core-principles

A set of working rules for coding agents, covering small tasks, traceable changes, starting with simple placeholders, and avoiding made-up details.

In plain words
What is it for?
Use it to guide planning, implementation, verification, and handling of uncertain requirements.
Why use it?
It gives the agent a consistent way to work through changes and verify them without losing the project’s instructions.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/matrixfounder/agentic-development/core-principles
Any agent
npx skills add MatrixFounder/Agentic-development --skill core-principles
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 554 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00554
Opus 5 $0.00013 $0.00277
Sonnet 5 $0.00005 $0.00111
Haiku 4.5 $0.00003 $0.00055

Measured 2d ago against content hash 1f0b86b72145, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

core-principles scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agent/skills/core-principles/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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:

  1. Check if your current prompt contains <user_rules> or <MEMORY[...]> blocks — these are project-specific instructions.
  2. If present, treat them as HIGHER PRIORITY than your internal defaults.
  3. 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.)

Read the full file on GitHub · 44 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 44 lines · 26 tokens per session scan A 1f0b86b72145

Subscribe to this mod's changes

core-principles is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 26 tokens to every session and 554 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

claude-to-deerflow

Interact with DeerFlow AI agent platform via its HTTP API. Use this skill when the user wants to send messages or questions to DeerFlow for research/analysis, start a DeerFlow conversation thread, check DeerFlow status or health, list available models/skills/agents in DeerFlow, manage DeerFlow memory, upload files to…

bytedance/deer-flow · 111 tokens

find-skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

bytedance/deer-flow · 67 tokens

skill-reviewer

Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.

bytedance/deer-flow · 38 tokens

zeroclaw

Help users operate and interact with their ZeroClaw agent instance — through both the CLI (zeroclaw commands) and the REST/WebSocket gateway API. Use this skill whenever the user wants to: send messages to ZeroClaw, manage memory or cron jobs, check system status, configure channels or providers, hit the gateway API…

zeroclaw-labs/zeroclaw · 167 tokens

coordinate

Coordinate a small team of Qwen Code teammates with enforced read-only workers, an optional worktree-pinned writer, shared tasks, peer messages, and existing Agent View tabs. Invoke explicitly with /coordinate.

QwenLM/qwen-code · 43 tokens

build-monetized-app

Use when the task is building a new app on Eliza Cloud that earns money — chat apps, agent apps, MCP-backed tools, anything that calls the cloud's chat/messages/inference endpoints on behalf of users. Covers app registration, container deploy, markup configuration, affiliate header, app charge requests, x402 payment…

elizaOS/eliza · 126 tokens