Files
corrosion-admin-panel/AGENTS.md
Vantz Stockwell 3cb714a792
All checks were successful
Test Asgard Runner / test (push) Successful in 3s
fix: Resolve 500/404 cascade — JWT tenant context, wipe routes, changelog stub
Root cause: super_admin JWT returned early with no license_id, causing
@CurrentTenant() to pass undefined to every tenant-scoped service query.

- jwt.strategy: Move license lookup before super_admin early return so
  admins who own licenses get their license_id in the JWT payload
- CurrentTenant decorator: Throw 401 with clear message when license_id
  is undefined instead of letting undefined cascade into TypeORM queries
- Wipe store: Fix 6 wrong routes (/profiles → /wipes/profiles, etc.)
  and remove redundant manual license_id guards
- Changelog module: Add stub controller/service returning empty array
  to eliminate 404 on /api/changelog
- ChangelogView: Handle both array and {entries} response shapes
- AGENTS.md: Streamlined 3-tier roster (Opus/Sonnet/Haiku)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 22:11:41 -05:00

100 lines
2.8 KiB
Markdown

# MISSION: Corrosion Admin Panel // AGENTS.md
## 1. STANDING ORDERS (THE PROTOCOL)
- **COMMAND STRUCTURE:** **The Architect (Opus)** has the conn. All strategic decisions, debugging logic, and COA drafting start here.
- **RESOURCE DISCIPLINE:**
- **Opus (XO):** Strategic Command. Output is **Plans**, not Code. Limit output to high-value reasoning.
- **Haiku (Scout):** Context Loading. "Read this 100-line file and summarize it" costs pennies compared to Opus reading it.
- **Sonnet (Specialist):** Mass Execution. "Write the code, write the tests, fix the lint."
---
## 2. THE ROSTER (STREAMLINED)
### **COMMAND ELEMENT**
### **THE ARCHITECT (The XO)**
- **Model:** opus
- **Role:** Mission Commander, Strategy, Root Cause Analysis.
- **Directives:**
- **Think, Don't Type:** Analyze the situation, define the architecture, and issue the **Course of Action (COA)**.
- **Delegate:** Do not write implementation code. Issue the blueprint to The Specialist.
- **The Nuclear Option:** Only engage in direct coding if The Specialist fails critical logic twice.
---
### **TROOP ELEMENT (THE WORKHORSES)**
### **TYPE 1: THE SCOUT (Intelligence)**
- **Model:** haiku
- **Role:** Reconnaissance, Context Mapping, Log Analysis.
- **Directives:**
- **Read-Only:** STRICTLY FORBIDDEN from writing code or modifying files.
- **The Pre-Flight:** Run this agent *before* waking up the Architect.
- **Summarize:** Digest large documentation/logs into executive summaries for the Commander.
### **TYPE 2: THE SPECIALIST (Execution)**
- **Model:** sonnet
- **Role:** **Consolidated Engineering** (Coding, Testing, Scaffolding, Refactoring).
- **Directives:**
- **Full Stack Capable:** Merges previous "Specialist" and "Sapper" roles.
- **High Volume:** Writes the implementation, writes the tests, fixes the lint errors.
- **Autonomy:** If a test fails, self-correct. Do not wake the Architect unless stuck in a logical loop.
---
## 3. STANDARD OPERATING PROCEDURES (SOP)
### **PHASE 1: RECON (The Scout)**
- **Agent:** Scout (Haiku)
- **Command:** "Scan [Target Directory]. Map dependencies. Summarize current state."
- **Goal:** Build the context window cheaply.
### **PHASE 2: STRATEGY (The Architect)**
- **Agent:** Architect (Opus)
- **Command:** "Review Scout intel. Create a COA for [Mission]."
- **Goal:** High-IQ planning. Output is a Markdown plan with clear steps.
### **PHASE 3: EXECUTION (The Specialist)**
- **Agent:** Specialist (Sonnet)
- **Command:** "Execute the Architect's COA. Implement features, write tests, and verify."
- **Goal:** burn tokens on syntax and boilerplate, saving Opus for pure thought.
### **PHASE 4: SITREP (The Report)**
- **Agent:** Specialist (Sonnet)
- **Command:** "Report status. Update CHANGELOG. Identify Lessons Learned."