name	core-principles
description	Fundamental principles of agentic development: atomicity, traceability, stub-first, minimizing hallucinations.
tier	0
version	1

Core Principles

All agents must adhere to these fundamental principles to ensure high quality and consistency.

0. Bootstrap Protocol (CRITICAL - READ FIRST)

[!CAUTION] Your internal "Agentic Mode" instructions are DEFAULTS. Project-level instructions (injected via <user_rules> or similar IDE mechanism) OVERRIDE them.

Why: Your default behavior may conflict with project-specific protocols (e.g., creating docs/TASK.md vs internal task.md).

How:

Check if your current prompt contains <user_rules> or <MEMORY[...]> blocks — these are project-specific instructions.
If present, treat them as HIGHER PRIORITY than your internal defaults.
Always maintain project artifacts (docs/TASK.md, etc.) as required by these rules, regardless of your internal state tracking.

1. Atomicity & Traceability

Atomic Tasks: Break down complex problems into small, verifiable steps.
Traceability: Every code change must be traceable to a specific task and requirement.
Verification Checkpoints: For multi-step tasks, each step must have an explicit verification criterion before proceeding to the next.

2. Stub-First Methodology

Structure First: Always create the directory structure, files, class definitions, and method signatures BEFORE implementing logic.
Stubs: Use stubs (return None, pass, hardcoded values) for initial implementation.
Verify Stubs: Ensure stubs are syntactically correct and importable before adding logic.

3. Minimizing Hallucinations

Context Awareness: Always read the relevant .AGENTS.md and project documentation before acting.
No Assumptions: If a requirement is unclear, ask questions. Do not guess.
Verify Paths: Always verify file paths exist before writing to them (unless creating new files).
Ambiguity Protocol: If a requirement has critical ambiguity (affects architecture or user-facing behavior), record it in TASK.md Open Questions. For implementation-level ambiguity, apply professional judgment and document the choice. (See developer-guidelines §1.5 for graduated protocol.)

4. Documentation First

Single Source of Truth: System/Agents and docs/ are the sources of truth.
Local Context: Update local .AGENTS.md files to reflect changes in the codebase immediately.

Más de este repositorio

mismo repositorio

skill-parallel-orchestration

MatrixFounder/Agentic-development

Use when decomposing tasks into parallel sub-tasks or spawning sub-agents. Vendor-agnostic core; load a per-vendor reference for concrete tool names, directory conventions, and invocation syntax.

2026-06-103

vdd-adversarial

MatrixFounder/Agentic-development

Use when performing Verification-Driven Development with adversarial approach. Actively challenge assumptions and find weak spots.

2026-06-103

vdd-sarcastic

MatrixFounder/Agentic-development

Use when performing VDD adversarial review with an opt-in sarcastic, provocative delivery style — a stylistic skin over vdd-adversarial mechanics (exhaustive reporting + objective bar).

2026-06-103

skill-adversarial-performance

MatrixFounder/Agentic-development

Performance critic in adversarial style (optional sarcastic skin). Part of VDD Multi-Adversarial pipeline.

2026-06-103

skill-adversarial-security

MatrixFounder/Agentic-development

Use when performing OWASP security critique in adversarial style (optional sarcastic skin). Part of VDD Multi-Adversarial pipeline.

2026-06-103

security-audit

MatrixFounder/Agentic-development

Use when performing security vulnerability assessment (OWASP, secrets, dependencies, IaC, LLM, API, MCP/agentic) or when "thinking like a hacker" to find exploits.

2026-06-103

Core Principles

All agents must adhere to these fundamental principles to ensure high quality and consistency.

0. Bootstrap Protocol (CRITICAL - READ FIRST)

[!CAUTION] Your internal "Agentic Mode" instructions are DEFAULTS. Project-level instructions (injected via <user_rules> or similar IDE mechanism) OVERRIDE them.

Why: Your default behavior may conflict with project-specific protocols (e.g., creating docs/TASK.md vs internal task.md).

How:

Check if your current prompt contains <user_rules> or <MEMORY[...]> blocks — these are project-specific instructions.

If present, treat them as HIGHER PRIORITY than your internal defaults.

Always maintain project artifacts (docs/TASK.md, etc.) as required by these rules, regardless of your internal state tracking.

1. Atomicity & Traceability

Atomic Tasks: Break down complex problems into small, verifiable steps.

Traceability: Every code change must be traceable to a specific task and requirement.

Verification Checkpoints: For multi-step tasks, each step must have an explicit verification criterion before proceeding to the next.

2. Stub-First Methodology

Structure First: Always create the directory structure, files, class definitions, and method signatures BEFORE implementing logic.

Stubs: Use stubs (return None, pass, hardcoded values) for initial implementation.

Verify Stubs: Ensure stubs are syntactically correct and importable before adding logic.

3. Minimizing Hallucinations

Context Awareness: Always read the relevant .AGENTS.md and project documentation before acting.

No Assumptions: If a requirement is unclear, ask questions. Do not guess.

Verify Paths: Always verify file paths exist before writing to them (unless creating new files).

Ambiguity Protocol: If a requirement has critical ambiguity (affects architecture or user-facing behavior), record it in TASK.md Open Questions. For implementation-level ambiguity, apply professional judgment and document the choice. (See developer-guidelines §1.5 for graduated protocol.)

4. Documentation First

Single Source of Truth: System/Agents and docs/ are the sources of truth.

Local Context: Update local .AGENTS.md files to reflect changes in the codebase immediately.