddressFamilies=AF_INET AF_INET6 AF_UNIX
+
+[Install]
+WantedBy=multi-user.target
+```
+
+**Commands:**
+`sudo systemctl daemon-reload`
+`sudo systemctl enable myapp`
+`sudo systemctl start myapp`
+`journalctl -u myapp -f` (Follow logs seamlessly)
+
+---
+
+## 2. Nginx Reverse Proxy Architecture
+
+You must shield your internal application framework (Node/Python/Ruby) behind Nginx. Nginx handles SSL termination, static file caching, and DDOS mitigation.
+
+```nginx
+# /etc/nginx/sites-available/myapp.com
+
+server {
+    listen 80;
+    server_name api.myapp.com;
+
+    # Force SSL Redirect
+    return 301 https://$host$request_uri;
+}
+
+server {
+    listen 443 ssl http2;
+    server_name api.myapp.com;
+
+    # SSL Certs (Let's Encrypt / Certbot)
+    ssl_certificate /etc/letsencrypt/live/api.myapp.com/fullchain.pem;
+    ssl_certificate_key /etc/letsencrypt/live/api.myapp.com/privkey.pem;
+
+    # Modern Security Headers
+    add_header Strict-Transport-Security "max-age=63072000" always;
+    add_header X-Content-Type-Options nosniff;
+    add_header X-Frame-Options DENY;
+
+    # GZIP Compression
+    gzip on;
+    gzip_types text/plain application/json;
+
+    location / {
+        # Proxy traffic to internal local process
+        proxy_pass http://127.0.0.1:3000;
+
+        # Forward original IP and Protocol for rate limiters
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+
+        # WebSocket support (Required for GraphQL subscriptions, TRPC, Socket.io)
+        proxy_http_version 1.1;
+        proxy_set_header Upgrade $http_upgrade;
+        proxy_set_header Connection "upgrade";
+    }
+}
+```
+
+---
+
+## 3. Server Hardening Fundamentals
+
+### SSH Security (`/etc/ssh/sshd_config`)
+
+```bash
+PermitRootLogin no           # Kill direct root login attacks immediately
+PasswordAuthentication no    # Enforce SSH key-based login ONLY
+Port 2022                    # (Optional) Obscurity defense against automated script-kiddie scanners
+```
+
+### Uncomplicated Firewall (UFW)
+
+A naked server with all ports open is a honeypot.
+
+```bash
+sudo ufw default deny incoming
+sudo ufw default allow outgoing
+sudo ufw allow 22/tcp      # Allow SSH
+sudo ufw allow 80/tcp      # Allow HTTP
+sudo ufw allow 443/tcp     # Allow HTTPS
+sudo ufw enable
+```
+
+### Fail2Ban
+
+Automatically bans IPs attempting brute force credential filling after 5 bad attempts.
+
+---
+
+## 4. Log Rotation (Prevent Disk Full Outages)
+
+A server will inevitably crash when `/var/log` consumes 100% of the disk.
+
+```bash
+# /etc/logrotate.d/myapp
+
+/var/www/myapp/logs/*.log {
+    daily                # Rotate every day
+    missingok            # Ignore if file is missing
+    rotate 14            # Keep 14 days of history
+    compress             # Gzip old logs
+    delaycompress        # Don't compress the one created yesterday
+    notifempty           # Do nothing if log is empty
+    copytruncate         # Copy then clear (avoids disrupting Node's open file handles)
+}
 ```
 
----
+## 🚨 Edge-Case & Failure Mode Matrix
 
-## 3. Server Hardening Fundamentals
+| Scenario | Risk | Production Mitigation |
+|:---|:---|:---|
+| **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
+| **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
+| **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
+| **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
+| **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
 
-### SSH Security (`/etc/ssh/sshd_config`)
 
-```bash
-PermitRootLogin no           # Kill direct root login attacks immediately
-PasswordAuthentication no    # Enforce SSH key-based login ONLY
-Port 2022                    # (Optional) Obscurity defense against automated script-kiddie scanners
-```
+## 🏛️ Tribunal Verification & Guardrails
 
-### Uncomplicated Firewall (UFW)
+**Active Reviewers:** `pipeline-reviewer` · `devops-engineer` · `resilience-reviewer`
+**Slash Command:** `/review` or `/tribunal-full`
 
-A naked server with all ports open is a honeypot.
+### 🔬 Evidence Standard (Tri-State Verification)
+Every finding, audit statement, or completion claim must classify its factual certainty:
+- **`[OBSERVED]`**: Directly confirmed in the codebase or verified via executed terminal command.
+- **`[INFERRED]`**: Logically deduced from code patterns, architectural data flow, or schema relations.
+- **`[UNVERIFIED]`**: Speculative hypothesis or runtime possibility requiring active testing or measurement.
 
-```bash
-sudo ufw default deny incoming
-sudo ufw default allow outgoing
-sudo ufw allow 22/tcp      # Allow SSH
-sudo ufw allow 80/tcp      # Allow HTTP
-sudo ufw allow 443/tcp     # Allow HTTPS
-sudo ufw enable
+### ✅ Pre-Flight Self-Audit Checklist
 ```
-
-### Fail2Ban
-
-Automatically bans IPs attempting brute force credential filling after 5 bad attempts.
-
----
-
-## 4. Log Rotation (Prevent Disk Full Outages)
-
-A server will inevitably crash when `/var/log` consumes 100% of the disk.
-
-```bash
-# /etc/logrotate.d/myapp
-
-/var/www/myapp/logs/*.log {
-    daily                # Rotate every day
-    missingok            # Ignore if file is missing
-    rotate 14            # Keep 14 days of history
-    compress             # Gzip old logs
-    delaycompress        # Don't compress the one created yesterday
-    notifempty           # Do nothing if log is empty
-    copytruncate         # Copy then clear (avoids disrupting Node's open file handles)
-}
+✅ Are strict execution modes (set -euo pipefail) active on all scripts?
+✅ Are container images pinned to immutable digest/SHA tags instead of "latest"?
+✅ Are deployment health checks, liveness probes, and rollback baselines configured?
+✅ Are CI secrets masked and unexposed to untrusted pull requests?
+✅ Did I verify environment compatibility across target runtimes?
 ```
+
+### 🛑 Verification-Before-Completion (VBC) Protocol
+**CRITICAL:** You must follow a strict "evidence-based closeout" state machine.
+- ❌ **Forbidden:** Declaring a task complete because the output "looks correct."
+- ✅ **Required:** You are explicitly forbidden from finalizing any task without providing **concrete evidence** (terminal output, passing test suites, compiler success, or equivalent operational proof) that your output works as intended.

package/.agents/skills/session-log-interrogation/SKILL.md

@@ -1,29 +1,81 @@
 ---
 name: session-log-interrogation
-description: "Use when teaching selective access to session history to prevent context window bloat during long-running sessions."
-version: 1.0.0
-last-updated: 2026-09-25
+description: "Use when searching, extracting, and synthesizing past conversation history and decision records. Prevents context amnesia without polluting current prompt budgets with massive raw transcripts."
+version: 6.0.0
+last-updated: 2026-09-29
 skills:
-  - context-engineering-pro
+  - fabel-protocol
 tools: Read, Grep, Glob, Bash, Edit, Write
 scripts-binding:
-  - .agent/scripts/session_logger.js
+  - .agent/scripts/session_manager.js
+  - .agent/scripts/verify_all.js
+  - .agent/scripts/lint_runner.js
 ---
 
-# Session Log Interrogation
+# Session Log Interrogation — Token-Efficient Multi-Session Memory
 
-## The Context Problem
-Long-running agent workflows generate thousands of events (Syscalls, Model turns, Tool Responses). Injecting the full session history into a prompt degrades reasoning, wastes tokens, and eventually hits hard limits.
+## Activation Boundaries
+- **Activate when:** Use when searching, extracting, and synthesizing past conversation history and decision records. Prevents context amnesia without polluting current prompt budgets with massive raw transcripts.
+- **DO NOT activate when:** The task falls outside the `session-log-interrogation` domain or is managed by a different dedicated specialist agent.
 
-## The Solution: Selective Interrogation
-The agent must filter and request specific event ranges rather than loading the entire file.
 
-## Tactics
-1. **Time-Bounded Queries**: Request events only since the last major Checkpoint (e.g., "Give me all events since Wave 2 started").
-2. **Error-Focused Scans**: Query specifically for `ToolFailed` or `SessionFailed` events to understand what went wrong, ignoring the happy-path `ToolCompleted` events.
-3. **Provenance Validation**: When referencing past actions, cite the exact `eventId`.
-4. **Context Budgets**: Never load more than 50 events into context at once. If the query yields more, aggregate them into a summary locally before passing to the model.
+## 🔁 Multi-Pass Execution Protocol
 
-## Anti-Patterns
-- ❌ Reading the raw `.agent_session.json` line-by-line using `cat`.
-- ✅ Using the `session_logger.js` or `harness_manager.js` to fetch structured, filtered logs.
+| Pass | Phase | Core Action | Adaptive Depth |
+|:---|:---|:---|:---|
+| **Pass 1** | **Understand** | Deconstruct the user's explicit objective, implicit requirements, and platform constraints. | Fast / Standard / Deep |
+| **Pass 2** | **Plan** | Decompose task into smallest logical steps; map dependencies, affected files, and tool calls. | Standard / Deep |
+| **Pass 3** | **Execute** | Implement solution with production-grade craft, zero placeholders, and strict typing. | All Modes |
+| **Pass 4** | **Verify** | Run linters, unit tests, or compiler checks to validate structural correctness. | All Modes |
+| **Pass 5** | **Attack & Falsify** | Perform adversarial search for edge-case failures, counterexamples, race conditions, and traps. | Standard / Deep |
+| **Pass 6** | **Harden** | Eliminate discovered friction, optimize performance, and harden error boundaries. | Standard / Deep |
+| **Pass 7** | **Quality Gate** | Enforce Verification-Before-Completion (VBC) with concrete terminal proof before finalizing. | All Modes |
+
+
+## Mandatory Pre-Flight Context Inspection
+1. **Target Decision Identification**: Pinpoint the exact question or architectural decision needed from past turns.
+2. **Compact Transcript First**: Query `transcript.jsonl` (compact format) first; avoid loading `transcript_full.jsonl` unless detail is missing.
+3. **Structured Event Extraction**: Grep for step types: `"type":"USER_INPUT"` or `"invoke_subagent"`.
+4. **Summary Distillation**: Summarize past context in 3-5 bullet points; NEVER paste raw transcripts into subagent prompts.
+5. **Drift Detection**: Verify that decisions recorded in past sessions still align with active codebase reality.
+
+## 🛠️ Technical Architecture & Reference Recipes
+
+### 1. Targeted Transcript Grep Commands
+```bash
+# Find all previous user directives on a topic
+grep -i "database migration" <appDataDir>/brain/<conversation-id>/.system_generated/logs/transcript.jsonl
+
+# Extract all subagent tasks launched
+grep "invoke_subagent" <appDataDir>/brain/<conversation-id>/.system_generated/logs/transcript.jsonl
+```
+
+## 🏛️ Tribunal Verification & Guardrails
+
+### 🔬 Evidence Standard (Tri-State Verification)
+Every finding, audit statement, or completion claim must classify its factual certainty:
+- **`[OBSERVED]`**: Directly confirmed in the codebase or verified via executed terminal command.
+- **`[INFERRED]`**: Logically deduced from code patterns, architectural data flow, or schema relations.
+- **`[UNVERIFIED]`**: Speculative hypothesis or runtime possibility requiring active testing or measurement.
+
+- **Active Reviewers:** `orchestrator`
+- **Evidence Standard:** Attribute past decisions explicitly as `[OBSERVED in session <id>]` vs current state.
+
+## 🚨 Edge-Case & Failure Mode Matrix
+
+| Scenario | Risk | Production Mitigation |
+|:---|:---|:---|
+| **Empty or Null Inputs** | Unhandled exception or unexpected rendering collapse | Enforce fallback guards, optional chaining, and explicit empty state handlers |
+| **Network Timeout / Latency** | Hanging operations or duplicate side-effects | Implement bounded abort controllers, exponential backoff, and idempotency keys |
+| **Concurrency / Race Conditions** | Stale state overwrite or inconsistent data mutations | Use atomic transactions, mutex locking, or cancel-on-resubmit controls |
+| **Invalid Schema / Malformed Payload** | Downstream runtime errors or security injection | Validate boundary payloads with Zod/Pydantic schemas prior to execution |
+| **Resource / Memory Saturation** | OOM errors, frame drops, or memory leaks | Clean up listeners, cancel active timers, and enforce pagination/virtualization |
+
+
+## 🤖 LLM-Specific Traps Table
+
+| Anti-Pattern | What AI Commonly Does Wrong | What Is Actually Correct |
+|:---|:---|:---|
+| **Hallucinated Tool Capabilities** | Assuming an external library or CLI command exists without verification | Run a verification check or verify package.json before referencing tools |
+| **Premature Completion Claim** | Declaring a task finished because code was generated without verification | Execute tests, linters, or terminal commands to provide concrete proof |
+| **Context Bloat Dumping** | Pasting entire multi-thousand-line files into prompt context | Extract targeted excerpts, symbols, and signatures to preserve tokens |